CN111208821A

CN111208821A - Automobile automatic driving control method, device, automatic driving device and system

Info

Publication number: CN111208821A
Application number: CN202010094861.6A
Authority: CN
Inventors: 李华兰
Original assignee: Individual
Current assignee: Runtong Intelligent Technology Zhengzhou Co ltd
Priority date: 2020-02-17
Filing date: 2020-02-17
Publication date: 2020-05-29
Anticipated expiration: 2040-02-17
Also published as: CN111208821B; CN111942396A; CN111942396B; CN111880545A

Abstract

The embodiment of the application provides an automobile automatic driving control method, an automobile automatic driving control device, an automobile automatic driving device and an automobile automatic driving control system, status information under each monitoring area is divided according to preset status categories, status summary information of each status category is generated respectively, so that differences of driving objects in different status categories in the automatic driving process can be fully considered, characteristic status differences of different drivers are effectively distinguished, floating changes of area characteristic points of the drivers in the automatic driving process are considered, automatic driving decisions are further made by further combining historical driving conditions of the drivers, and data accuracy of an automatic driving strategy decision process can be improved.

Description

Automobile automatic driving control method and device, automatic driving device and system

Technical Field

The application relates to the technical field of automatic driving, in particular to an automatic driving control method and device for an automobile, an automatic driving device and an automatic driving system.

Background

With the development of science and technology and the progress of society, the automatic driving technology becomes a development trend in the traffic field, in the conventional automatic driving technology, a unified feature class is generally output to adaptively adjust the automatic driving strategy by combining the overall feature state of the driver, but the scheme does not consider the difference of the driver for different state classes in the automatic driving process, and the driver is generally required to be in a driving state in the automatic driving process in order to improve the driving safety, however, the difference of the feature states of different drivers is large because the driving habits of different drivers are different and the feature states of the drivers are fluctuated, so that the decision process of the automatic driving strategy is not sufficient.

Disclosure of Invention

In order to overcome the defects in the prior art, the present application aims to provide an automatic driving control method, an automatic driving control device, an automatic driving device and an automatic driving control system for an automobile, which can improve the data accuracy of a decision process of an automatic driving strategy.

In a first aspect, the present application provides an automatic driving control method for an automobile, applied to an automatic driving device, where the automatic driving device is in communication connection with a plurality of state monitoring devices in the automobile, and the method includes:

acquiring state information of a driving object in a monitoring area of each state monitoring device, dividing the state information in each monitoring area according to a preset state category, and respectively generating state summary information of each state category;

determining preset area feature points in each monitoring area according to the identity authentication information of the driving object, and respectively determining floating change information of a floating area of the preset area feature points in state summary information of corresponding state types aiming at the preset area feature points in each monitoring area to obtain a first state floating change result of the preset area feature points, wherein the preset area feature points are area feature points which are matched with the identity authentication information of the driving object in advance;

determining frequent region feature points in each monitoring region according to historical driving information of the driving object, respectively obtaining floating tracks of the frequent region feature points aiming at the frequent region feature points in each monitoring region, determining floating change information of the floating tracks in state summarizing information of corresponding state types, and obtaining a second state floating change result of the frequent region feature points, wherein the frequent region feature points are region feature points of which the change frequency in the historical driving information of the driving object is greater than a set frequency threshold value, and the change frequency is used for expressing the change degree of the region feature points in unit time;

and generating an automatic driving control instruction for the automobile according to the matching relation between the first state floating change result and the second state floating change result.

In a possible design of the first aspect, the step of dividing the status information in each monitoring area according to a predetermined status category and generating status summary information of each status category includes:

acquiring state category characteristic points corresponding to each preset state category, forming a characteristic point set of each preset state category, and acquiring coincidence characteristic point information of the target characteristic points of each monitoring area and the characteristic points of the characteristic point set;

calculating the number of key feature points of each target state category according to the superposition feature point information of the target feature point number and the feature point number of the feature point set, and selecting state category feature points from the feature point set according to the number of the key feature points of each target state category to obtain an initial feature point matrix;

if the total feature point distribution quantity of the initial feature point matrix is greater than the maximum total feature point distribution quantity meeting the total feature point distribution quantity requirement, reducing the coarse-range key feature points in the initial feature point matrix by a first set quantity, and increasing the fine-range key feature points in the initial feature point matrix by the first set quantity, wherein the fine-range key feature points refer to key feature points of which the unit intensity degree of the key feature points in the detection area is less than the set degree, and the coarse-range key feature points refer to key feature points of which the unit intensity degree of the key feature points in the detection area is not less than the set degree;

calculating the total characteristic point distribution quantity of the updated initial characteristic point matrix;

if the total characteristic point distribution quantity of the initial characteristic point matrix after the updating is larger than the maximum total characteristic point distribution quantity, the initial characteristic point matrix after the updating is executed with the processing again;

if the total feature point distribution quantity of the initial feature point matrix after the updating is less than or equal to the maximum total feature point distribution quantity, taking the initial feature point matrix before the updating as a first updating matrix, and sequencing all the target state classes according to the sequence of the state classes from low priority to high priority to obtain a target state class sequence;

grouping the target state categories according to the target state category sequence, wherein each group comprises a first state category and a second state category which are arranged at two sides of a target position of the target state category sequence and consistent with the difference of the target position, and the priority of the first state category is smaller than that of the second state category;

and according to the sequence from low priority to high priority of the difference with the target position, sequentially taking each packet as a target packet, and performing the following second updating processing on the target packet: adding one more key feature point of a first state category of the target group in the first update matrix, and reducing one less key feature point of a second state category of the target group in the first update matrix;

judging whether the total characteristic point distribution quantity of the updated first updating matrix meets the total characteristic point distribution quantity requirement or not;

if the total characteristic point distribution quantity of the updated first updating matrix meets the total characteristic point distribution quantity requirement, taking the updated first updating matrix as a final characteristic point matrix;

if the total characteristic point distribution quantity of the updated first updating matrix does not meet the total characteristic point distribution quantity requirement, taking the next group as a new target group, and performing the second updating processing on the new target group;

if the total feature point distribution quantity of the initial feature point matrix is less than the minimum total feature point distribution quantity meeting the total feature point distribution quantity requirement, performing the following third updating processing on the initial feature point matrix: increasing the coarse range key feature points in the initial feature point matrix by a first set number, and decreasing the fine range key feature points in the initial feature point matrix by the first set number;

if the total characteristic point distribution quantity of the initial characteristic point matrix after the updating is less than the minimum total characteristic point distribution quantity, executing the third updating treatment on the initial characteristic point matrix after the updating again;

if the total feature point distribution quantity of the initial feature point matrix after the updating is greater than or equal to the minimum total feature point distribution quantity, taking the initial feature point matrix before the updating as a second updating matrix, and sequencing all the target state classes according to the sequence of the state classes from low priority to high priority to obtain a target state class sequence;

and sequentially taking each packet as a target packet according to the sequence from low priority to high priority of the difference with the target position, and performing the following fourth updating processing on the target packet: reducing the key feature points of the first state category of the target grouping in the second update matrix by one, and increasing the key feature points of the second state category of the target grouping in the second update matrix by one;

judging whether the total characteristic point distribution quantity of the second updated matrix after the updating meets the total characteristic point distribution quantity requirement or not;

if the total feature point distribution quantity of the second updated matrix meets the total feature point distribution quantity requirement, taking the second updated matrix as the final feature point matrix;

if the total feature point distribution quantity of the second updated matrix after the updating does not meet the total feature point distribution quantity requirement, taking the next group as a new target group, and performing the fourth updating processing on the new target group;

and classifying the state information of each feature point in the final feature point matrix of each target state category into the state summary information of the state category.

In a possible design of the first aspect, the identification information includes biometric information, and the step of determining preset area feature points in each monitored area according to the identification information of the driving object includes:

collecting biological characteristic information of the driving object;

and obtaining preset area characteristic points in each monitoring area according to the biological characteristic information and the corresponding relation between each preset area characteristic point in each detection area and each preset biological characteristic information configured in advance.

