CN114690750A - Remote passenger-replacing parking method and system - Google Patents
Remote passenger-replacing parking method and system Download PDFInfo
- Publication number
- CN114690750A CN114690750A CN202210296147.4A CN202210296147A CN114690750A CN 114690750 A CN114690750 A CN 114690750A CN 202210296147 A CN202210296147 A CN 202210296147A CN 114690750 A CN114690750 A CN 114690750A
- Authority
- CN
- China
- Prior art keywords
- module
- parking
- information
- state
- output
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000013439 planning Methods 0.000 claims description 88
- 230000006870 function Effects 0.000 claims description 62
- 230000004927 fusion Effects 0.000 claims description 61
- 238000007726 management method Methods 0.000 claims description 51
- 230000008447 perception Effects 0.000 claims description 40
- 238000013523 data management Methods 0.000 claims description 15
- 230000001133 acceleration Effects 0.000 claims description 13
- 238000013461 design Methods 0.000 claims description 12
- 238000003745 diagnosis Methods 0.000 claims description 12
- 238000005286 illumination Methods 0.000 claims description 12
- 238000012544 monitoring process Methods 0.000 claims description 12
- 238000007499 fusion processing Methods 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 9
- 230000007246 mechanism Effects 0.000 claims description 9
- 230000003068 static effect Effects 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 7
- 230000009471 action Effects 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000013459 approach Methods 0.000 claims description 2
- 238000011161 development Methods 0.000 abstract description 4
- 230000006399 behavior Effects 0.000 description 35
- 230000010354 integration Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/0055—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots with safety arrangements
- G05D1/0061—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots with safety arrangements for transition from automatic pilot to manual pilot and vice versa
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The invention relates to a remote passenger-riding parking method and system. The invention solves the problems of limited use and long-distance passenger-riding parking scenes, can ensure that the long-distance passenger-riding parking can be really used in any parking lot, does not need to consume a large amount of manpower, financial resources and material resources, does not need to use the function after the infrastructure and map acquisition coverage are complete after a plurality of years, and can be used as long as a vehicle is provided with the long-distance passenger-riding parking system. The invention really solves the pain of the user, meets the real requirements of the user and promotes the rapid application and development of remote valet parking.
Description
Technical Field
The invention belongs to the technical field of parking, and particularly relates to a remote passenger-riding parking method and system.
Background
At present, the prior art related to a remote passenger-replacing parking system is mainly divided into two schemes based on an intelligent field side and an intelligent vehicle side, wherein the former scheme requires that infrastructure such as a sensor, a central computing unit and a communication module are pre-installed in a parking lot, and a high-precision map of a parking environment is drawn in advance; although the latter does not require the installation of the sensor, the central processing unit and other infrastructure in the parking lot, the sensing and positioning of the parking lot environment are carried out through the vehicle-mounted sensor of the vehicle, the parking environment high-precision map drawn in advance and the vehicle end calculating unit, and the sensing and positioning have the following limitations: firstly, the failure rate of learning of the local map of the parking lot generated after learning is high, a lot of typical semantic information such as a library position number, an arrow, a lane line and the like is needed, positioning is not accurate along with the lapse of time, re-learning is needed, and the time for generating the map after learning is long; secondly, the generated global high-precision map is collected in advance, so that great manpower, material resources and financial resources are consumed, a collection vehicle with collection equipment is needed for each parking lot or a person carrying the collection equipment runs out of a complete parking lot to generate the map, therefore, if the people need to get through all the parking lots in all cities across the country, the use is unrealistic, and a long time is needed, so that the use is very limited, and only the parking lot on test can use the function; finally, the foundation construction of the parking lot needs to consume capital and is transformed in cooperation with the field section, the work needs to be completed and is popularized with great effort, and many years of time are needed, so that the function is limited to be used, and the function can be used only in a trial parking lot.
Accordingly, there is a need in the art for improvements that overcome the above-mentioned limitations and thereby facilitate the rapid deployment and development of remote valet parking.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a remote passenger-assisted parking method and system, and solve the problem of many limitations caused by drawing a high-precision map of a parking environment for remote passenger-assisted parking.
