CN116923382B

CN116923382B - Parking method and device

Info

Publication number: CN116923382B
Application number: CN202311125055.0A
Authority: CN
Inventors: 刘永孛; 孙传扬; 孙杰
Original assignee: Hangzhou Hikvision Digital Technology Co Ltd
Current assignee: Hangzhou Hikvision Digital Technology Co Ltd
Priority date: 2023-09-01
Filing date: 2023-09-01
Publication date: 2025-02-11
Anticipated expiration: 2043-09-01
Also published as: CN116923382A

Abstract

The embodiment of the present application provides a parking method and device, which relates to the field of data processing technology. The method includes: based on sensor data and a pre-built parking map of a parking space to be parked, generating a first driving path to a gear shift location, and controlling the vehicle to drive based on the first driving path; if the gear shift condition is met, sensing obstacles around the vehicle based on sensor data, and sensing the parking space to be parked; based on the sensed obstacles and the sensed parking space, generating a second driving path, controlling the vehicle to switch gears and park in the parking space to be parked based on the second driving path; during the vehicle driving based on the second driving path, if the difference between the vehicle terminal posture indicated by the second driving path and the vehicle terminal posture indicated by the sensed parking space is greater than a preset posture threshold, updating the untraveled section in the second driving path based on the sensed obstacles and the sensed parking space. The solution provided by the embodiment of the present application can realize automatic parking.

Description

Parking method and device

Technical Field

The application relates to the technical field of automatic driving, in particular to a parking method and device.

Background

With the improvement of the living standard of people, automobiles become one of the main travel tools in the daily life of people. When an automobile owner starts an automatic parking function, a parking space to be parked needs to be manually selected, and in view of the situation, an automatic parking scheme needs to be provided to free the hands of the automobile owner, so that convenience is brought to the automobile owner in parking.

Disclosure of Invention

The embodiment of the application aims to provide a parking method and a device for controlling a vehicle to automatically park into a parking space. The specific technical scheme is as follows:

in a first aspect, an embodiment of the present application provides a parking method, including:

Generating a first travel path for traveling to a gear shifting place based on sensor data acquired by a sensor carried by a vehicle and a pre-constructed parking space map of a parking space to be parked, and controlling the vehicle to travel based on the first travel path;

If a gear shifting condition is met, sensing obstacles around the vehicle based on the sensor data, sensing the parking space to be parked, generating a second driving path for enabling the vehicle to park in the parking space to be parked based on the sensed obstacles and the sensed parking space, controlling the vehicle to switch gear shifting and park in the parking space to be parked based on the second driving path;

And in the running process of the vehicle based on the second running path, if the difference between the vehicle final point pose indicated by the second running path and the vehicle final point pose indicated by the perceived parking space is greater than a preset pose threshold, updating the non-running road section in the second running path based on the perceived obstacle and the perceived parking space.

In a second aspect, an embodiment of the present application provides a parking apparatus, including:

the first travel path generation module is used for generating a first travel path for traveling to a gear shifting place based on sensor data acquired by a sensor carried by a vehicle and a pre-constructed parking space map of a parking space to be parked, and controlling the vehicle to travel based on the first travel path;

The second driving path generating module is used for sensing obstacles around the vehicle based on the sensor data and sensing the parking space to be parked, generating a second driving path for enabling the vehicle to be parked into the parking space to be parked based on the sensed obstacles and the sensed parking space, controlling the vehicle to switch the gear and parking the vehicle to be parked into the parking space to be parked based on the second driving path if a gear shifting condition is met;

and the path updating module is used for updating the non-driving road section in the second driving path based on the perceived obstacle and the perceived parking space if the difference between the vehicle final point pose indicated by the second driving path and the vehicle final point pose indicated by the perceived parking space is larger than a preset pose threshold value in the driving process of the vehicle based on the second driving path.

In a third aspect, an embodiment of the present application provides an in-vehicle control apparatus, including:

A memory for storing a computer program;

and the controller is used for realizing the method of the first aspect when executing the program stored on the memory.

In a fourth aspect, embodiments of the present application provide a computer readable storage medium having a computer program stored therein, which when executed by a controller, implements the method of the first aspect.

In a fifth aspect, an embodiment of the present application provides a vehicle having a computer program stored therein, which when executed by a controller implements the method of the first aspect.

In a sixth aspect, embodiments of the present application provide a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of the first aspect.

From the above, when the scheme provided by the embodiment of the application is applied to parking, a first driving path for driving to a gear shifting place is generated based on the sensor data and the pre-constructed parking space map of the parking space to be parked, and the vehicle is controlled to drive based on the first driving path, when the gear shifting condition is met, a second driving path for parking the vehicle into the parking space can be generated based on the perceived obstacle and the perceived parking space, and the vehicle is controlled to successfully park into the parking space based on the second driving path, so that automatic parking is realized, and convenience is brought to the parking of a vehicle owner.

Of course, it is not necessary for any one product or method of practicing the application to achieve all of the advantages set forth above at the same time.

Drawings

In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the application, and other embodiments may be obtained according to these drawings to those skilled in the art.

Fig. 1 is a schematic flow chart of a first parking method according to an embodiment of the present application;

FIG. 2 is a schematic diagram of a first path according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a second path according to an embodiment of the present application;

FIG. 4 is a schematic diagram of a third path according to an embodiment of the present application;

FIG. 5 is a schematic diagram of a boundary line according to an embodiment of the present application;

FIG. 6 is a schematic diagram of a collision detection process according to an embodiment of the present application;

Fig. 7 is a schematic flow chart of a second parking method according to an embodiment of the present application;

Fig. 8 is a schematic diagram of a parking process according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of a parking device according to an embodiment of the present application;

fig. 10 is a schematic structural diagram of a vehicle-mounted control device according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by the person skilled in the art based on the present application are included in the scope of protection of the present application.

First, an execution subject of the scheme provided by the embodiment of the present application is described.

The implementation main body of the scheme provided by the embodiment of the application is vehicle-mounted control equipment with the functions of data processing, storage and the like.

The following describes the parking scheme provided by the embodiment of the present application in detail.

Referring to fig. 1, a schematic flow chart of a first parking method according to an embodiment of the present application is provided, where the method includes the following steps S101 to S103.

Step S101, a first travel path for traveling to a gear shifting place is generated based on sensor data acquired by a sensor carried by the vehicle and a pre-constructed parking space map of a parking space to be parked, and the vehicle is controlled to travel based on the first travel path.

The embodiment of the application does not limit the types and the number of the sensors, and only ensures that the sensors can acquire sensor data for determining the position, the gesture and other information of the vehicle.

For example, the sensor may include a vision sensor, a radar sensor, an inertial sensor, a positioning sensor, and the like. The vision sensor may include a monocular camera, the inertial sensor may be an IMU (Inertial Measurement Unit ), an acceleration sensor, a gyroscope, etc., and the positioning sensor may be a GPS (Global Positioning System ) sensor, a beidou satellite navigation system sensor, etc.

Sensor data collected by the sensors is different according to the types of the sensors.

For example, the sensor data collected by the vision sensor may be an image, the sensor data collected by the inertial sensor may be pose data such as speed, acceleration, angular velocity, etc., and the sensor data collected by the positioning sensor may be positioning data such as longitude and latitude coordinates, etc.

Based on one or more of the above-described sensor data, the location of the vehicle may be determined, as embodiments of the application are not limited in this regard. For example, the location of the vehicle may be determined using monocular vision positioning principles based on images acquired by vision sensors, the location of the vehicle may be determined based on positioning information acquired by positioning sensors, etc.

Owners typically have a tendency to park vehicles in fixed spaces when parking at frequent points of entry, e.g., at home, near a company. The environment around the fixed parking space is relatively fixed compared with the environment around the random parking space. If the vehicle can identify the fixed parking space by itself, the situation that the parking space is manually found and then manually selected is avoided, and the vehicle is more convenient for the vehicle owner.

The pre-constructed parking space map will be described below.