In a possible design of the first aspect, the step of obtaining a first state floating change result of the preset area feature point by determining floating change information of the floating area of the preset area feature point in the state summary information of the corresponding state category for the preset area feature point in the monitoring area includes:

respectively acquiring three-dimensional fixed points matched with the preset region feature points aiming at the preset region feature points in each monitoring region, and acquiring a corresponding three-dimensional space region as a target three-dimensional space region when the three-dimensional fixed points continuously fall into a coordinate range corresponding to one three-dimensional space region in the monitoring region within a preset time period;

judging whether the area range of the target three-dimensional space area is the same as the area range input by a preset automatic driving control model;

if the area ranges are different, the area range of the target three-dimensional space area is zoomed to a three-dimensional space area which is consistent with the area range input by the model of the automatic driving control model, and the area range is input into the automatic driving control model;

calculating an input three-dimensional space region by adopting the automatic driving control model, and acquiring floating change information corresponding to the input three-dimensional space region;

tracking each floating position of the preset region characteristic points in the target three-dimensional space region to obtain a floating characteristic vector of each floating position in the target three-dimensional space region;

determining a region with the floating position frequency greater than a preset threshold value in the floating change information corresponding to the input three-dimensional space region as a floating region;

converting the vector value of each floating position in the input three-dimensional space region to obtain a floating feature vector of each floating position in the input three-dimensional space region;

calculating a first floating vector mean value of the whole three-dimensional space region according to the floating feature vector of each floating position in the target three-dimensional space region;

calculating a second floating vector mean value of the floating region according to the floating feature vector of each floating position in the floating region;

calculating the first floating vector mean value, the second floating vector mean value and a preset coefficient to obtain a floating reference coefficient of the floating region, calculating a ratio of a floating feature vector of each floating position in the target three-dimensional space region to the floating reference coefficient, and obtaining a first floating strength of each floating position in the target three-dimensional space region according to the ratio;

calculating the first floating intensity and the floating change information of each floating position in the target three-dimensional space region to obtain the floating intensity of each floating position in the target three-dimensional space region;

or, calculating a ratio of a floating feature vector of each floating position in the target three-dimensional space region to the floating reference coefficient to obtain a first floating strength of each floating position in the target three-dimensional space region, calculating the first floating strength of each floating position in the target three-dimensional space region according to a preset floating range to obtain a second floating strength of each floating position in the target three-dimensional space region, wherein a difference value between the second floating strength and the first floating strength is smaller than the preset floating range, calculating the second floating strength of each floating position in the target three-dimensional space region and the floating change information to obtain the floating strength of each floating position in the target three-dimensional space region;

determining a target coefficient of each floating position in the target three-dimensional space region according to a target feature point, floating strength and the floating change information of a specified space position, and calculating a ratio of the floating strength of each floating position in the target three-dimensional space region to a preset constant, wherein the target coefficient is a value obtained by multiplying a feature vector value of the target feature point of the specified space position by the floating strength and dividing the feature vector value by the floating change information;

calculating the product of the ratio of the floating strength of each floating position to a preset constant and a corresponding target coefficient, and obtaining a first state floating result of each floating position in the target three-dimensional space region;

performing color editing processing on the target three-dimensional space region according to the first state floating result of each floating position to output the target three-dimensional space region;

or calculating the ratio of the floating intensity of each floating position in the target three-dimensional space region to a preset constant;

calculating the product of the ratio of the floating intensity of each floating position to a preset constant and the corresponding target dyeing value, and obtaining a first state floating result of each floating position in the target three-dimensional space region;

calculating a first state floating result of each floating position in the target three-dimensional space region, the target three-dimensional space region and the floating change information to obtain a second state floating result of each floating position in the target three-dimensional space region;

and arranging the second state floating results of each floating position to obtain a first state floating change result of the preset region characteristic point.

In a possible design of the first aspect, the step of determining frequent region feature points in each monitored region according to the historical driving information of the driving object includes:

acquiring historical driving information of the driving object, wherein the historical driving information comprises a plurality of position change information corresponding to a plurality of area characteristic points respectively;

when it is determined that a plurality of position change information corresponding to any one area feature point all meet a preset position change condition, determining an initial position of a first position change interval matched with the preset position change condition according to the position change information of the area feature point and the amplitude of the position change interval, wherein the preset position change condition comprises: the position change amplitude is larger than a set amplitude threshold value;

determining a plurality of position change intervals matched with the preset position change condition corresponding to the initial positions of the area feature points according to the position change information of the area feature points, the amplitude of the position change intervals, the initial position of the first position change interval and the number of preset position change intervals;

if the position of the area characteristic point of the tracking node corresponding to the area characteristic point in the area characteristic point is matched with the initial position of a target position change interval, and if the tracking node is the first tracking node of the target position change interval, acquiring the area characteristic point matched with the previous position change interval adjacent to the target position change interval as a screening area characteristic point, and identifying one area characteristic point without the screening area characteristic point in the tracking node as a target area characteristic point matched with the target position change interval;

if the tracking node is not the first tracking node of the target position change interval, acquiring a target area characteristic point matched with the target position change interval, identifying the target area characteristic point in the tracking node, and identifying at least one active position node of the target area characteristic point, wherein the area characteristic point corresponds to a plurality of position change intervals;

in the position change interval, according to the position information of at least one active position node of the target area feature point in the plurality of tracking nodes, calculating the moving space distance of any two adjacent tracking nodes of the at least one active position node of the target area feature point in the position change interval, and the position vector of the at least one active position node of the target area feature point in the position change interval;

counting the duration of the position change interval, determining the average change frequency and the change frequency variance of the target area feature point in the position change interval according to the movement space distance and the position vector, and calculating the frequent feature parameter of the target area feature point in the position change interval according to the average change frequency and the change frequency variance;

and calculating the frequent feature score of each region feature point according to the frequent feature parameter of each region feature point in the matched position change interval, and determining the region feature point with the frequent feature score larger than the set score as the frequent region feature point.

In a possible design of the first aspect, the step of generating an autopilot control command for the vehicle according to a matching relationship between the first state floating change result and the second state floating change result includes:

matching the state floating result of each first floating position in the first state floating change results with the state floating result of each matched second floating position in the second state floating change results to obtain a plurality of matching degrees, wherein each matched second floating position in the second state floating change results is matched with the corresponding first floating position in the arrangement sequence of the state floating change results, and the matching degrees are determined according to the coincidence degree between the state floating results of the first floating positions and the state floating results of the matched second floating positions;

and generating an automatic driving control instruction for the automobile according to the matching degrees.

In one possible design of the first aspect, the step of generating an automatic driving control instruction for the automobile according to the plurality of matching degrees includes:

determining a first number of the plurality of matching degrees which is lower than a first set matching degree, a second number which is greater than a second set matching degree and a third number of intervals between the first set matching degree and the second set matching degree;

if the first number is larger than the sum of the second number and the third number, generating a first automatic driving control instruction for the automobile, wherein the first automatic driving control instruction is used for controlling the automobile to enter a preset deceleration mode;

if the third quantity is larger than the sum of the first quantity and the second quantity, generating a second automatic driving control instruction for the automobile, wherein the second automatic driving control instruction is used for controlling the automobile to enter a preset acceleration mode;

and if the second quantity is greater than the sum of the first quantity and the third quantity, generating a third automatic driving control instruction for the automobile, wherein the third automatic driving control instruction is used for controlling the automobile to enter a preset constant speed mode.