In order to solve the technical problems, the invention adopts the following technical scheme:
a remote passenger-riding parking method specifically comprises the following steps:
s1: a user issues a parking starting instruction on a parking APP module, the instruction request is sent to a data management module through a cloud platform, the data management module continues to send the instruction request to a state management module, and the state management module receives the instruction request and sets the state to be activated from a standby state;
s2: the behavior decision module carries out function decision and outputs a mode selection state after receiving that the system state output by the state management module is activated, if the decision result is parking, a parking function mode is output, the behavior decision module plans a parking space, calculates the position and the posture of the vehicle which is finally stopped, and S3 is executed; if the decision result is driving, outputting a driving function mode until the decision result is parking;
s3: after receiving the parking function mode output by the behavior decision module, the motion planning module decides to enter a parking planning mode and outputs the parking planning mode to the transverse and longitudinal control module, and meanwhile, parking path parameter calculation is carried out according to the position and the posture in the step S2;
s4: and the transverse and longitudinal control module receives the parking planning mode output by the motion planning module to decide the control mode as parking control, determines control tracking under the track according to the parking path parameters in the step S3, and outputs the current action enable of the vehicle execution mechanism as brake enable to finish parking.
Further perfecting the technical scheme, the method also comprises a step S0 before the step S1,
s0: the sensing module acquires information and outputs the information to the sensing fusion module and the state management module, and the sensing fusion module receives the information from the sensing module, performs fusion processing and outputs the fused information; and meanwhile, the state management module carries out filtering processing and logic judgment on the information output by the sensing module, and finally, the state management module integrates the information processed by the Input module, the sensing module and the self module to judge whether the current state is in a system design operation range, and if the current state is in the system design operation range, the state management module sets the state as standby and waits for a user to send a parking instruction at the parking APP module.
Further, in the step S0:
the information output by the sensing module comprises lane lines, guardrails, road edge coefficients and attribute information, and also comprises ambient temperature, rainfall, illumination, visibility, target attribute information, all original point cloud information, FreeStace information, parking space information and state information of each sensor in the sensing module;
the perception fusion module carries out fusion processing on information from the perception module, wherein the fusion processing comprises preprocessing and fusion of lane lines, road edges and guardrails, and also comprises preprocessing of targets, clock synchronization, target association, associated target fusion, target rationality detection, target selection and FreeScae fusion; the information output by the perception fusion module comprises lane lines, guardrails, road edge coefficients and attribute information after fusion, and also comprises target attribute information, point cloud information, FreeStace information and parking space state;
the state management module carries out filtering processing and logic judgment on the ambient temperature, rainfall, illuminance and visibility output by the sensing module, divides the rainfall into a large grade, a medium grade and a small grade, divides the visibility into a high grade and a low grade, and divides the illumination into a strong grade, a normal grade and a weak grade; the state management module simultaneously carries out filtering processing and logical judgment on the state of a vehicle door, the opening degree of an accelerator, a brake switch, a steering wheel corner and the torque of a steering hand, and divides the operation of a driver into three states of overtaking, taking over and non-operation;
and finally, the state management module integrates the rainfall level, the visibility level, the illumination level, the driver operation, the vehicle information Input by the Input module and the state information of each sensor output by the sensing module to judge whether the vehicle information is in the system design operation range currently.
Further, in step S2, when the behavior decision module makes a functional decision:
when the parking space state output by the perception fusion module is sometimes and the parking space information is an effective parking space, the behavior decision module makes a parking function decision and outputs a parking function mode;
when the parking space state output by the perception fusion module is absent, the behavior decision module makes a driving function decision and outputs a driving function mode; when the parking space is in the driving function mode, if the parking space state output by the perception fusion module is changed from non-existence to sometimes and the parking space information is an effective parking space, the behavior decision module makes a decision to be changed from a driving function decision to a parking function decision.
Further, when the vehicle is in a driving function mode, the behavior decision module predicts an expected driving track of a target according to the target vehicle attribute, lane line information and FreeScae information output by the perception fusion module, then judges whether a vehicle exists in the region of interest, whether the vehicle has an approaching trend and whether the vehicle presses a line, and screens out a scene danger level decision target, a following target and a static target;
meanwhile, the behavior decision module takes FreeStace information output by the perception fusion module as an original path and is subjected to gridding, the target expected driving track and the static target are mapped to a FreeStace grid obtained through gridding, and a trip vehicle space is planned.
Further, when the motion planning module receives a driving function mode output by the behavior decision module, the motion planning module enters a driving planning mode, and scene decision and path planning are performed according to a driving space output by the behavior decision module and target attribute information output by the perception fusion module, wherein the path planning comprises current lane keeping path planning, escape path planning, obstacle detouring path planning and following path planning; the motion planning module makes a path selection decision and outputs a final path parameter;
the motion planning module calculates the target acceleration of the vehicle during cruising according to the vehicle following target and the target attribute output by the behavior decision module, the vehicle speed signal output by the Input module and the vehicle ramp acceleration signal, and performs acceleration planning according to the scene danger level decision target output by the behavior decision module to complete target acceleration planning, control and output.