The pre-constructed map may include a complete parking path for a vehicle to park in a parking space, environmental information around the path, and information such as a parking space position. The complete parking path is constructed based on data acquired by a sensor during the process that the vehicle owner drives the vehicle to enter the parking space, namely, the complete parking path is a path that the vehicle owner controls the vehicle to enter the parking space.

Under the condition, the pre-constructed map can be a parking space map constructed after the vehicle owner confirms by sending out a map construction prompt based on the historical parking information of the parking space.

The pre-constructed parking space map of the parking space to be parked comprises a fixed parking space of the vehicle, and the fixed parking space of the vehicle comprises:

the space management system synchronizes the paid space to the vehicle and/or,

A pre-stored parking space received through an interactive system in an onboard system of the vehicle, and/or,

The vehicle automatically stores the common parking space based on the historical parking information.

The historical parking information may include, but is not limited to, the number of historical parking times, the historical parking duration, the parking frequency, etc. of the vehicle at the parking spot.

Thus, it is possible to determine whether the parking space is a fixed parking space based on the above-described history parking information.

For example, if the historical parking times are greater than the preset times, the parking space is determined to be a fixed parking space, if the historical parking time is greater than the preset time, the parking space is determined to be a fixed parking space, if the parking frequency is greater than the preset frequency, the parking space is determined to be a fixed parking space, the historical parking times, the historical parking time and the parking frequency can be weighted according to preset weights, if the calculation result is greater than a preset threshold value, the parking space is determined to be a fixed parking space, and the like.

Therefore, whether the parking space is a fixed parking space can be more comprehensively and reasonably determined based on various historical parking information.

For another example, the interactive system in the vehicle-mounted system of the vehicle may, but is not limited to, include a display screen, after the vehicle is parked, prompt the vehicle owner through the display screen whether to add the left parking space of the door as a fixed parking space, and after the vehicle owner agrees, the vehicle-mounted system constructs a pre-constructed parking space map of the newly added left parking space of the door. When the gear shifting condition (the vehicle runs to the door), the obstacle around the vehicle is sensed based on the sensor data, the left parking space of the door is sensed, the vehicle is controlled to switch to the gear shifting position, and the parking space to be parked is parked based on the second running path.

The starting time of the buffered sensor data will be described below.

The method comprises the steps of detecting that a vehicle arrives at a specified position, starting to cache sensor data, wherein the starting time of the cached sensor data is the time when the vehicle arrives at the specified position, the specified position can be the position in an area where the vehicle enters a parking space, such as the position of a parking lot gate, and the like, or starting to cache the sensor data when a cache start instruction sent by a vehicle owner is received, and the starting time of the cached sensor data is the time when the instruction is received.

Specifically, based on the cached sensor data, a map of the parking space may be constructed by using a SLAM algorithm such as Gmapping, hector, karto, cartographer, which is not limited in the embodiment of the present application.

Therefore, the method and the system can actively remind the vehicle owner of whether to construct a parking space map under the condition that the parking space is the fixed parking space of the vehicle according to the historical parking information of the parking space, and perform map construction after being confirmed without the vehicle owner searching the parking space, so that user experience is improved, in addition, after being confirmed, the map construction can be directly performed based on cached sensor data, the process is noninductive for the user, the process is convenient for the vehicle owner, and the practicability of the scheme is improved.

In another case, the pre-constructed map may be a parking space map of a parking space to be parked, which is constructed by the vehicle based on the perceived data after the active instruction of the user.

For example, the vehicle first parks into the private parking space, and the vehicle owner can send out a parking space map construction instruction through the user interface, so that the vehicle-mounted control device can construct a parking space map of the private parking space based on the cached sensor data, and a pre-constructed parking space map is obtained.

The shift points described above are explained below.

In a scenario where a vehicle is parked in a parking space, the vehicle generally needs to advance to a suitable location, switch to reverse gear at the location, reverse, and gradually park in the parking space. The above-described place of shifting to the reverse gear may be referred to as a shift place.

In this step, the generated first travel path is a path for the vehicle to reach the shift point.

A specific mode of generating the first travel path to the shift point will be described below.

In one embodiment, a complete travel path for the vehicle to park in the parking space can be generated based on sensor data acquired by a sensor carried by the vehicle and a pre-constructed parking space map of the parking space to be parked, and a path recorded in the complete travel path and before a gear shifting place is intercepted to serve as a first travel path for traveling to the gear shifting place.

It can be seen that the complete path of travel of the vehicle into the parking space contains a point which characterizes the transition from forward to reverse, so that the first point which characterizes the transition from forward to reverse can be determined from the complete path of travel, and the determined point can be referred to as the shift point.

Thus, the path before the gear shifting point recorded in the complete driving path is intercepted, and the path can be used as a first driving path for driving to the gear shifting point.

Specifically, the current position of the vehicle and the positions of the obstacles around the current position can be determined based on sensor data acquired by sensors carried by the vehicle, and then the obtained current position, the positions of the obstacles and the positions of the parking spaces recorded in the pre-constructed parking space map are used as inputs of a path planning algorithm, so that a complete driving path for the vehicle to park in the parking spaces is obtained.

The path planning algorithm may be an a-star algorithm, a hybrid a-star algorithm, a Dijkstra algorithm, a JSP (Jump Point Search ) algorithm, a greedy algorithm, or the like.

Therefore, the first travel path which travels to the gear shifting place can be obtained conveniently based on the fact that the complete travel path which enables the vehicle to be parked in the parking space is generated, and then the path recorded in the complete travel path and before the gear shifting place is intercepted, prediction of the gear shifting place is not needed, and generation efficiency of the first travel path is improved.

The first travel path is more intuitively described below with reference to fig. 2.

Referring to fig. 2, a schematic diagram of a first path according to an embodiment of the present application is provided.

The map parking space in fig. 2 refers to a parking space recorded in a pre-constructed parking space map.

As can be seen from fig. 2, the first travel path is a path generated based on the map parking space, so that the vehicle arrives at the shift location, and thus, after arriving at the shift location based on the first travel path, the vehicle can perform subsequent path planning, and a new path obtained based on the planning is parked into the parking space.

In another embodiment, a shift point for facilitating parking in a parking space may be predicted based on a pre-constructed parking space map of a parking space to be parked, and then a path by which the vehicle reaches the predicted shift point may be generated as the first travel path.

The shift location predicted may be a location determined based on a parking space area recorded in the pre-constructed parking space map, for example, may be a side front of the parking space area, which is not limited in the embodiment of the present application.

The generation manner of the first travel path is the same as that of the previous embodiment, and the difference is only the steps of replacing the position of the parking space recorded in the pre-constructed map with the position of the predicted shift location and canceling the path interception, which are not repeated here.

In yet another embodiment, an avoidance priority characteristic value of the perceived obstacle may be obtained, the perceived obstacle may be classified based on the obtained avoidance priority characteristic value, a parkable area may be constructed based on the classified high priority obstacle, and a boundary line of the parkable area may be obtained, thereby generating a first travel path that does not collide with both the boundary line and the low priority obstacle. The detailed description will be given in the following examples, which will not be described in detail here.

The first travel path is a path generated during parking so that the vehicle travels to the shift point, and the generation process of the first travel path may be referred to as a shift planning stage.

After the first travel path is generated, the vehicle can be controlled to travel on the basis of the first travel path.

In addition, in the running process of the control vehicle based on the first running path, the obstacle around the vehicle can be detected based on the sensor data acquired in real time, so that the control vehicle can be controlled to perform path fine adjustment on the basis of running along the first running path, and the vehicle is prevented from colliding with the detected obstacle.

Step S102, if the gear shifting condition is met, sensing obstacles around the vehicle based on the sensor data, sensing a parking space to be parked, generating a second driving path for parking the vehicle into the parking space to be parked based on the sensed obstacles and the sensed parking space, controlling the vehicle to switch the gear shifting position, and parking the vehicle into the parking space to be parked based on the second driving path.

The obstacle can be any obstacle such as a stand column, a vehicle, a roadblock, a pedestrian, a cone barrel and the like.