In a second aspect, an embodiment of the present application further provides an automatic driving control device for an automobile, where the automatic driving control device is applied to an automatic driving device, the automatic driving device is in communication connection with a plurality of state monitoring devices in the automobile, and the device includes:

the acquisition module is used for acquiring the state information of the driving object in the monitoring area of each state monitoring device, dividing the state information in each monitoring area according to the preset state category and respectively generating the state summary information of each state category;

the first determining module is used for determining preset area characteristic points in each monitoring area according to the identity authentication information of the driving object, and respectively determining floating change information of a floating area of the preset area characteristic points in state summarizing information of corresponding state types aiming at the preset area characteristic points in each monitoring area to obtain a first state floating change result of the preset area characteristic points, wherein the preset area characteristic points are area characteristic points which are matched with the identity authentication information of the driving object in advance;

a second determining module, configured to determine frequent region feature points in each monitored region according to historical driving information of the driving object, obtain, for the frequent region feature points in each monitored region, floating tracks of the frequent region feature points, respectively, determine floating change information of the floating tracks in state summary information of corresponding state types, and obtain a second state floating change result of the frequent region feature points, where the frequent region feature points are region feature points whose change frequency in the historical driving information of the driving object is greater than a set frequency threshold, and the change frequency is used to indicate a change degree of the region feature points in unit time;

and the generating module is used for generating an automatic driving control instruction for the automobile according to the matching relation between the first state floating change result and the second state floating change result.

In a third aspect, an embodiment of the present application further provides an automatic driving system, where the automatic driving system includes an automatic driving device and a plurality of state monitoring devices in an automobile communicatively connected to the automatic driving device, and the method includes:

the state monitoring device is used for monitoring state information of the driving object in the monitored area;

the automatic driving device is used for acquiring the state information of the driving object in the monitoring area of each state monitoring device, dividing the state information in each monitoring area according to the preset state category and respectively generating the state summarizing information of each state category;

the automatic driving device is used for determining preset area characteristic points in each monitoring area according to the identity authentication information of the driving object, respectively determining floating change information of a floating area of the preset area characteristic points in state summarizing information of corresponding state types aiming at the preset area characteristic points in each monitoring area, and obtaining a first state floating change result of the preset area characteristic points, wherein the preset area characteristic points are area characteristic points which are matched with the identity authentication information of the driving object in advance;

the automatic driving device is used for determining frequent region feature points in each monitoring region according to historical driving information of the driving object, respectively acquiring floating tracks of the frequent region feature points aiming at the frequent region feature points in each monitoring region, determining floating change information of the floating tracks in state summary information of corresponding state types, and obtaining a second state floating change result of the frequent region feature points, wherein the frequent region feature points are region feature points of which the change frequency in the historical driving information of the driving object is greater than a set frequency threshold value, and the change frequency is used for expressing the change degree of the region feature points in unit time;

and the automatic driving device is used for generating an automatic driving control instruction for the automobile according to the matching relation between the first state floating change result and the second state floating change result.

In a fourth aspect, the present invention further provides an automatic driving device, where the automatic driving device includes a processor, a machine-readable storage medium, and a network interface, where the machine-readable storage medium, the network interface, and the processor are connected through a bus system, the network interface is configured to be communicatively connected to at least one condition monitoring device, the machine-readable storage medium is configured to store a program, an instruction, or a code, and the processor is configured to execute the program, the instruction, or the code in the machine-readable storage medium to perform the automatic driving control method for an automobile in the first aspect or any one of the possible designs in the first aspect.

In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are detected on an automatic driving device, the instructions cause the automatic driving device to execute the automatic driving control method for a vehicle in the first aspect or any one of the possible designs of the first aspect.

Based on any one of the above aspects, the status information in each monitoring area is divided according to the predetermined status category, and the status summary information of each status category is generated respectively, so that the difference of the driving object in the automatic driving process for different status categories can be fully considered, and the characteristic status difference of different drivers can be effectively distinguished, so that the floating change of the area characteristic point of the driver in the automatic driving process is considered, the automatic driving decision is further performed by combining the historical driving condition of the driver, and the data accuracy of the decision process of the automatic driving strategy can be improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.

Fig. 1 is a schematic view of an application scenario of an automatic driving system according to an embodiment of the present application;

FIG. 2 is a schematic flow chart illustrating an automatic driving control method for a vehicle according to an embodiment of the present disclosure;

FIG. 3 is a functional block diagram of an automatic driving control device of a vehicle according to an embodiment of the present disclosure;

fig. 4 is a block diagram schematically illustrating a structure of an automatic driving apparatus for implementing the automatic driving control method of the vehicle according to the embodiment of the present application.

Detailed Description

The present application will now be described in detail with reference to the drawings, and the specific operations in the method embodiments may also be applied to the apparatus embodiments or the system embodiments. In the description of the present application, "at least one" includes one or more unless otherwise specified. "plurality" means two or more. For example, at least one of A, B and C, comprising: a alone, B alone, a and B in combination, a and C in combination, B and C in combination, and A, B and C in combination.

Fig. 1 is an interactive schematic diagram of an autopilot system 10 provided in an embodiment of the present application. The autopilot system 10 may include an autopilot device 100 and a condition monitoring device 200 communicatively coupled to the autopilot device 100, and the autopilot device 100 may include a processor for executing command operations. The autopilot system 10 shown in fig. 1 is merely one possible example, and in other possible embodiments, the autopilot system 10 may include only some of the components shown in fig. 1 or may include additional components.

In some embodiments, the autopilot device 100 may be a single autopilot device or a group of autopilot devices. The set of autopilot units may be centralized or distributed. In some embodiments, the autopilot device 100 may be local or remote with respect to the condition monitoring device 200. For example, the autopilot device 100 may access information stored in the condition monitoring device 200 and a database, or any combination thereof, via a network. As another example, the autopilot device 100 may be directly connected to at least one of the condition monitoring device 200 and a database to access information and/or data stored therein.

In some embodiments, the autopilot device 100 may include a processor. The processor may process information and/or data related to the service request to perform one or more of the functions described herein. A processor may include one or more processing cores (e.g., a single-core processor (S) or a multi-core processor (S)). Merely by way of example, a Processor may include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), an Application Specific Instruction Set Processor (ASIP), a Graphics Processing Unit (GPU), a Physical Processing Unit (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), a controller, a microcontroller Unit, a reduced Instruction Set computer (reduced Instruction Set computer), a microprocessor, or the like, or any combination thereof.

The network may be used for the exchange of information and/or data. In some embodiments, one or more components in the autopilot system 10 (e.g., autopilot device 100, condition monitoring device 200, and a database) may send information and/or data to other components. In some embodiments, the network may be any type of wired or wireless network, or combination thereof. Merely by way of example, Network 130 may include a wired Network, a Wireless Network, a fiber optic Network, a telecommunications Network, an intranet, the internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a WLAN, a Metropolitan Area Network (MAN), a Wide Area Network (WAN), a Public Switched Telephone Network (PSTN), a bluetooth Network, a ZigBee Network, a Near Field Communication (NFC) Network, or the like, or any combination thereof. In some embodiments, the network may include one or more network access points. For example, the network may include wired or wireless network access points, such as base stations and/or network switching nodes, through which one or more components of the autopilot system 10 may connect to the network to exchange data and/or information.

The aforementioned database may store data and/or instructions. In some embodiments, the database may store data assigned to condition monitoring device 200. In some embodiments, the database may store data and/or instructions for the exemplary methods described herein. In some embodiments, the database may include mass storage, removable storage, volatile Read-write Memory, or Read-Only Memory (ROM), among others, or any combination thereof. By way of example, mass storage may include magnetic disks, optical disks, solid state drives, and the like; removable memory may include flash drives, floppy disks, optical disks, memory cards, zip disks, tapes, and the like; volatile read-write memory may include Random Access Memory (RAM); the RAM may include Dynamic RAM (DRAM), Double data Rate Synchronous Dynamic RAM (DDR SDRAM); static RAM (SRAM), Thyristor-Based Random Access Memory (T-RAM), Zero-capacitor RAM (Zero-RAM), and the like. By way of example, ROMs may include Mask Read-Only memories (MROMs), Programmable ROMs (PROMs), Erasable Programmable ROMs (PERROMs), Electrically Erasable Programmable ROMs (EEPROMs), compact disk ROMs (CD-ROMs), digital versatile disks (ROMs), and the like.