Furthermore, the transverse and longitudinal control module decides a control mode as driving control according to the driving planning mode output by the motion planning module, realizes control tracking under a determined track according to the final path parameter output by the motion planning module, and outputs the current action enable of the vehicle executing mechanism to switch between brake enable and torque enable.
Furthermore, when the system state output by the state management module is activated, the safety supervision module, the diagnosis module, the data recording module and the functional state decision module all start to work;
the safety supervision module checks all information output by the perception fusion module, all information output by the behavior decision module, the track planned by the motion planning module and the control mode decided by the transverse and longitudinal control modules, checks all calculated values for correctness and safety, judges the correctness of the opportunity at the same time, and outputs a control instruction to the execution mechanism if the judgment result passes; if the judgment result is wrong, controlling according to the value calculated by the safety monitoring module;
the diagnosis module carries out state diagnosis and records fault information;
the data recording module records all relevant data for accident judgment and function upgrade;
the functional state decision module controls light and windscreen wipers according to the rainfall level, the visibility level and the illumination level output by the state management module, and simultaneously displays the working state according to the state output by the state management module;
the data management module uploads videos output by the perception fusion module and states output by the state management module to the cloud platform, and the cloud platform transmits information from the data management module to the parking APP module for information display in the parking process
The invention also relates to a remote valet parking system, comprising:
the sensing module is used for identifying lane lines, road edges, guardrails, target obstacles, parking spaces, traffic identification signs, characters, numbers, external weather environment and vehicle information;
the perception fusion module is used for fusing lane lines, fusion targets and fusion FreeScace;
the state management module is used for state preprocessing and state machine management and managing the state transfer of the remote passenger-replacing parking function;
the functional state decision module is used for vehicle body control and HMI display alarm decision;
the behavior decision module is used for planning a travelable area, predicting an expected target traveling track, selecting a car following target, identifying a potential risk target, planning a driving space, planning a parking space and calculating a parking expected pose;
the motion planning module is used for planning a driving path, a parking path and longitudinal planning;
the transverse and longitudinal control module is used for transverse and longitudinal control of parking and driving;
the data management module is used for realizing video cloud-on, APP control and feedback, OTA and vehicle information cloud-on functions;
the safety monitoring module is used for functional safety, check monitoring and control arbitration;
the parking APP module is used for parking mobile phone operation, information display and feedback;
the diagnosis module is used for diagnosing E2E information, monitoring the state of each module and recording fault codes;
the data recording module is used for recording data in various abnormal states;
the Input module is used for inputting vehicle information;
and the cloud platform is used for the parking APP of the mobile terminal to carry out information transmission with the system.
Further, the states of the remote valet parking function include off, standby, active, and fail.
Compared with the prior art, the invention has the following beneficial effects:
the remote agent parking method solves the problems of remote agent parking scenes and limited use, can ensure that the remote agent parking can be really used in any parking lot, does not need to consume a large amount of manpower, financial resources and material resources, does not need to use the function after infrastructure and map acquisition coverage are complete after a plurality of years, and can be used as long as a vehicle is provided with the remote agent parking system. The invention really solves the pain of the user, meets the real requirements of the user and promotes the rapid application and development of remote valet parking.
Drawings
Fig. 1 is an architecture diagram of a remote valet parking system according to an embodiment.
Detailed Description
The following describes embodiments of the present invention in further detail with reference to the accompanying drawings.
The remote passenger-replacing parking method specifically comprises the following steps:
s1: a user issues a parking starting instruction on a parking APP module, the instruction request is sent to a data management module through a cloud platform, the data management module continues to send the instruction request to a state management module, and the state management module receives the instruction request and sets the state to be activated from a standby state;
s2: the behavior decision module carries out function decision and outputs a mode selection state after receiving that the system state output by the state management module is activated, if the decision result is parking, a parking function mode is output, the behavior decision module plans a parking space, calculates the position and the posture of the vehicle which finally stops, and executes S3; if the decision result is driving, outputting a driving function mode until the decision result is parking;
s3: after receiving the parking function mode output by the behavior decision module, the motion planning module decides to enter a parking planning mode and outputs the parking planning mode to the transverse and longitudinal control module, and meanwhile, parking path parameter calculation is carried out according to the position and the posture in the step S2;
s4: and the transverse and longitudinal control module receives the parking planning mode output by the motion planning module to decide the control mode as parking control, determines control tracking under the track according to the parking path parameters in the step S3, and outputs the current action enable of the vehicle execution mechanism as brake enable to finish parking.