Specifically, the information such as the position, the size and the like of the obstacle around the vehicle can be perceived in real time based on the sensor data acquired in real time, and the information such as the position, the size and the like of the parking space to be parked in can be perceived in real time based on the sensor data acquired in real time.

Thus, as the vehicle runs, the collected sensor data is dynamically updated, the perceived obstacle is dynamically updated, and the perceived parking space is also dynamically updated.

For example, when the shift condition is satisfied, it may be considered that the vehicle is now suitably shifted to the reverse gear for reversing, and therefore, a second travel path for causing the vehicle to park in the parking space may be generated, and the vehicle may be controlled to shift to the reverse gear and park in the parking space based on the second travel path.

The shift conditions described above are explained below.

The shift condition may include at least one of:

1. the vehicle travels to the cruising end point recorded in the pre-constructed map.

The above-mentioned cruising end point refers to a place representing the first transition of the vehicle from the forward state to the backward state in the parking path recorded in the pre-constructed map, and may also be referred to as a shift place in the parking path recorded in the pre-constructed map.

The parking path recorded in the pre-constructed map is a path for a vehicle owner to control the vehicle to park in a parking space, and when the vehicle runs to the cruising end point, the vehicle runs to a gear shifting place of the path.

The gear shifting place of the path is generally the better gear shifting place determined by the vehicle owner, so that the gear shifting condition is determined to be met when the vehicle runs to the cruising end point so as to carry out subsequent path planning, the condition that the vehicle misses the better gear shifting place due to the fact that the vehicle continues to run can be avoided, and the parking efficiency is improved.

2. The vehicle travels to a shift location based on the first travel path.

The gear shifting place is the optimal gear shifting place determined in the first driving path generation process, and when the vehicle is driven to the gear shifting place, the condition that the vehicle meets the gear shifting condition can be determined so as to carry out subsequent path planning, so that the parking efficiency is improved.

3. The vehicle is stopped during traveling based on the first travel path.

For example, a route jam or the like occurs during the travel of the vehicle based on the first travel route.

From the foregoing, it is possible to control the vehicle to make a fine adjustment of the path on the basis of traveling along the first travel path so that the vehicle does not collide with the detected obstacle. On the basis, if the vehicle is parked, the vehicle is prevented from being blocked in a serious path in the process of travelling along the first travelling path and cannot continue travelling based on the fine adjustment of the path, so that the vehicle is determined to meet the gear shifting condition at the moment so as to carry out subsequent path planning, long-time parking of the vehicle can be avoided, and the parking efficiency is improved.

Specifically, the second travel path may be generated in the following manner.

In one embodiment, the current position of the vehicle and the positions of the obstacles around the current position may be determined based on sensor data acquired by sensors carried by the vehicle, and then the obtained current position, the perceived position of the obstacle, and the perceived position of the parking space are used as inputs of a path planning algorithm, so as to obtain a second driving path for the vehicle to park in the parking space.

The path planning algorithm may be the same as the algorithm described in the foregoing step S101, and will not be described herein.

The second travel path will be described more intuitively with reference to fig. 3.

Referring to fig. 3, a schematic diagram of a second path according to an embodiment of the present application is provided.

The black dots in fig. 3 indicate the positions of the vehicles when the vehicle meets the gear shifting condition, and the map parking spaces refer to the parking spaces recorded in the pre-constructed parking space map, and the perceived parking spaces are the perceived parking spaces mentioned above.

As can be seen from fig. 3, the second travel path is a path generated based on the perceived parking space from the position where the vehicle is located when the shift condition is satisfied to the position where the perceived parking space is located.

In another embodiment, an avoidance priority representation value of the perceived obstacle may be obtained, the perceived obstacle may be classified based on the obtained avoidance priority representation value, a parkable area may be constructed based on the classified high priority obstacle, and a boundary line of the parkable area may be obtained, thereby generating a first travel path that does not collide with both the boundary line and the low priority obstacle. The detailed description will be given in the following examples, which will not be described in detail here.

The second driving path is a path generated in the parking process and used for enabling the vehicle to be parked in the parking space, and the generation process of the second driving path can be called a static planning stage.

Similar to step S101, in the process of controlling the vehicle to park into the parking space based on the second travel path, the obstacle around the vehicle may be detected based on the sensor data acquired in real time, so that the vehicle may be controlled to perform the path fine adjustment on the basis of traveling along the second travel path, so that the vehicle does not collide with the detected obstacle.

Step S103, if the difference between the final position and the final position of the vehicle indicated by the second driving path and the final position of the vehicle indicated by the perceived parking space is larger than a preset position and position threshold value in the driving process of the vehicle based on the second driving path, updating the non-driving road section in the second driving path based on the perceived obstacle and the perceived parking space.

The final position and posture of the vehicle are the positions and postures of the vehicle when the vehicle is parked in the parking space.

After the second travel path is determined, a pose of the vehicle when the vehicle is parked in the parking space based on the second travel path may also be determined, and the pose may be referred to as a vehicle final point pose indicated by the second travel path.

For example, the vehicle pose when the parking space is at the path end point of the second travel path may be determined as the vehicle end point pose indicated by the second travel path.

Based on the perceived location of the parking spot, the pose of the vehicle when the vehicle is parked into the parking spot may also be determined, which may be referred to as the perceived final point pose of the vehicle indicated by the parking spot.

For example, the vehicle pose when the parking space is at the center point of the perceived area where the parking space is located may be determined as the vehicle final point pose indicated by the perceived map.

The second driving path is a path generated based on the last perceived parking space, and the vehicle position is continuously changed in the process of driving based on the second driving path, so that the real-time acquired sensor data are different, and the parking space perceived based on the sensor data can be dynamically changed. That is, the latest perceived parking space may be different from the last perceived parking space, and thus, there may be a difference between the vehicle endpoint pose indicated by the second travel path and the vehicle endpoint pose indicated by the real-time perceived parking space.

In addition, as the distance from the parking space is closer and closer in the process of the vehicle traveling based on the second traveling path, the parking space dynamically perceived based on the sensor data acquired in real time can be considered to be more and more accurate, namely, the parking space dynamically perceived is considered to be closer to the real parking space.

In summary, when the difference between the vehicle final position and the vehicle final position is greater than the preset position threshold, the difference between the perceived parking space and the dynamic perceived parking space is considered to be greater, so that the non-driving road section in the second driving path can be updated in time to ensure accurate parking.

Specifically, the current position of the vehicle, the position of the perceived obstacle in real time and the perceived position of the parking space can be used as inputs of a path planning algorithm, so that a driving path for the vehicle to park into the parking space from the current position is obtained, that is, a non-driving road section in the second driving path is updated.

The updated second travel path will be more intuitively described with reference to fig. 4.

Referring to fig. 4, a schematic diagram of a third path according to an embodiment of the present application is provided.

In fig. 4, black dots represent the current position of the vehicle, the map parking space refers to the parking space recorded in the pre-constructed parking space map, the perceived parking space is the perceived parking space mentioned above, and the updated perceived parking space represents the dynamically perceived parking space.

As can be seen from fig. 4, the second travel path is a path generated based on the updated perceived parking space from the current position of the vehicle to the position where the updated perceived parking space is located.

It can be seen that in the process that the vehicle runs on the updated second running path, whether the difference between the vehicle final point pose indicated by the second running path and the vehicle final point pose indicated by the perceived parking space is greater than a preset pose threshold or not can be continuously detected on the basis of the dynamically perceived parking space, so that the non-running sub-road section in the second running path can be continuously and dynamically updated until the vehicle is parked in the parking space, and the process can be called as a dynamic planning stage.

From the above, when the scheme provided by the embodiment of the application is applied to parking, the first driving path for driving to the gear shifting place is generated based on the sensor data and the pre-constructed parking space map of the parking space to be parked, and the vehicle is controlled to drive based on the first driving path, when the gear shifting condition is met, the second driving path for parking the vehicle into the parking space can be generated based on the perceived obstacle and the parking space, and the vehicle is controlled to successfully park into the parking space based on the second driving path, so that automatic parking is realized, and convenience is brought to vehicle owners for parking.