In some embodiments, a database may be connected to a network to communicate with one or more components in the autopilot system 10 (e.g., autopilot device 100, condition monitoring device 200, etc.). One or more components in the autopilot system 10 may access data or instructions stored in a database via a network. In some embodiments, the database may be directly connected to one or more components of the autopilot system 10 (e.g., autopilot device 100, condition monitoring device 200, etc.; or, in some embodiments, the database may be part of autopilot device 100.

In this embodiment, the status monitoring device 200 may be various monitoring sensors (e.g., a gravity sensor, a biometric sensor, an iris sensor, a motion sensor, etc.), and this embodiment is not limited in this respect.

To solve the technical problem in the foregoing background art, fig. 2 is a schematic flow chart of an automatic driving control method for a vehicle according to an embodiment of the present application, which can be executed by the automatic driving apparatus 100 shown in fig. 1, and the automatic driving control method for a vehicle is described in detail below.

Step S110 is to acquire the status information of the driving object in the monitoring area of each status monitoring device, and divide the status information in each monitoring area according to the predetermined status category to generate status summary information of each status category.

Step S120, determining preset area characteristic points in each monitoring area according to the identity authentication information of the driving object, and respectively determining the floating change information of the floating area of the preset area characteristic points in the state summarizing information of the corresponding state types aiming at the preset area characteristic points in each monitoring area to obtain a first state floating change result of the preset area characteristic points.

Step S130, determining frequent region characteristic points in each monitoring region according to historical driving information of the driving object, respectively obtaining the floating tracks of the frequent region characteristic points aiming at the frequent region characteristic points in each monitoring region, determining the floating change information of the floating tracks in the state summarizing information of the corresponding state types, and obtaining a second state floating change result of the frequent region characteristic points.

And step S140, generating an automatic driving control instruction for the automobile according to the matching relation between the first state floating change result and the second state floating change result.

In this embodiment, for each condition monitoring device, the corresponding monitoring area may be allocated according to a preset design requirement and a specific function of the condition monitoring device, so that the condition monitoring device monitors only the condition information of the driving object in the corresponding monitoring area. For example, for a driving object, each feature region of the head, each joint feature region of the hand, a neck feature region, a leg region, and the like may be individually designed to correspond to a detection region, and a related state monitoring device may be provided to correspond to the detection region to monitor state information of the driving object.

In this embodiment, the preset area feature point may be an area feature point that is matched with the identity authentication information of the driving object in advance. In detail, different preset region feature points corresponding to different driving subjects (for example, the elderly, the middle aged, or the males, the females) may be preset according to different driving habits.

In this embodiment, the predetermined category may be determined according to the function of the vehicle, and may include, for example, a clutch operation category, a steering wheel operation category, an electrical device control category, and the like, which is not specifically limited herein.

In this embodiment, the frequent region feature point may be a region feature point in which the change frequency in the historical driving information of the driving target is greater than a set frequency threshold, and the change frequency may be used to indicate the change degree of the region feature point in unit time.

Based on the above design, in the present embodiment, the status information in each monitoring area is divided according to the predetermined status category, and the status summary information of each status category is generated respectively, so that the difference of the driving object in the automatic driving process for different status categories can be fully considered, and the characteristic status difference of different drivers can be effectively distinguished, so that the floating change of the area characteristic point of the driver in the automatic driving process is considered, and thus the automatic driving decision is performed in further combination with the historical driving condition of the driver, and the data accuracy of the decision process of the automatic driving strategy can be improved.

In a possible design, for step S110, in the process of dividing the status information in each monitoring area, in order to improve the accuracy of the division and reduce redundant information to improve the decision efficiency, this embodiment may obtain status category feature points corresponding to each predetermined status category, form a feature point set of each predetermined status category, and obtain the coincidence feature point information of the target feature point number of each monitoring area and the feature point number of the feature point set. For example, the state category feature points under the clutch operation category, the steering wheel operation category and the electrical device control category may be acquired respectively for the clutch operation category, the steering wheel operation category and the electrical device control category, for example, the state category feature points under the clutch operation category may include part specific feature points of legs, and the state category feature points under the steering wheel operation category may include part specific feature points of hands, feature points of eyes, and the like. That is, the state class feature point corresponding to each predetermined state class may be used to implement the coordination of the operation process corresponding to the predetermined state class.

On the basis, the number of the key feature points of each target state category can be calculated according to the superposition feature point information of the target feature point number and the feature point number of the feature point set, and the state category feature points are selected from the feature point set according to the number of the key feature points of each target state category to obtain an initial feature point matrix.

For example, if the total feature point distribution number of the initial feature point matrix is greater than the maximum total feature point distribution number that satisfies the total feature point distribution number requirement, the coarse-range key feature points in the initial feature point matrix are decreased by a first set number, and the fine-range key feature points in the initial feature point matrix are increased by a first set number.

As one possible design, the narrow-range key feature points may be key feature points whose unit density of the detection area where the key feature points are located is less than a set level, and the wide-range key feature points may be key feature points whose unit density of the detection area where the key feature points are located is not less than the set level.

Therefore, the total feature point distribution number of the initial feature point matrix updated this time can be calculated, and then the next processing operation is executed according to the total feature point distribution number, and several possible examples will be given below to further explain the embodiment in detail.

For example, if the total feature point distribution number of the initial feature point matrix updated this time is greater than the maximum total feature point distribution number, the above processing is performed on the initial feature point matrix updated this time again.

For another example, if the total feature point distribution number of the initial feature point matrix after the current update is less than or equal to the maximum total feature point distribution number, the initial feature point matrix before the current update is used as the first update matrix, and the target state categories are sorted in the order from low priority to high priority of the state categories, so as to obtain the target state category sequence.

Then, the target state categories may be grouped according to the target state category sequence, each group including a first state category and a second state category which are on both sides of the target position of the target state category sequence and which are consistent with a difference between the target positions, the priority of the first state category being smaller than the priority of the second state category.

Then, each packet may be sequentially used as a target packet in an order from a low priority to a high priority in the gap from the target position, and the following second update processing may be performed on the target packet: and increasing one key feature point of the first state category of the target group in the first updating matrix, and decreasing one key feature point of the second state category of the target group in the first updating matrix.

On the basis, whether the total feature point distribution quantity of the updated first updating matrix meets the requirement of the total feature point distribution quantity can be further judged.

And if the total characteristic point distribution quantity of the updated first updating matrix meets the requirement of the total characteristic point distribution quantity, taking the updated first updating matrix as a final characteristic point matrix.

And if the total feature point distribution quantity of the updated first updating matrix does not meet the total feature point distribution quantity requirement, taking the next group as a new target group, and performing second updating processing on the new target group.

If the total feature point distribution quantity of the initial feature point matrix is less than the minimum total feature point distribution quantity meeting the total feature point distribution quantity requirement, performing the following third updating processing on the initial feature point matrix: the coarse-range key feature points in the initial feature point matrix are increased by a first set number, and the fine-range key feature points in the initial feature point matrix are decreased by the first set number.

On the basis, the total distribution quantity of the feature points of the initial feature point matrix after the updating can be further calculated.

And if the total characteristic point distribution quantity of the initial characteristic point matrix after the updating is less than the minimum total characteristic point distribution quantity, executing third updating processing on the initial characteristic point matrix after the updating again.

And if the total characteristic point distribution quantity of the initial characteristic point matrix after the updating is greater than or equal to the minimum total characteristic point distribution quantity, taking the initial characteristic point matrix before the updating as a second updating matrix, and sequencing all target state types according to the sequence of the state types from low priority to high priority to obtain a target state type sequence.

On this basis, the target state categories can be further grouped according to the target state category sequence, each group comprises a first state category and a second state category which are arranged on two sides of the target position of the target state category sequence and consistent with the difference of the target position, and the priority of the first state category is smaller than that of the second state category.

Then, according to the sequence from low priority to high priority of the difference with the target position, taking each packet as a target packet in turn, and performing the following fourth updating processing on the target packet: and reducing the key feature points of the first state category of the target group in the second updating matrix by one, and increasing the key feature points of the second state category of the target group in the second updating matrix by one.

On the basis, whether the total feature point distribution quantity of the second updated matrix after the updating meets the requirement of the total feature point distribution quantity can be further judged.