The remote agent parking method solves the problems of remote agent parking scenes and limited use, can enable the remote agent parking to be really used in any parking lot, does not need to consume a large amount of manpower, financial resources and material resources, does not need to use the function after infrastructure and map acquisition coverage are complete after a plurality of years, and can be used as long as a vehicle is provided with the remote agent parking system. The invention really solves the pain of the user, meets the real requirements of the user and promotes the rapid application and development of remote valet parking.
In the remote valet parking method according to the embodiment, step S1 is preceded by:
s0: the sensing module acquires information and outputs the information to the sensing fusion module and the state management module, and the sensing fusion module receives the information from the sensing module, performs fusion processing and outputs the fused information; and meanwhile, the state management module carries out filtering processing and logic judgment on the information output by the sensing module, and finally, the state management module integrates the information processed by the Input module, the sensing module and the self module to judge whether the current state is in a system design operation range, and if the current state is in the system design operation range, the state management module sets the state as standby and waits for a user to send a parking instruction at the parking APP module.
When the method is implemented, the perception module, the perception fusion module and the state management module are used for judging whether the vehicle is in the system design operation range in advance, and the related work of information acquisition, information fusion processing, state preprocessing and the like is not required to be carried out until a parking instruction is issued by a user, so that the experience of the user is improved.
Wherein, in the step S0:
the information output by the sensing module comprises lane lines, guardrails, road edge coefficients and attribute information, and also comprises ambient temperature, rainfall, illumination, visibility, target attribute information, all original point cloud information, FreeStace information, parking space information and state information of each sensor in the sensing module;
the perception fusion module carries out fusion processing on information from the perception module, wherein the fusion processing comprises preprocessing and fusion of lane lines, road edges and guardrails, and also comprises preprocessing of targets, clock synchronization, target association, associated target fusion, target rationality detection, target selection and FreeScae fusion; the information output by the perception fusion module comprises lane lines, guardrails, road edge coefficients and attribute information after fusion, and also comprises target attribute information, point cloud information, FreeStace information and parking space state;
the state management module carries out filtering processing and logic judgment on the ambient temperature, rainfall, illuminance and visibility output by the sensing module, divides the rainfall into a large grade, a medium grade and a small grade, divides the visibility into a high grade and a low grade, and divides the illumination into a strong grade, a normal grade and a weak grade; the state management module simultaneously carries out filtering processing and logical judgment on the state of a vehicle door, the opening degree of an accelerator, a brake switch, a steering wheel corner and the torque of a steering hand, and divides the operation of a driver into three states of overtaking, taking over and non-operation;
and finally, the state management module integrates the rainfall level, the visibility level, the illumination level, the driver operation, the vehicle information Input by the Input module and the state information of each sensor output by the sensing module to judge whether the system is in the design operation range at present.
During implementation, if the system is in a system design operation range, the state management module sets the state as standby and waits for a user to send a parking instruction in the parking APP module; if the system is not in the system design operation range, the state management module sets the state to be closed, and the whole system exits.
In step S2, when the behavior decision module makes a functional decision:
when the parking space state output by the perception fusion module is sometimes and the parking space information is an effective parking space, the behavior decision module makes a parking function decision and outputs a parking function mode;
when the parking space state output by the perception fusion module is absent, the behavior decision module makes a driving function decision and outputs a driving function mode; when the parking space is in the driving function mode, if the parking space state output by the perception fusion module is changed from non-existence to sometimes and the parking space information is an effective parking space, the behavior decision module makes a decision to be changed from a driving function decision to a parking function decision.
In implementation, because driving and parking are dynamic processes, the conversion between the driving and the parking is set as a dynamic process, namely, the system searches for a parking available area as a dynamic process, and if the sensing fusion module outputs a result that a parking space state exists, other modules in the system directly finish parking according to a parking function mode output by the behavior decision module; if the current situation can not be parked, the behavior decision module makes a driving function decision and outputs a driving function mode, and similarly, other modules in the system help the vehicle to finish driving according to the driving function mode output by the behavior decision module; in the driving process, once the parking space state output by the perception fusion module is changed from absent to present, the behavior decision module can correspondingly change the function decision from driving to parking.