The first driving path is generated based on sensor data and a pre-built parking space map of a parking space to be parked, namely, a gear shifting place recorded in the first driving path is determined based on the sensor data and the pre-built parking space map, so that a superior gear shifting place suitable for gear shifting can be determined, and parking efficiency can be improved.

In addition, in the process that the vehicle runs based on the second running path, the non-running road section in the second running path can be updated based on the difference between the vehicle final position and the perceived vehicle final position. Because the distance from the vehicle to the parking space is closer and closer in the process of driving on the basis of the second driving path, the parking space dynamically perceived on the basis of the sensor data acquired in real time can be considered to be more and more accurate, namely, the parking space dynamically perceived is considered to be closer to the real parking space. Therefore, when the difference between the vehicle final position and the vehicle final position is larger than the preset position threshold, the difference between the perceived parking space and the dynamic perceived parking space is larger, so that the non-driving road section in the second driving path is updated, the parking path can be adjusted in real time according to the dynamic perceived parking space, the parking and kneading times are reduced, and the parking accuracy is improved.

In one embodiment of the present application, the following steps a and B may be further included before the step S101.

And A, triggering an automatic parking function ready prompt after detecting that the vehicle is in the area described by the pre-constructed parking space map.

Specifically, the vehicle position can be determined based on the sensor data acquired in real time, and if the vehicle position is in the area described by the pre-constructed parking space map, the automatic parking function ready prompt can be triggered.

The form of the automatic parking function ready prompt can be a popup prompt on a user interface, or can be a prompt message for displaying the automatic parking function ready prompt on the user interface, etc.

And step B, in response to the automatic parking function start instruction, executing step S101.

Specifically, if any one of the following conditions is detected to be satisfied, the automatic parking function start instruction of the vehicle owner can be considered to be received:

The vehicle owner can identify the positive action from the image collected by the vision sensor mounted in the vehicle, and identify the positive voice from the voice picked up by the voice receiving module mounted in the vehicle by touching the automatic parking function starting icon on the user interface.

The positive characterization action may be nodding, a gesture representing "OK", etc., and the positive characterization speech may be "good", "OK", etc.

In one case, the above conditions may be preset by the owner of the vehicle.

It can be seen that after the vehicle is detected to be in the area described by the pre-constructed parking space map, the driver does not need to wait until the driver's eyes see the parking space or the vehicle-mounted sensor detects the parking space, and the automatic parking function ready prompt can be actively triggered, so that the parking process is executed after the automatic parking function start instruction is received, that is, the driver is not depended on the automatic initiation of the parking function start instruction, even if the parking space is blocked, the driver can push the parking function to the driver by himself as long as the vehicle detects that the parking requirement is met, for example, the driver is prompted to start the parking function at the entrance of the parking space, so that the whole parking process is more convenient and humanized, and the user experience in the parking process is improved.

Another way of generating the aforementioned first travel path and second travel path is described below through steps C-F. Since the first travel path and the second travel path are generated in a similar manner, the first travel path and the second travel path are hereinafter referred to as travel paths.

And C, sensing obstacles around the vehicle based on the sensor data, and obtaining an avoidance priority representation value of the sensed obstacles.

The embodiment of the application is not limited to a mode of sensing the obstacle around the vehicle based on the sensor, and is not repeated here.

The manner in which the avoidance priority characteristic value of the perceived obstacle is obtained is described below.

In one embodiment, a confidence coefficient correction coefficient of the perceived obstacle category, a second distance between each side of the obstacle and the parking space, and a second distance corresponding to each side of the obstacle can be obtained, and an avoidance priority characterization value of the perceived obstacle is obtained based on the obtained obstacle category, confidence coefficient correction coefficient and second distance.

According to different paths to be generated, the parking spaces can be the parking spaces in the pre-constructed parking space map or the perceived parking spaces. For example, the space may be a space in a pre-constructed space map when the first travel path is generated, and the space may be a perceived space when the second travel path is generated.

The second distance is not limited by the embodiment of the present application, and is illustrated by way of example.

In this case, the second distance may be a distance between each side of the three-dimensional contour of the obstacle and the parking space.

For example, the distance between the center point of each side of the three-dimensional profile and the center point of the parking space parking side may be set.

In another case, the second distance may be a distance between each side of the projection area of the obstacle on the ground and the parking space.

For example, the distance between the center point of each side of the projection area and the center point of the parking space parking side may be set.

In one case, the perceived avoidance priority characterization value for each obstacle may be obtained according to the following expression:

Wherein W _i represents the avoidance priority value of the obstacle i, c _i represents the priority coefficient of the obstacle class of the obstacle i, V represents the position of the parking space, E _i,j represents the position of the jth side of the obstacle i, dis (E _i,j, V) represents the second distance between the jth side of the obstacle i and the parking space, δ _i,j represents the confidence coefficient of the second distance, α represents the preset scaling factor, and W _max represents the preset maximum avoidance priority value.

Based on the above expression, it can be seen that when the second distance between each side of the obstacle and the parking space is not 0, a certain distance is still provided between the obstacle and the parking space, and the avoidance priority representation value can be determined based on the priority coefficient of the category of the obstacle and the second distance between each side of the obstacle and the parking space, and when the second distance between one side of the obstacle and the parking space is 0, a certain side of the obstacle is already closely attached to the parking space, so that the collision risk between the vehicle and the obstacle is high in the process of parking the vehicle into the parking space, and therefore the avoidance priority representation value of the obstacle can be determined as the maximum avoidance priority representation value.

Therefore, after the confidence coefficient correction coefficients of the perceived obstacle category, the second distance between each side of the obstacle and the parking space and the second distance corresponding to each side are obtained, the avoidance priority representation value of the obstacle can be obtained rapidly and accurately based on the expression.

In another embodiment, the priority scores corresponding to the obstacle category, the correction coefficient and the second distance of the obstacle may be determined based on the preset corresponding relation between the obstacle category, the correction coefficient and the second distance and the priority scores, and then the priority scores corresponding to the obstacle category, the correction coefficient and the second distance are weighted according to the corresponding preset weight, and the obtained calculation result is used as the avoidance priority representation value of the obstacle.

Therefore, the avoidance priority representation value of the obstacle is comprehensively determined based on the perceived obstacle category of the obstacle, the second distance between each side of the obstacle and the parking space and the confidence coefficient correction coefficient of the second distance corresponding to each side, so that the determined avoidance priority representation value is related to the obstacle category and the second distance between each side of the obstacle and the parking space, and the more comprehensive and accurate avoidance priority representation value can be obtained.

And D, classifying the perceived obstacle to obtain a high-priority obstacle with the avoidance priority characterization value larger than a preset characterization value threshold and a low-priority obstacle with the avoidance priority characterization value not larger than the characterization value threshold.

It can be seen that the avoidance priority characterization value characterizes the influence degree of the obstacle on the vehicle when the vehicle is parked in the parking space, so that the obstacle with the avoidance priority characterization value larger than the preset characterization value threshold can be determined to be a high-priority obstacle, and the obstacle with the avoidance priority characterization value smaller than the preset characterization value threshold can be determined to be a low-priority obstacle.

In one case, the category of perceived obstacle i may be determined based on the following expression:

When type _i is 1, it indicates that the obstacle i is a high priority obstacle, and when type _i is 0, it indicates that the obstacle i is a low priority obstacle, and W _standard indicates the above-described characteristic value threshold.

And E, constructing a parkable area based on the high-priority obstacle, and obtaining a boundary line of the parkable area.

Specifically, since the high-priority obstacle has been determined at this time, it is possible to construct a parkable region based on each side of the high-priority obstacle, and obtain the boundary line of the parkable region.

For example, based on the closest side to the parking space among the sides of each high-priority obstacle, the parkable region may be determined, and thus the boundary line of the parkable region may be obtained.

The boundary line will be described more intuitively with reference to fig. 5.

Referring to fig. 5, a schematic diagram of a boundary line is provided in an embodiment of the present application.