And if the total characteristic point distribution quantity of the second updated matrix after the updating meets the requirement of the total characteristic point distribution quantity, taking the second updated matrix after the updating as a final characteristic point matrix.

And if the total feature point distribution quantity of the second updated matrix after the updating does not meet the total feature point distribution quantity requirement, taking the next group as a new target group, and performing fourth updating processing on the new target group.

Therefore, the state information of each feature point in the final feature point matrix of each target state category can be classified into the state summary information of the state category.

Based on the design, the dividing accuracy in the process of dividing the state information in each monitoring area can be improved, and redundant information is reduced to improve the decision efficiency.

In one possible design, for step S120, the identity authentication information may include biometric information, such as fingerprint feature information, face feature information, iris feature information, voice feature information, and the like, which is not specifically limited herein, and one or more combinations of the biometric information and the voice feature information may be flexibly selected according to actual hardware components in the automobile, and when a plurality of combinations are selected, the accuracy of identity verification may be improved. On the basis, when the driving object is recognized to sit at the driving position, the biological characteristic information of the driving object can be collected, and the preset area characteristic points in each monitoring area are obtained according to the biological characteristic information and the corresponding relation between each piece of biological characteristic information which is configured in advance and the preset area characteristic points in each detection area.

In a possible design, for step S120, in order to accurately determine the first state floating change result of the preset region feature point and avoid the influence of the inertial floating feature on the result in the position floating process, in this embodiment, for the preset region feature point in each monitoring region, a three-dimensional fixed point matched with the preset region feature point is respectively obtained, and a three-dimensional space region corresponding to the three-dimensional fixed point when the three-dimensional fixed point continuously falls within a coordinate range corresponding to one three-dimensional space region in the monitoring region in a preset time period is obtained as the target three-dimensional space region.

On the basis, whether the area range of the target three-dimensional space area is the same as the area range input by the preset automatic driving control model is further judged.

If the area ranges are different, the area range of the target three-dimensional space area is zoomed to a three-dimensional space area which is consistent with the area range input by the model of the automatic driving control model, and the area range is input into the automatic driving control model.

Then, an automatic driving control model is adopted to calculate the input three-dimensional space region, floating change information corresponding to the input three-dimensional space region is obtained, each floating position of a preset region feature point in the target three-dimensional space region is tracked, a floating feature vector of each floating position in the target three-dimensional space region is obtained, and then a region, with the floating position frequency being larger than a preset threshold value, in the floating change information corresponding to the input three-dimensional space region is determined as a floating region.

Then, the vector value of each floating position in the input three-dimensional space region can be converted to obtain the floating feature vector of each floating position in the input three-dimensional space region, the first floating vector mean value of the whole three-dimensional space region is calculated according to the floating feature vector of each floating position in the target three-dimensional space region, and the second floating vector mean value of the floating region is calculated according to the floating feature vector of each floating position in the floating region. Then, calculating the first floating vector mean value, the second floating vector mean value and a preset coefficient to obtain a floating reference coefficient of the floating region, calculating the ratio of the floating feature vector of each floating position in the target three-dimensional space region to the floating reference coefficient, obtaining the first floating strength of each floating position in the target three-dimensional space region according to the ratio, and then calculating the first floating strength and the floating change information of each floating position in the target three-dimensional space region to obtain the floating strength of each floating position in the target three-dimensional space region.

Or, in another possible design, the embodiment may further calculate a ratio of the floating feature vector of each floating position in the target three-dimensional space region to the floating reference coefficient to obtain a first floating strength of each floating position in the target three-dimensional space region, calculate the first floating strength of each floating position in the target three-dimensional space region according to a preset floating range, obtain a second floating strength of each floating position in the target three-dimensional space region, where a difference between the second floating strength and the first floating strength is smaller than the preset floating range, calculate the second floating strength and the floating change information of each floating position in the target three-dimensional space region, and obtain the floating strength of each floating position in the target three-dimensional space region.

Therefore, the present embodiment may determine a target coefficient of each floating position in the target three-dimensional space region according to the target feature point of the specified space position, the floating strength, and the floating change information, and calculate a ratio of the floating strength of each floating position in the target three-dimensional space region to a preset constant, where the target coefficient may be a value obtained by multiplying the feature vector value of the target feature point of the specified space position by the floating strength and dividing the multiplied value by the floating change information.

And then, calculating the product of the ratio of the floating strength of each floating position to a preset constant and the corresponding target coefficient, and obtaining the first state floating result of each floating position in the target three-dimensional space region.

And then, carrying out color editing processing on the target three-dimensional space area according to the first state floating result of each floating position to output the target three-dimensional space area.

Or, in another case, the embodiment may also calculate a ratio of the floating intensity of each floating position in the target three-dimensional space region to a preset constant, and calculate a product of the ratio of the floating intensity of each floating position to the preset constant and the corresponding target dyeing value, so as to obtain the first state floating result of each floating position in the target three-dimensional space region.

Therefore, the embodiment can calculate the first state floating result of each floating position in the target three-dimensional space region, the target three-dimensional space region and the floating change information, obtain the second state floating result of each floating position in the target three-dimensional space region, and arrange the second state floating results of each floating position to obtain the first state floating change result of the preset region feature point.

In a possible design, regarding step S130, in order to improve the situation and increase the accuracy of the frequent feature points, in consideration of the fact that some regional feature points may be abnormal movements of other components such as clothes of the driving object, the present embodiment first acquires the historical driving information of the driving object, and the historical driving information may include a plurality of pieces of position change information corresponding to a plurality of regional feature points, respectively.

Then, when it is determined that a plurality of position change information corresponding to any one of the area feature points all satisfy a preset position change condition, according to the position change information of the area feature points and the amplitude of the position change interval, determining an initial position of a first position change interval matched with the preset position change condition, wherein the preset position change condition includes: the position change amplitude is larger than a set amplitude threshold value.

On the basis, the initial positions of the plurality of position change sections matched with the preset position change condition corresponding to the area feature points can be determined according to the position change information of the area feature points, the amplitude of the position change sections, the initial position of the first position change section and the number of the preset position change sections.

If the position of the area characteristic point of the tracking node corresponding to the area characteristic point in the area characteristic point is matched with the initial position of the target position change interval, and if the tracking node is the first tracking node of the target position change interval, acquiring the area characteristic point matched with the previous position change interval adjacent to the target position change interval as a screening area characteristic point, and identifying one area characteristic point without the screening area characteristic point in the tracking node as the target area characteristic point matched with the target position change interval.

And if the tracking node is not the first tracking node of the target position change interval, acquiring a target area characteristic point matched with the target position change interval, identifying the target area characteristic point in the tracking node, and identifying at least one active position node of the target area characteristic point, wherein the area characteristic point corresponds to a plurality of position change intervals.

And then, in the position change interval, calculating the moving space distance of at least one active position node of the target area characteristic point between any two adjacent tracking nodes in the position change interval and the position vector of at least one active position node of the target area characteristic point in the position change interval according to the position information of the at least one active position node of the target area characteristic point in the plurality of tracking nodes.

Then, the duration of the position change interval may be counted, and according to the moving spatial distance and the position vector, the average change frequency and the change frequency variance of the target region feature point in the position change interval may be determined, and according to the average change frequency and the change frequency variance, the frequent feature parameter of the target region feature point in the position change interval may be calculated, so that according to the frequent feature parameter of each region feature point in the matched position change interval, the frequent feature score of each region feature point may be calculated, and the region feature point whose frequent feature score is greater than the set score may be determined as the frequent region feature point. For example, the frequent feature parameters of each region feature point in the matched position change interval may be weighted and summed to obtain the frequent feature score of each region feature point.

Based on the above design, the present embodiment considers the case where some regional feature points may be abnormal movements of other components such as clothes of the driving object, and thus the accuracy and reliability of frequent feature points can be effectively improved through the above further screening process.

It should be particularly noted that after determining the frequent region feature points in each monitoring region, the present embodiment may further obtain a second state floating change result of the frequent region feature points according to a similar operation manner of obtaining the first state floating change result of the preset region feature points in the foregoing embodiment, which is not described herein again.

In a possible design, further referring to step S140, after obtaining the first state floating change result and the second state floating change result, the embodiment may match the state floating result of each first floating position in the first state floating change result with the state floating result of each matched second floating position in the second state floating change result, so as to obtain a plurality of matching degrees. Each matched second floating position in the second state floating change results is matched with the corresponding first floating position in the arrangement sequence of the respective state floating change results, and the matching degree is determined according to the coincidence degree between the state floating result of the first floating position and the state floating result of the matched second floating position.

Thus, an automatic driving control command for the automobile can be generated according to the plurality of matching degrees.

For example, in one possible design, the present embodiment may determine a first number of the plurality of degrees of matching that is lower than a first set degree of matching, a second number of the plurality of degrees of matching that is greater than a second set degree of matching, and a third number of intervals between the first set degree of matching and the second set degree of matching.

And if the first number is larger than the sum of the second number and the third number, generating a first automatic driving control instruction for the automobile, wherein the first automatic driving control instruction is used for controlling the automobile to enter a preset deceleration mode.

And if the third number is larger than the sum of the first number and the second number, generating a second automatic driving control instruction for the automobile, wherein the second automatic driving control instruction is used for controlling the automobile to enter a preset acceleration mode.

And if the second number is greater than the sum of the first number and the third number, generating a third automatic driving control instruction for the automobile, wherein the third automatic driving control instruction is used for controlling the automobile to enter a preset constant speed mode.

It should be noted that, during the automatic driving, when entering the preset deceleration mode, it does not mean that the vehicle decelerates all the time, but means that the vehicle uniformly fluctuates at the current speed down to a certain speed range. Similarly, when entering the preset acceleration mode, the vehicle is not always accelerated but is uniformly fluctuated in a certain speed range at the current speed. When the automobile enters the preset constant speed mode, the automobile can be understood to be uniformly fluctuated in a minimum speed range of the current speed.

It is understood that the first number, the second number, and the third number may fluctuate in real time during actual automatic driving, and the automatic driving apparatus 100 may adaptively switch the automatic driving control command at any time. In addition, other automatic driving strategies may exist in the automatic driving process, and the scheme provided by this embodiment may be executed simultaneously with the other automatic driving strategies, or may also be executed with a certain precondition, and may be flexibly designed by a person skilled in the art according to implementation possibilities of the scheme, and is not specifically limited herein.

Fig. 3 is a schematic functional block diagram of an automatic driving control device 300 of an automobile according to an embodiment of the present application, and the automatic driving control device 300 of the present embodiment may be divided into functional blocks according to the foregoing method embodiments. For example, the functional blocks may be divided for the respective functions, or two or more functions may be integrated into one processing block. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. It should be noted that, the division of the modules in the present application is schematic, and is only a logical function division, and there may be another division manner in actual implementation. For example, in the case of dividing each function module according to each function, the automatic driving control device 300 of the vehicle shown in fig. 3 is only a schematic device diagram. The automatic driving control device 300 may include an obtaining module 310, a first determining module 320, a first determining module 330, and a generating module 340, and the functions of the functional modules of the automatic driving control device 300 are described in detail below.

The obtaining module 310 is configured to obtain status information of the driving object in the monitoring area of each status monitoring device, divide the status information in each monitoring area according to a predetermined status category, and generate status summary information of each status category respectively.

The first determining module 320 is configured to determine preset region feature points in each monitoring region according to the identity authentication information of the driving object, and determine floating change information of a floating region of the preset region feature points in the state summary information of the corresponding state category for the preset region feature points, respectively, to obtain a first state floating change result of the preset region feature points, where the preset region feature points are region feature points that are pre-matched with the identity authentication information of the driving object.

The second determining module 330 is configured to determine frequent region feature points in each monitoring region according to historical driving information of the driving object, obtain floating tracks of the frequent region feature points respectively for the frequent region feature points in each monitoring region, determine floating change information of the floating tracks in the status summary information of the corresponding status category, and obtain a second status floating change result of the frequent region feature points, where the frequent region feature points are region feature points whose change frequency in the historical driving information of the driving object is greater than a set frequency threshold, and the change frequency is used to indicate a change degree of the region feature points in unit time.

And the generating module 340 is configured to generate an automatic driving control instruction for the vehicle according to a matching relationship between the first state floating change result and the second state floating change result.

Further, fig. 4 is a schematic structural diagram of an automatic driving device 100 for executing the automatic driving control method of the automobile according to the embodiment of the present application. As shown in fig. 4, the autopilot device 100 may include a network interface 110, a machine-readable storage medium 120, a processor 130, and a bus 140. The processor 130 may be one or more, and one processor 130 is illustrated in fig. 4 as an example. The network interface 110, the machine-readable storage medium 120, and the processor 130 may be connected by a bus 140 or otherwise, as exemplified by the connection by the bus 140 in fig. 4.

The machine-readable storage medium 120 is a computer-readable storage medium, and can be used to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the automatic driving control method of the vehicle in the embodiment of the present application (for example, the obtaining module 310, the first determining module 320, the first determining module 330, and the generating module 340 of the automatic driving control device 300 of the vehicle shown in fig. 3). The processor 130 executes various functional applications and data processing of the terminal device by detecting software programs, instructions and modules stored in the machine-readable storage medium 120, that is, the above-mentioned automatic driving control method for the vehicle is implemented, and details are not described herein.

The machine-readable storage medium 120 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the machine-readable storage medium 120 may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile memory may be a Read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash memory. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of example, but not limitation, many forms of RAM are available, such as Static random access memory (Static RAM, SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic random access memory (Synchronous DRAM, SDRAM), Double data rate Synchronous Dynamic random access memory (DDR SDRAM), Enhanced Synchronous SDRAM (ESDRAM), Synchronous link SDRAM (SLDRAM), and direct memory bus RAM (DR RAM). It should be noted that the memories of the systems and methods described herein are intended to comprise, without being limited to, these and any other suitable memory of a publishing node. In some examples, the machine-readable storage medium 120 may further include memory located remotely from the processor 130, which may be connected to the autopilot device 100 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The processor 130 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method embodiments may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 130. The processor 130 may be a general-purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, or discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor.

The autopilot device 100 may interact with other equipment (e.g., condition monitoring device 200) via the network interface 110. Network interface 110 may be a circuit, bus, transceiver, or any other device that may be used to exchange information. Processor 130 may send and receive information using network interface 110.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, autopilot device, or data center to another website site, computer, autopilot device, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device including one or more available media integrated automotive vehicles, data centers, and the like. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.

Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

It will be apparent to those skilled in the art that various changes and modifications may be made in the embodiments of the present application without departing from the spirit and scope of the application. Thus, to the extent that such expressions and modifications of the embodiments of the application fall within the scope of the claims and their equivalents, the application is intended to embrace such alterations and modifications.

Claims

1. A method for controlling automatic driving of an automobile is characterized in that, it is applied to an automatic driving device, and the automatic driving device is communicatively connected with a plurality of state monitoring devices in an automobile, and the method comprises:

Obtain the state information of the driving object under the monitoring area of each state monitoring device, and divide the state information under each monitoring area according to a predetermined state category, and respectively generate the state summary information of each state category;

Determine the preset area feature points in each monitoring area according to the identity authentication information of the driving object, and determine the floating of the preset area feature points for the preset area feature points in each monitoring area. The floating change information of the region in the state summary information of the corresponding state category is obtained, and the first state floating change result of the feature point of the preset region is obtained, and the feature point of the preset region is the identity authentication information of the driving object. Pre-matched regional feature points;

Determine frequent area feature points in each monitoring area according to the historical driving information of the driving object, obtain the floating trajectories of the frequent area feature points for the frequent area feature points in each monitoring area, and determine The floating change information of the floating trajectory in the state summary information of the corresponding state category is obtained, and the second state floating change result of the frequent area feature points is obtained, and the frequent area feature points are the historical driving information of the driving object. The change frequency in is greater than the regional feature point of the set frequency threshold, and the change frequency is used to represent the change degree of the regional feature point in unit time;

According to the matching relationship between the first state floating change result and the second state floating change result, an automatic driving control instruction for the car is generated.