In fig. 5, non-motor vehicle 1, non-motor vehicle 2, motor vehicle 1, motor vehicle 2, and cone 2 represent high priority obstacles, pedestrian 1, motor vehicle 3, non-motor vehicle 3, cone 1, and cone 3 represent low priority obstacles, and black lines represent boundary lines of a parking area.

As can be seen from fig. 5, the parkable region can be determined based on the closest side to the parking space among the sides of each high-priority obstacle, so that the boundary line of the parkable region can be obtained.

In one embodiment of the application, when the parkable area is constructed based on the high-priority obstacle, the parkable area can be constructed based on the sensing result of the high-priority obstacle corresponding to each type of sensor.

The sensing result corresponding to each type of sensor is a result of sensing the obstacle by adopting data acquired by the type of sensor.

In one case, the sensor may include a vision camera and an ultrasonic radar.

Correspondingly, the perception result of the visual camera on the high-priority obstacle can comprise an obstacle classification result aiming at the image acquired by the visual camera and an obstacle detection result aiming at the image, and the perception result of the ultrasonic radar on the high-priority obstacle can comprise a radar detection result.

In this case, the confidence priorities of the sensing results corresponding to each type of sensor may be comprehensively considered, and the parking-capable area may be constructed.

For example, according to the order of the confidence level priority from high to low, the sensing result of the ultrasonic radar on the high-priority obstacle, the obstacle classification result corresponding to the visual camera and the obstacle detection result corresponding to the visual camera are fused to obtain the comprehensive sensing result of the high-priority obstacle, so that the parking area is constructed based on the comprehensive sensing result of the high-priority obstacle.

Therefore, the accuracy of the high-priority obstacle sensing can be improved by comprehensively considering the sensing results of the high-priority obstacles corresponding to the various types of sensors, so that the accuracy of the parking area constructed based on the sensing results of the high-priority obstacles corresponding to the various types of sensors is improved.

And F, generating a driving path which does not collide with the boundary line and the low-priority obstacle.

In one embodiment of the present application, a travel path that does not collide with both the boundary line and the low-priority obstacle may be generated based on the result of sensing a high-priority obstacle corresponding to each type of sensor and the result of sensing a low-priority obstacle corresponding to a preset type of sensor.

In one case, the sensor of the above-mentioned preset type may be a vision camera. Thus, the sensing result of the low-priority obstacle corresponding to the sensor of the preset type may be an obstacle classification result for the image acquired by the vision camera and an obstacle detection result for the image.

It can be seen that the perception result of the low-priority obstacle corresponding to the sensor of the preset type is considered when the driving path is generated. Because the low-priority obstacle is an obstacle with smaller influence degree when the vehicle is parked in the parking space, the requirement on the perception accuracy of the low-priority obstacle is lower, and therefore, the efficiency when the high-priority obstacle is perceived can be improved by only obtaining the perception result of the low-priority obstacle corresponding to the preset type of sensor, and the efficiency when the driving path is generated based on the perception result of the low-priority obstacle is improved.

The following describes a mode of generating a travel path that does not collide with both the boundary line and the low-priority obstacle.

In one embodiment, the candidate paths may be generated based on the boundary lines and the low-priority obstacles, and then the boundary lines and the low-priority obstacles are projected to the grid map to obtain the grid map recorded with the obstacle information, so that the collision paths in the candidate paths are determined based on the collision situation between the candidate paths and the obstacle information in the grid map.

The generation method of the candidate paths is similar to the generation method of the paths described in the step S101, and only the boundary line and the low-priority obstacle are used as inputs of the path planning algorithm, which is not described herein.

After the boundary line and the low-priority obstacle are projected to the grid map, the boundary line and the low-priority obstacle are recorded in the grid map, so that a collision path in the candidate path can be determined based on the collision condition between the candidate path and the obstacle information in the grid map.

The manner in which the above collision condition is determined will be described below.

In one case, whether the candidate path collides with the grid where the low-priority obstacle is located in the grid map can be judged, if so, the candidate path is directly determined to be the collision path, and if not, the candidate path is determined to be the collision path under the conditions that the candidate path collides with the grid where the boundary line is located in the grid map and the vector line of the boundary line.

The collision detection flow is described more intuitively with reference to fig. 6.

Referring to fig. 6, a schematic diagram of a collision detection process according to an embodiment of the present application is provided, and the process shown in fig. 6 includes the following steps S601 to S608.

Step S601, classifying the perceived obstacle to obtain a high-priority obstacle and a low-priority obstacle.

Step S602, constructing a parkable area based on the high-priority obstacle, and obtaining a boundary line of the parkable area.

Step S603, projecting the boundary line and the low priority obstacle to the grid map.

Step S604, judging whether the candidate path collides with the grid where the low priority obstacle is located, if yes, executing step S608, and if no, executing step S605.

If it is determined that the candidate path collides with the grid where the low priority obstacle is located, step S608 is executed to directly determine that the candidate path is a collision path, otherwise step S605 is executed to determine whether the candidate path collides with the grid where the boundary line is located.

Step S605, judging whether the candidate path collides with the grid where the boundary line is located, if yes, executing step S606, and if no, executing step S607.

If it is determined that the candidate path collides with the grid where the boundary line is located, step S606 may be executed to continuously determine whether the candidate path collides with the boundary line vector line, or else, determine that the candidate path is not the collision path.

Step S606, judging whether the candidate path collides with the boundary line vector line, if yes, executing step S608, and if not, executing step S607.

If it is determined whether the candidate path collides with the boundary line vector line, it means that the candidate path collides with both the grid where the boundary line is located and the boundary line vector line, so that step S608 may be executed to determine that the candidate path is a collision path, otherwise step S607 is executed to determine that the candidate path is not a collision path.

Step S607, determining that the candidate path is not the collision path.

Step S608, determining the candidate path as the collision path.

On the one hand, the low-priority obstacle is an obstacle with smaller influence degree when the vehicle is parked in the parking space, the distance from the low-priority obstacle to the parking space is generally longer, and the accuracy requirement on the perception result of the low-priority obstacle is lower, so that if the candidate path collides with the grid where the low-priority obstacle is located in the grid map, the candidate path can be directly considered to collide with the low-priority obstacle, namely, the candidate path is a collision path, and the efficiency of determining the candidate path is improved.

On the other hand, since the high-priority obstacle is an obstacle having a large degree of influence when the vehicle is parked in the parking space, the distance from the parking space is generally short, and the accuracy requirement for the perceived result of the high-priority obstacle is also high, the accuracy of the boundary line of the parkable region determined based on the high-priority obstacle is high. Based on the above, when the candidate path collides with the grid where the boundary line in the grid map is located, the precise comparison between the candidate path and the vector line of the boundary line can be performed, and if the candidate path collides with both the grid where the boundary line in the grid map is located and the vector line of the boundary line, the candidate path is determined to collide with the boundary line, that is, the candidate path is determined to be the collision path, so that the accuracy in determining the candidate path is improved.

Therefore, after the boundary line and the low-priority obstacle are projected to the grid map, the collision situation between the candidate path and the boundary line and the low-priority obstacle in the grid map can be conveniently determined based on the grid where the boundary line and the low-priority obstacle are located in the grid map, so that the collision path in the candidate path can be quickly determined based on the collision situation.

In another case, if the candidate path is judged to collide with any one of the grids of the low-priority obstacle or the high-priority obstacle in the grid map, the candidate path can be determined to be a collision path.

In another embodiment, the boundary line, the position of the low priority obstacle, and the candidate path may be unified under the same two-dimensional coordinate system, and then, based on the intersection of the line segment of the candidate path under the two-dimensional coordinate system and the boundary line under the two-dimensional coordinate system, and the positional relationship between the line segment corresponding to the candidate path and the point of the low priority obstacle under the two-dimensional coordinate system, it is determined whether the candidate path is the collision path.

Specifically, if the line segment corresponding to the candidate path intersects with the line segment corresponding to the boundary line, or if the point corresponding to the low-priority obstacle is located in the line segment corresponding to the candidate path, it may be determined whether the candidate path is a collision path.