2. The method for controlling automatic driving of automobiles according to claim 1, wherein the step of dividing the status information under each monitoring area according to a predetermined status category, and generating the status summary information of each status category, respectively, include:

Obtain the state category feature points corresponding to each predetermined state category, form a feature point set of each predetermined state category, and obtain the coincidence feature point information of the target feature points of each monitoring area and the feature point number of the feature point set ;

Calculate the number of key feature points of each target state category according to the coincident feature point information of the number of target feature points and the number of feature points of the feature point set, and according to the number of key feature points of each target state category, from all Select the state category feature points from the feature point set described, and obtain the initial feature point matrix;

If the total feature point distribution quantity of the initial feature point matrix is greater than the maximum total feature point distribution quantity that satisfies the requirement of the total feature point distribution quantity, then reduce the coarse-range key feature points in the initial feature point matrix by the first setting and increase the fine-range key feature points in the initial feature point matrix by the first set number, wherein the fine-range key feature points refer to the unit density of the key feature points in the detection area where they are located The key feature points that are less than the set level, and the coarse-range key feature points refer to the key feature points whose unit density in the detection area where the key feature points are located is not less than the set level;

Calculate the total number of feature point distributions of the initial feature point matrix after this update;

If the total feature point distribution quantity of the updated initial feature point matrix is greater than the maximum total feature point distribution quantity, the above processing is performed again on the updated initial feature point matrix;

If the total number of feature point distributions of the initial feature point matrix after this update is less than or equal to the maximum total number of feature point distributions, the initial feature point matrix before this update is used as the first update matrix, according to the state category from low to low Sort each of the target state categories in the order of priority to high priority to obtain a sequence of target state categories;

According to the sequence of target state categories, each of the target state categories is grouped, and each of the groupings includes the first target position on both sides of the target position of the sequence of target status categories and consistent with the distance between the target positions. a state class and a second state class, the first state class has a lower priority than the second state class;

According to the order of the distance from the target position from low priority to high priority, each of the groups is taken as a target group in turn, and the following second update processing is performed on the target group: The key feature point of the first state category of the target grouping is increased by one, and the key feature point of the second state category of the target grouping in the first update matrix is decreased by one;

Judging whether the total feature point distribution quantity of the first update matrix after this update meets the requirement for the total feature point distribution quantity;

If the total feature point distribution quantity of the first update matrix after this update meets the requirement on the total feature point distribution quantity, then the first update matrix after this update is used as the final feature point matrix;

If the total feature point distribution quantity of the first update matrix after this update does not meet the total feature point distribution quantity requirement, the next grouping is taken as a new target grouping, and the second grouping is performed on the new target grouping. update processing;

If the total feature point distribution quantity of the initial feature point matrix is less than the minimum total feature point distribution quantity satisfying the requirement of the total feature point distribution quantity, the following third update processing is performed on the initial feature point matrix: The coarse-range key feature points in the feature point matrix are increased by a first set amount, and the fine-range key feature points in the initial feature point matrix are decreased by the first set number;

If the total feature point distribution number of the updated initial feature point matrix is less than the minimum total feature point distribution number, the third update process is performed again on the updated initial feature point matrix;

If the total number of feature point distributions of the initial feature point matrix after this update is greater than or equal to the minimum total number of feature point distributions, the initial feature point matrix before this update is used as the second update matrix, according to the state category from low to low Sort each of the target state categories in the order of priority to high priority to obtain a sequence of target state categories;

According to the order of the distance from the target position from low priority to high priority, each of the groups is taken as a target group in turn, and the following fourth update processing is performed on the target group: The key feature point of the first state category of the target grouping is reduced by one, and the key feature point of the second state category of the target grouping in the second update matrix is increased by one;

Judging whether the total feature point distribution quantity of the second update matrix after this update meets the requirement for the total feature point distribution quantity;

If the total feature point distribution quantity of the second update matrix after this update meets the requirement for the total feature point distribution quantity, then the second update matrix after this update is used as the final feature point matrix;

If the total feature point distribution quantity of the second update matrix after this update does not meet the requirement of the total feature point distribution quantity requirement, the next grouping is taken as a new target grouping, and the fourth step is performed on the new target grouping. update processing;

The state information of each feature point in the final feature point matrix of each target state category is classified as the state summary information of the state category.

3 . The automatic driving control method of claim 1 , wherein the identity authentication information includes biometric information, and the preset information in each monitoring area is determined according to the identity authentication information of the driving object. 4 . The steps of regional feature points include:

collecting biometric information of the driving object;

According to the biometric information and the corresponding relationship between each preconfigured biometric information and the preset area feature points in each detection area, the preset area feature points in each monitoring area are obtained.

4 . The automatic driving control method of claim 1 , wherein, for the preset area feature points in each of the monitoring areas, and respectively determine that the floating area of the preset area feature points is in the 5. 5 . The floating change information in the state summary information of the corresponding state category, and the steps of obtaining the first state floating change result of the feature point in the preset area include:

For the preset area feature points in each of the monitoring areas, obtain a three-dimensional fixed point matching the preset area feature point respectively, and obtain one of the three-dimensional fixed points that continuously fall within the monitoring area within a preset time period When the three-dimensional space area corresponding to the three-dimensional space area is within the coordinate range, the corresponding three-dimensional space area is used as the target three-dimensional space area;

judging whether the area range of the target three-dimensional space area is the same as the area range input by the model of the preset automatic driving control model;

If the area ranges are not identical, scaling the area range of the target three-dimensional space area to a three-dimensional space area consistent with the area range input by the model of the automatic driving control model, and inputting it to the automatic driving control model;

Calculate the input three-dimensional space area by using the automatic driving control model, and obtain floating change information corresponding to the input three-dimensional space area;

Tracking each floating position of the preset area feature point in the target three-dimensional space area, and obtaining a floating feature vector of each floating position in the target three-dimensional space area;

Determining an area in the floating change information corresponding to the input three-dimensional space area with a frequency of floating position greater than a preset threshold as a floating area;

Convert the vector value of each floating position in the input three-dimensional space region, and obtain the floating feature vector of each floating position in the input three-dimensional space region;

According to the floating feature vector of each floating position in the target three-dimensional space region, calculate the first floating vector mean value of the entire three-dimensional space region;

According to the floating feature vector of each floating position in the floating region, calculate the mean value of the second floating vector of the floating region;

Calculate the mean value of the first floating vector, the mean value of the second floating vector and the preset coefficient, obtain the floating reference coefficient of the floating area, and calculate the floating feature vector of each floating position in the target three-dimensional space area and the ratio of the floating reference coefficients, and obtaining the first floating intensity of each floating position in the target three-dimensional space region according to the ratio;

calculating the first floating strength of each floating position in the target three-dimensional space region and the floating change information, and obtaining the floating strength of each floating position in the target three-dimensional space region;

Or, calculate the ratio of the floating feature vector of each floating position in the target three-dimensional space region to the floating reference coefficient to obtain the first floating strength of each floating position in the target three-dimensional space region, and use the preset floating The range calculates the first floating strength of each floating position in the target three-dimensional space area, and obtains the second floating strength of each floating position in the target three-dimensional space area, wherein the second floating strength is the same as the The difference between the first floating intensities is smaller than the preset floating range, and the second floating intensity and the floating change information of each floating position in the target three-dimensional space region are calculated to obtain the target three-dimensional space float strength for each float position in the region;

Determine the target coefficient of each floating position in the target three-dimensional space area according to the target feature points, floating strength and the floating change information of the specified spatial position, and calculate the floating strength of each floating position in the target three-dimensional space area The ratio to a preset constant, wherein the target coefficient is the value of the feature vector value of the target feature point at the specified spatial position multiplied by the floating intensity and divided by the floating change information;

Calculate the product of the ratio of the floating strength of each floating position to a preset constant and the corresponding target coefficient, and obtain the first state floating result of each floating position in the target three-dimensional space region;

Perform color editing processing on the target three-dimensional space area according to the first state floating result of each floating position to output the target three-dimensional space area;

Or, calculating the ratio of the floating intensity of each floating position in the target three-dimensional space region to a preset constant;

Calculate the product of the ratio of the floating intensity of each floating position to a preset constant and the corresponding target dyeing value, and obtain the first state floating result of each floating position in the target three-dimensional space area;

Calculate the first state floating result of each floating position in the target three-dimensional space area, the target three-dimensional space area and the floating change information, and obtain the second state of each floating position in the target three-dimensional space area floating result;

Arranging the second state floating result of each floating position to obtain the first state floating change result of the feature point in the preset area.

5. The method for controlling automatic driving of automobiles according to any one of claims 1 to 4, wherein the step of determining frequent area feature points in each monitoring area according to historical driving information of the driving object ,include:

acquiring historical driving information of the driving object, where the historical driving information includes a plurality of position change information respectively corresponding to a plurality of regional feature points;

When it is determined that a plurality of position change information corresponding to any one regional feature point satisfies the preset position change condition, the preset position change condition is determined according to the position change information of the regional feature point and the magnitude of the position change interval. The initial position of the first matched position change interval, wherein the preset position change condition includes: the position change amplitude is greater than the set amplitude threshold;

According to the position change information of the regional feature point, the magnitude of the position change interval, the initial position of the first position change interval, and the number of preset position change intervals, determine the position change condition that matches the preset position change condition. The plurality of position change intervals correspond to the initial positions of the feature points in the region;

If the position of the regional feature point in the regional feature point of the tracking node corresponding to the regional feature point matches the initial position of the target position change interval, and if the tracking node is in the target position change interval For the first tracking node, obtain the area feature points matching the previous position change interval adjacent to the target position change interval as the screening area feature points, and identify and remove the screening area feature points in the tracking node. A regional feature point of is as the target region feature point matched with the target position change interval;

If the tracking node is not the first tracking node in the target position change interval, obtain a target area feature point matching the target position change interval, and identify the target area feature point in the tracking node, and identify at least one active location node of the target area feature point, wherein the area feature point corresponds to a plurality of position change intervals;

In the position change interval, according to the position information of the at least one active position node of the target area feature point in the plurality of tracking nodes, calculate the position of the at least one active position node of the target area feature point at the position The moving space distance between any two adjacent tracking nodes in the change interval, and the position vector of at least one active position node of the feature point of the target area in the position change interval;

Count the duration of the position change interval, and determine the average change frequency and change frequency variance of the feature points of the target area in the position change interval according to the moving space distance and the position vector, according to the The average change frequency and the variance of the change frequency are calculated, and the frequent feature parameters of the target area feature points in the position change interval are calculated;

According to the frequent feature parameters of each regional feature point in the matched position change interval, the frequent feature score of each of the regional feature points is calculated, and the regional feature point whose frequent feature score is greater than the set score is determined as the frequent regional feature point.

6 . The automatic driving control method according to claim 1 , wherein the matching relationship between the floating change result of the first state and the floating change result of the second state is based on the matching relationship between the floating change result of the first state and the second state floating change result. , the steps of generating an automatic driving control instruction for the vehicle include:

Matching the state floating result of each first floating position in the first state floating change result with the state floating result of each matching second floating position in the second state floating change result to obtain multiple matching degrees , wherein each matching second floating position in the second state floating change result matches the arrangement order of the corresponding first floating position in the respective state floating change result, and the matching degree is based on the first floating position. determining the degree of coincidence between the state floating result of the position and the matching state floating result of the second floating position;

An automatic driving control command for the car is generated according to the plurality of matching degrees.

7. The method for controlling automatic driving of automobiles according to claim 6, wherein the step of generating the automatic driving control instructions for the automobile according to the plurality of matching degrees comprises:

determining a first number of the plurality of matching degrees that is lower than a first set matching degree, a second number that is greater than a second set matching degree, and a second number that is located between the first set matching degree and the second set matching degree the third number of intervals between degrees;

If the first number is greater than the sum of the second number and the third number, generating a first automatic driving control command for the car, the first automatic driving control command is used to control the car to enter Preset deceleration mode;

If the third number is greater than the sum of the first number and the second number, generating a second automatic driving control command for the car, the second automatic driving control command is used to control the car to enter Preset acceleration mode;

If the second number is greater than the sum of the first number and the third number, generate a third automatic driving control command for the car, the third automatic driving control command is used to control the car to enter Preset constant speed mode.

8. An automatic driving control device for an automobile, characterized in that, it is applied to an automatic driving device, and the automatic driving device is communicatively connected with a plurality of state monitoring devices in an automobile, and the device comprises:

The acquiring module is used to acquire the state information of the driving object under the monitoring area of each state monitoring device, and divide the state information under each monitoring area according to a predetermined state category, and respectively generate the state summary information of each state category;

The first determination module is configured to determine the preset area feature points in the respective monitoring areas according to the identity authentication information of the driving object, and determine the preset area feature points in the respective monitoring areas respectively. The floating change information of the floating area of the preset area feature point in the state summary information of the corresponding state category, and the first state floating change result of the preset area feature point is obtained, and the preset area feature point is the same as the The regional feature points pre-matched by the identity authentication information of the driving object;

The second determination module is configured to determine the frequent area feature points in the respective monitoring areas according to the historical driving information of the driving object, and obtain the frequent area feature points for the frequent area feature points in the respective monitoring areas respectively. and determine the floating change information of the floating trajectory in the state summary information of the corresponding state category, and obtain the second state floating change result of the frequent area feature points, and the frequent area feature points are all The change frequency in the historical driving information of the driving object is greater than the regional feature point of the set frequency threshold, and the change frequency is used to represent the change degree of the regional feature point in unit time;

The generating module is configured to generate an automatic driving control instruction for the car according to the matching relationship between the floating change result of the first state and the floating change result of the second state.

9. An automatic driving system, characterized in that the automatic driving system comprises an automatic driving device and a plurality of state monitoring devices in a car that are communicatively connected to the automatic driving device, and the method comprises:

The state monitoring device is used to monitor the state information of the driving object in the monitored area;

The automatic driving device is used to obtain the state information of the driving object under the monitoring area of each state monitoring device, and divide the state information under each monitoring area according to a predetermined state category, and respectively generate the state of each state category. Summary information;

The automatic driving device is configured to determine the preset area feature points in the respective monitoring areas according to the identity authentication information of the driving object, and determine the preset area feature points in the respective monitoring areas respectively. The floating change information of the floating area of the preset area feature point in the state summary information of the corresponding state category, to obtain the first state floating change result of the preset area feature point, and the preset area feature point is the same as the Regional feature points pre-matched by the identity authentication information of the driving object;

The automatic driving device is configured to determine frequent area feature points in each monitoring area according to the historical driving information of the driving object, and obtain the frequent area feature points for the frequent area feature points in each monitoring area respectively. The floating trajectory of the point, and determine the floating change information of the floating trajectory in the state summary information of the corresponding state category, and obtain the second state floating change result of the frequent area feature point, and the frequent area feature point is The change frequency in the historical driving information of the driving object is greater than the regional feature point of the set frequency threshold, and the change frequency is used to represent the change degree of the regional feature point in unit time;

The automatic driving device is configured to generate an automatic driving control instruction for the car according to the matching relationship between the floating change result of the first state and the floating change result of the second state.

10. An automatic driving device, characterized in that, the automatic driving device comprises a processor, a machine-readable storage medium, and a network interface, and a communication between the machine-readable storage medium, the network interface, and the processor is performed. the bus system is connected, the network interface is used for communicating with at least one condition monitoring device in the vehicle, the machine-readable storage medium is used for storing programs, instructions or codes, and the processor is used for executing the machine-readable storage A program, instruction or code in the medium to execute the method for controlling automatic driving of an automobile according to any one of claims 1-7.