From the above, when the driving path is generated by applying the scheme provided by the embodiment of the application, firstly, the perceived obstacle is classified based on the avoidance priority representation value obtained, the high-priority obstacle and the low-priority obstacle are obtained, and the parkable area is constructed based on the high-priority obstacle, and the boundary line of the parkable area is obtained, so that the driving path which does not collide with the boundary line and the low-priority obstacle can be generated, the collision situation between the vehicle and the obstacle in the driving process based on the generated driving path can be reduced, and the safety of the parking process is improved.

In addition, the parkable area is constructed based on the high-priority obstacles, the boundary line of the parkable area is a continuous line segment, and the positions of the high-priority obstacles are discrete points, so that the generated path is ensured not to collide with the boundary line, and compared with the condition that the generated path is ensured not to collide with each high-priority obstacle, the probability of collision between the generated path and each high-priority obstacle can be further reduced, and the rationality and the safety of the parking process are further improved.

Referring to fig. 7, a flow chart of a second parking method according to an embodiment of the present application is shown, where the method includes the following steps S701-S706.

Step S701, controlling the vehicle to cruise based on the sensor data and the travel path information recorded in the pre-constructed map.

Specifically, the vehicle position may be determined based on the sensor data, and then the vehicle may be controlled to cruise based on the path indicated by the travel path information recorded in the pre-constructed map based on the deviation between the vehicle position and the path indicated by the travel path information.

Step S702, during cruising, a first distance between a vehicle and a parking space to be parked is obtained based on sensor data.

Specifically, the first distance between the vehicle and the parking space may be obtained in the following manner.

In one case, the distance between the rear axle of the vehicle and the parking space is obtained as the first distance between the vehicle and the parking space based on the sensor data.

The parking boundary line refers to a boundary line through which a vehicle passes when entering a parking space, among 4 boundary lines of the parking space.

Thus, the distance between the rear wheel axle of the vehicle and the parking space is used as the first distance, and the rear wheel of the vehicle can first touch the parking space parking boundary line because the vehicle is parked into the parking space through reversing, therefore, the distance between the rear wheel axle of the vehicle and the parking space can accurately represent the distance between the vehicle and the parking space, so that the accuracy of generating the first driving path based on the first distance can be improved.

Step S703, judging whether the first distance is smaller than a preset distance threshold, if yes, executing step S704.

The distance threshold may be set by a worker according to an actual scene or experience.

Step S704, a first travel path for traveling to a gear shifting place is generated based on sensor data acquired by a sensor carried by the vehicle and a pre-constructed parking space map of a parking space to be parked, and the vehicle is controlled to travel based on the first travel path.

This step is the same as step S101 in the embodiment shown in fig. 1, and will not be described again here.

In this case, if the first travel path generation fails, it may be further determined whether the vehicle has traveled to a cruising end point recorded in the pre-built map, and if not, the vehicle may be controlled to continue cruising based on the sensor data and the travel path information recorded in the pre-built parking space map.

Under the condition that the first travel path is failed to be generated, if the vehicle does not travel to the cruise endpoint recorded in the pre-constructed map, the vehicle can be controlled to continue to cruise, so that the new occasion meeting the condition that the first distance is smaller than the preset distance threshold value is determined in the subsequent cruise process, the first travel path is regenerated, and the completeness and rationality of the scheme are improved.

Step S705, if the gear shifting condition is met, sensing obstacles around the vehicle based on the sensor data, sensing a parking space to be parked, generating a second driving path for parking the vehicle into the parking space to be parked based on the sensed obstacles and the sensed parking space, controlling the vehicle to switch the gear shifting position, and parking the vehicle into the parking space to be parked based on the second driving path.

Step S706, if the difference between the final position and the final position of the vehicle indicated by the second driving path and the final position of the vehicle indicated by the perceived parking space is larger than a preset position and position threshold value in the driving process of the vehicle based on the second driving path, updating the non-driving road section in the second driving path based on the perceived obstacle and the perceived parking space.

The steps S705 to S706 are the same as the steps S102 to S103 in the embodiment shown in fig. 1, and are not described here again.

From the above, when the scheme provided by the embodiment of the application is applied to parking, the vehicle can be controlled to cruise based on the sensor data and the travel path information recorded in the pre-constructed map, and in the process of cruising, the first distance between the vehicle and the parking space to be parked is obtained, so that when the first distance is smaller than the preset distance threshold value, the first travel path for traveling to the gear shifting place can be generated, that is, when the distance between the vehicle and the parking space is smaller, the first travel path can be generated. Because the sensor carried on the vehicle is accurate in sensing result of the information around the parking space when the distance between the vehicle and the parking space is smaller, the first travel path is generated at the moment, and the accuracy of the generated first travel path can be improved.

In addition, the first driving path which drives to the gear shifting place can be generated before the vehicle does not reach the cruise endpoint, so that the gear shifting place which is earlier than the cruise endpoint can be determined, the advanced reversing is realized, and the parking efficiency is improved.

In one embodiment of the present application, the shift condition in the embodiment shown in fig. 7 described above includes at least one of the following conditions:

The vehicle is driven to a cruising end point recorded in the pre-constructed map, the vehicle is driven to a gear shifting position based on a first driving path, and the vehicle is stopped in the driving process based on the first driving path.

The above various shift conditions have been described in the step S102 of the embodiment shown in fig. 1, and are not described here again.

It should be noted that, in the above-described embodiments of the automatic parking method, different implementations of each step and implementations of the adding step may be referred to each other and combined to obtain a new embodiment, which is not described herein again.

The following describes a parking process in its entirety.

Referring to fig. 8, a schematic diagram of a parking process according to an embodiment of the present application is provided.

As can be seen from fig. 8, after a certain parking condition is satisfied, a parking process may be performed, and the parking process may be divided into three phases, i.e., a gear shift planning phase, a static planning phase, and a dynamic planning phase, which are described below.

A gear shifting planning stage:

Firstly, whether the distance between the vehicle and the parking space is smaller than a distance threshold value can be judged, if not, the vehicle can be controlled to continue cruising, whether the vehicle reaches a cruising end point is judged, if yes, a static planning stage is entered, if not, whether the distance between the vehicle and the parking space is smaller than the distance threshold value is judged, if yes, a gear shifting planning stage is entered, a first planning path is generated, whether the generation is successful is judged, if not, whether the vehicle reaches the cruising end point is judged, if yes, whether gear shifting conditions are met is judged, and if yes, the static planning stage is entered.

Static planning stage:

and generating a second planning path, judging whether the generation is successful, if so, controlling the vehicle to run based on the second planning path, and judging whether the pose difference between the vehicle final position pose indicated by the second running path and the perceived vehicle final position pose indicated by the parking space is larger than a pose threshold value in the running process, if so, entering a dynamic planning stage, if not, judging whether to park in the parking space, and if not, namely, if not, stopping the flow if the path generation fails.

Dynamic programming:

And if so, returning to the step of updating the non-traveling sub-road section in the second planning path, otherwise, judging whether the parking space is parked, if not, continuing to judge whether the pose difference is greater than the pose threshold, namely, continuously detecting whether the pose difference is greater than the pose threshold before parking the parking space, and if so, controlling the vehicle to travel to a parking point and returning to the step of generating the second planning path in the static planning stage.

Corresponding to the parking method, the embodiment of the application also provides a parking device.

Referring to fig. 9, a schematic structural diagram of a parking device according to an embodiment of the present application is provided, where the device includes the following modules:

the first travel path generation module 901 is configured to generate a first travel path for traveling to a shift location based on sensor data acquired by a sensor carried by a vehicle and a pre-constructed parking space map of a parking space to be parked, and control the vehicle to travel based on the first travel path;

A second driving path generating module 902, configured to, if a gear shift condition is met, sense an obstacle around the vehicle based on the sensor data, sense the parking space to be parked, generate a second driving path for the vehicle to park in the parking space to be parked based on the sensed obstacle and the sensed parking space, control the vehicle to switch gear and park in the parking space to be parked based on the second driving path;

The path updating module 903 is configured to update, during a running process of the vehicle based on the second running path, a non-running road section in the second running path based on the perceived obstacle and the perceived parking space if a difference between the vehicle endpoint pose indicated by the second running path and the vehicle endpoint pose indicated by the perceived parking space is greater than a preset pose threshold.

In addition, in the process that the vehicle runs based on the second running path, the non-running road section in the second running path can be updated based on the difference between the vehicle final position and the perceived vehicle final position. Because the distance from the vehicle to the parking space is closer and closer in the process of driving on the basis of the second driving path, the parking space dynamically perceived on the basis of the sensor data acquired in real time can be considered to be more and more accurate, namely, the position of the parking space dynamically perceived is considered to be closer to the position of the real parking space. Therefore, when the difference between the vehicle final position and the vehicle final position is larger than the preset position threshold, the difference between the perceived parking space and the dynamic perceived parking space is larger, so that the non-driving road section in the second driving path is updated, the parking path can be adjusted in real time according to the real-time perceived parking space, the parking and kneading times are reduced, and the parking accuracy is improved.

In one embodiment of the present application, before the first travel path generation module 901, the method further includes:

The first cruising module is used for controlling the vehicle to cruise based on the sensor data and the driving path information recorded in the pre-constructed map;

The first distance obtaining module is used for obtaining a first distance between the vehicle and the parking space to be parked based on the sensor data in the cruising process;

The distance determining module is configured to trigger the first driving path generating module 901 if the first distance is less than a preset distance threshold.

In one embodiment of the present application, the first distance obtaining module is specifically configured to obtain, based on the sensor data, a distance between the rear axle of the vehicle and a parking boundary line of the parking space to be parked as a first distance between the vehicle and the parking space to be parked during cruising.

In one embodiment of the present application, if the first travel path generation fails, the apparatus further includes:

the terminal judging module is used for judging whether the vehicle runs to a cruising terminal recorded in the pre-constructed map or not, and if not, triggering a second cruising module;

And the second cruising module is used for controlling the vehicle to continue cruising based on the sensor data and the driving path information recorded in the pre-built parking space map.

In one embodiment of the present application, the shift condition includes at least one of:

The vehicle is driven to a cruising end point recorded in the pre-constructed map, the vehicle is driven to the gear shifting place based on the first driving path, and the vehicle is stopped in the driving process based on the first driving path.

If the vehicle is parked, the vehicle is prevented from being blocked along a serious path in the process of traveling along the first traveling path, and cannot continue traveling based on the fine adjustment of the path, so that the vehicle is determined to meet the gear shifting condition at the moment so as to carry out subsequent path planning, long-time parking of the vehicle can be avoided, and the parking efficiency is improved.

In one embodiment of the present application, the first travel path generating module 901 is specifically configured to generate a complete travel path for the vehicle to park in a parking space to park in based on sensor data acquired by a sensor carried by the vehicle and a pre-constructed parking space map of the parking space to park in, and intercept a path before a shift location recorded in the complete travel path as a first travel path for traveling to the shift location.

In one embodiment of the application, the travel path is generated according to the following modules, wherein the travel path comprises the first travel path and/or the second travel path:

The obstacle sensing module is used for sensing obstacles around the vehicle based on the sensor data and obtaining an avoidance priority representation value of the sensed obstacles;

The obstacle classification module is used for classifying perceived obstacles to obtain high-priority obstacles with avoidance priority characterization values larger than a preset characterization value threshold and low-priority obstacles with avoidance priority characterization values not larger than the characterization value threshold;

The system comprises a boundary line obtaining module, a parking area obtaining module and a parking area obtaining module, wherein the boundary line obtaining module is used for constructing a parking area based on a high-priority obstacle and obtaining the boundary line of the parking area;

And the third driving path generation module is used for generating a driving path which does not collide with the boundary line and the low-priority obstacle.

In one embodiment of the present application, the third travel path generation module includes:

A candidate path generation sub-module for generating a candidate path based on the boundary line and a low priority obstacle;

The projection submodule is used for projecting the boundary line and the low-priority obstacle to the grid map to obtain the grid map recorded with the obstacle information;

the collision path determining submodule is used for determining collision paths in the candidate paths based on collision conditions between the candidate paths and obstacle information in the grid map;

and the driving path selection sub-module is used for selecting a driving path from candidate paths except the collision path.

In one embodiment of the application, the collision path determination submodule is specifically configured to determine whether a candidate path collides with a grid where a low-priority obstacle is located in the grid map, if so, directly determine that the candidate path is a collision path, and if not, determine that the candidate path is a collision path when the candidate path collides with both the grid where the boundary line is located in the grid map and a vector line of the boundary line.

In one embodiment of the present application, the obstacle sensing module includes:

The information obtaining sub-module is used for sensing obstacles around the vehicle based on the sensor data and obtaining a category of the obstacle of the sensed obstacle, a second distance between each side of the obstacle and a parking space and a confidence coefficient of the second distance corresponding to each side, wherein the parking space comprises a parking space in the pre-built parking space map and/or a sensed parking space;

The characterization value obtaining sub-module is used for obtaining the avoidance priority characterization value of the perceived obstacle based on the obtained obstacle category, the second distance and the confidence coefficient.

In one embodiment of the present application, the characterization value obtaining submodule is specifically configured to obtain the avoidance priority characterization value of each perceived obstacle according to the following expression:

wherein W _i represents an avoidance priority representation value of an obstacle i, c _i represents a priority coefficient of an obstacle class of the obstacle i, V represents a position of the parking space, E _i,j represents a position of a jth edge of the obstacle i, dis (E _i,j, V) represents a second distance between the jth edge of the obstacle i and the parking space, δ _i,j represents a confidence correction coefficient of the second distance, α represents a preset scaling factor, and W _max represents a preset maximum avoidance priority representation value.

In one embodiment of the application, the sensor comprises multiple types of sensors;

The boundary line obtaining module is specifically configured to construct a parkable area based on sensing results of high-priority obstacles corresponding to each type of sensor, where the sensing result corresponding to each type of sensor is a result of sensing the obstacle by using data collected by the type of sensor, and obtain a boundary line of the parkable area;

the third driving path generating module is specifically configured to generate a driving path that does not collide with the boundary line and the low-priority obstacle based on a sensing result of the high-priority obstacle corresponding to each type of sensor and a sensing result of the low-priority obstacle corresponding to the preset type of sensor.

In addition, the perception result of the low-priority obstacle corresponding to the sensor of the preset type is considered when the driving path is generated. Because the low-priority obstacle is an obstacle with smaller influence degree when the vehicle is parked in the parking space, the requirement on the perception accuracy of the low-priority obstacle is lower, and therefore, the efficiency when the high-priority obstacle is perceived can be improved by only obtaining the perception result of the low-priority obstacle corresponding to the preset type of sensor, and the efficiency when the driving path is generated based on the perception result of the low-priority obstacle is improved.

the parking function prompt module is used for triggering an automatic parking function ready prompt after detecting that the vehicle is in the area described by the pre-constructed parking space map;

And the indication response module is used for responding to the automatic parking function starting indication and triggering the first driving path generation module 901.

It can be seen that after the vehicle is detected to be in the area described by the pre-constructed parking space map, the automatic parking function ready prompt can be actively triggered, so that the parking process is executed after the automatic parking function start instruction is received, that is, the parking function is automatically pushed to the vehicle owner after the vehicle owner actively initiates the parking function start instruction, and the vehicle owner can start parking only by simple confirmation, so that the whole parking process is more convenient and humanized, and the user experience in the parking process is improved.

In one embodiment of the application, the pre-constructed parking space map is constructed as follows:

After the vehicle is parked in the parking space to be parked, determining whether the parking space to be parked is a fixed parking space of the vehicle or not based on historical parking information of the vehicle in the parking space to be parked, if so, triggering a map construction prompt for the parking space to be parked, and constructing a parking space map of the parking space to be parked based on cached sensor data in response to the map construction instruction to obtain the pre-constructed parking space map.

Therefore, the method and the system can actively remind the vehicle owner of whether to construct a parking space map under the condition that the parking space is the fixed parking space of the vehicle according to the historical parking information of the parking space, and perform map construction after being confirmed without additional operation of the vehicle owner, so that user experience is improved, in addition, after being confirmed, the map construction can be directly performed based on cached sensor data, the process is noninductive for the user, the process is convenient for the vehicle owner, and the practicability of the scheme is improved.

In one embodiment of the present application, the pre-constructed parking space map of the parking space to be parked includes a fixed parking space of the vehicle, and the fixed parking space of the vehicle includes:

the space management system synchronizes the paid space to the vehicle and/or,

In the scheme provided by the embodiment of the application, the related processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the personal information of the user are executed on the premise that the user is aware and authorized, and the related legal regulations are met, so that the public order welcome is not violated.

The embodiment of the application also provides a vehicle-mounted control device, as shown in fig. 10, which comprises:

a memory 1001 for storing a computer program;

the controller 1002 is configured to implement the parking method described above when executing a program stored in the memory 1001.

And the vehicle-mounted control device may further include a communication bus and/or a communication interface, where the controller 1002, the communication interface, and the memory 1001 perform communication with each other through the communication bus.

The communication bus mentioned for the above-mentioned in-vehicle control device may be a peripheral component interconnect standard (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, or the like. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.

The communication interface is used for communication between the vehicle-mounted control equipment and other equipment.

The Memory may include random access Memory (Random Access Memory, RAM) or may include Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned controller.

The controller may be a general-purpose Processor including a central processing unit (Central Processing Unit, CPU), a network Processor (Network Processor, NP), etc., or may be a digital signal Processor (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components.

In yet another embodiment of the present application, a computer readable storage medium is provided, in which a computer program is stored, which when executed by a controller, implements the above-described parking method.

In yet another embodiment of the present application, a vehicle is provided, in which a computer program is stored, which when executed by a controller, implements the above-described parking method.

In yet another embodiment of the present application, a computer program product containing instructions that, when run on a computer, cause the computer to perform any of the above-described embodiments of the parking method is also provided.

In the above embodiments, it may be implemented in whole or in part 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, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, 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 such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, tape), an optical medium (e.g., DVD), or a Solid state disk (Solid STATE DISK, SSD), etc.

It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.

In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for the apparatus, the in-vehicle control device, and the storage medium embodiment, since they are substantially similar to the method embodiment, the description is relatively simple, and reference is made to the partial description of the method embodiment for relevant points.

The foregoing description is only of the preferred embodiments of the present application and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application are included in the protection scope of the present application.

Claims

1. A method of parking, the method comprising:

in the running process of the vehicle based on the second running path, if the difference between the vehicle final position and the vehicle final position is larger than a preset position threshold, updating a non-running road section in the second running path based on the perceived obstacle and the perceived parking space;

the driving path is generated according to the following mode, wherein the driving path comprises a first driving path and/or a second driving path, the first driving path and/or the second driving path are/is used for sensing obstacles around the vehicle based on the sensor data and obtaining avoidance priority representation values of the sensed obstacles, the sensed obstacles are classified to obtain high-priority obstacles with the avoidance priority representation values being larger than a preset representation value threshold and low-priority obstacles with the avoidance priority representation values not larger than the representation value threshold, a parkable area is built based on the high-priority obstacles and the boundary line of the parkable area is obtained, and the driving path which does not collide with the boundary line and the low-priority obstacles is generated.

2. The method of claim 1, wherein the step of determining the position of the substrate comprises,

Before the first travel path to the gear shifting place is generated based on the sensor data acquired by the sensor carried by the vehicle and the pre-built parking space map of the parking space to be parked, the method further comprises the steps of controlling the vehicle to cruise based on the sensor data and travel path information recorded in the pre-built parking space map, acquiring a first distance between the vehicle and the parking space to be parked based on the sensor data in the cruising process, and executing the first travel path to the gear shifting place based on the sensor data acquired by the sensor carried by the vehicle and the pre-built parking space map of the parking space to be parked if the first distance is smaller than a preset distance threshold.

3. The method of claim 2, wherein the step of determining the position of the substrate comprises,

The method for obtaining the first distance between the vehicle and the parking space to be parked based on the sensor data comprises the steps of obtaining the distance between a rear wheel axle of the vehicle and a parking boundary line of the parking space to be parked based on the sensor data as the first distance between the vehicle and the parking space to be parked;

And/or

If the first travel path generation fails, judging whether the vehicle has traveled to a cruising end point recorded in the pre-built parking space map, and if not, controlling the vehicle to continue cruising based on the sensor data and travel path information recorded in the pre-built parking space map;

And/or

The gear shifting condition comprises at least one of the following conditions that the vehicle runs to a cruising end point recorded in the pre-built parking space map, the vehicle runs to the gear shifting place based on the first running path, and the vehicle stops in the running process based on the first running path.

4. The method of claim 1, wherein the step of determining the position of the substrate comprises,

The method comprises the steps of generating a candidate path based on the boundary line and the low-priority obstacle, projecting the boundary line and the low-priority obstacle to a grid map to obtain the grid map recorded with obstacle information, determining the collision path in the candidate path based on the collision condition between the candidate path and the obstacle information in the grid map, and selecting the running path from the candidate paths except the collision path;

And/or

The method comprises the steps of obtaining a confidence coefficient correction coefficient of a perceived obstacle category, a second distance between each side of the obstacle and a parking space, and a second distance corresponding to each side of the obstacle, wherein the parking space comprises a parking space and/or a perceived parking space in the pre-constructed parking space map, and obtaining the perceived obstacle avoidance priority representation value based on the obtained obstacle category, the second distance and the confidence coefficient correction coefficient.

5. The method of claim 4, wherein the step of determining the position of the first electrode is performed,

The method comprises the steps of determining whether a candidate path collides with a grid where a low-priority obstacle is located in a grid map or not based on collision conditions between the candidate path and obstacle information in the grid map, if so, directly determining the candidate path as the collision path, and if not, determining the candidate path as the collision path under the condition that the candidate path collides with the grid where the boundary line is located in the grid map and a vector line of the boundary line.

6. The method of claim 1, wherein the sensor comprises a multi-type sensor;

The constructing a parkable area based on the high priority obstacle comprises the following steps:

Constructing a parking area based on the sensing results of the high-priority obstacles corresponding to the sensors of each type, wherein the sensing results corresponding to the sensors of each type are the results of sensing the obstacles by adopting the data acquired by the sensors of each type;

the generating a travel path that does not collide with both the boundary line and a low-priority obstacle includes:

and generating a driving path which does not collide with the boundary line and the low-priority obstacle based on the sensing result of the high-priority obstacle corresponding to each type of sensor and the sensing result of the low-priority obstacle corresponding to the preset type of sensor.

7. The method according to any one of claims 1 to 6, wherein,

Before the pre-constructed parking space map of the parking space to be parked and the sensor data acquired based on the sensors carried by the vehicle are generated, the method further comprises the steps of triggering an automatic parking function ready prompt after detecting that the vehicle is in an area described by the pre-constructed parking space map;

And/or

The method comprises the steps of after detecting that a vehicle is parked in a parking space to be parked, determining whether the parking space to be parked is a fixed parking space of the vehicle or not based on historical parking information of the vehicle in the parking space to be parked, if so, triggering a map construction prompt for the parking space to be parked, and constructing a parking space map of the parking space to be parked based on cached sensor data in response to a map construction instruction to obtain the pre-constructed parking space map.

8. The method of any one of claims 1-6, wherein the pre-constructed parking space map of the parking space to be parked comprises a fixed parking space of the vehicle, the fixed parking space of the vehicle comprising:

the space management system synchronizes the paid space to the vehicle and/or,

9. An in-vehicle control apparatus, characterized by comprising:

A memory for storing a computer program;

A controller for implementing the method of any one of claims 1-8 when executing a program stored on a memory.

10. A vehicle having a computer program stored therein, which when executed by a controller, implements the method of any one of claims 1-8.