Wherein, when the bicycle is in the running function mode,
the behavior decision module predicts a target expected driving track according to the target vehicle attribute, lane line information and FreeScace information output by the perception fusion module, then judges whether vehicles exist in the region of interest, whether the vehicles approach or not and whether the vehicles press lines or not, and screens out a scene danger level decision target, a following target and a static target;
meanwhile, the behavior decision module takes FreeStace information output by the perception fusion module as an original path and is subjected to gridding, the target expected driving track and the static target are mapped to a FreeStace grid obtained through gridding, and a trip vehicle space is planned.
When the motion planning module receives a driving function mode output by the behavior decision module, the motion planning module enters a driving planning mode, and scene decision and path planning are carried out according to a driving space output by the behavior decision module and target attribute information output by the perception fusion module, wherein the path planning comprises current lane keeping path planning, escape path planning, obstacle detouring path planning and following path planning; the motion planning module makes a path selection decision and outputs a final path parameter;
the motion planning module calculates the target acceleration of the vehicle during cruising according to the vehicle following target and the target attribute output by the behavior decision module, the vehicle speed signal output by the Input module and the vehicle ramp acceleration signal, and performs acceleration planning according to the scene danger level decision target output by the behavior decision module to complete target acceleration planning, control and output.
In implementation, it should be noted here that when the lighting system is not in the driving function mode, the behavior decision module needs to determine whether there is a vehicle in the region of interest, whether there is a approaching trend of the vehicle, whether the vehicle is pressed, and screen out a scene risk level decision target, a vehicle following target, and a static target.
When the motion planning module calculates the parking path parameters in step S3, scene decision and path planning are also required to be performed on the parking space; assuming that there is an obstacle in front of the vehicle during parking, the motion planning module outputs an obstacle detouring path plan and continues parking, and it is understood that the parking path in step S3 includes the obstacle detouring path that may need to be used during parking.
The transverse and longitudinal control module decides a control mode as driving control according to a driving planning mode output by the motion planning module, realizes control tracking under a determined track according to a final path parameter output by the motion planning module, and outputs the current action enable of the vehicle execution mechanism to switch between brake enable and torque enable.
When the system state output by the state management module is activated, the safety supervision module, the diagnosis module, the data recording module and the functional state decision module all start to work;
the safety supervision module checks all information output by the perception fusion module, all information output by the behavior decision module, the track planned by the motion planning module and the control mode decided by the transverse and longitudinal control modules, checks all calculated values for correctness and safety, judges the correctness of the opportunity at the same time, and outputs a control instruction to the execution mechanism if the judgment result passes; if the judgment result is wrong, controlling according to the value calculated by the safety monitoring module;
the diagnosis module carries out state diagnosis and records fault information;
the data recording module records all relevant data for accident judgment and function upgrading;
the functional state decision module controls light and windscreen wipers according to the rainfall level, the visibility level and the illumination level output by the state management module, and simultaneously displays the working state according to the state output by the state management module;
the data management module uploads the video output by the perception fusion module and the state output by the state management module to the cloud platform, and the cloud platform transmits the information from the data management module to the parking APP module to display the information in the parking process.
In practice, when the safety supervision module checks and monitors, the safety supervision module judges the correctness of the time, the meaning of the time specifically indicates whether the time for sending the instruction is reasonable, for example, when a driving mode is adopted, an obstacle appears in front, the motion planning module can calculate the deceleration required by braking according to the distance, the speed and the acceleration of the current obstacle, and the distance, the speed or the deceleration to which degree is required by braking or the deceleration is required at which moment, the deceleration is sent to avoid collision. The safety supervision module also has a set of algorithm to calculate the values, if the time for sending out the deceleration is too late, the vehicle may be braked for a short time and a short distance, and the collision can be caused; in short, the timing is suitable for the command timing of deceleration, steering angle and torque sent by the system, and the command timing cannot be too early or too late.
Referring to fig. 1, a remote valet parking system according to an embodiment includes:
the sensing module is used for identifying lane lines, road edges, guardrails, target obstacles, parking spaces, traffic identification signs, characters, numbers, external weather environment and vehicle information;
the perception fusion module is used for fusing lane lines, fusion targets and fusion FreeScace;
the state management module is used for state preprocessing and state machine management and managing the state transfer of the remote passenger-replacing parking function;
the functional state decision module is used for vehicle body control and HMI display alarm decision;
the behavior decision module is used for planning a travelable area, predicting an expected target traveling track, selecting a car following target, identifying a potential risk target, planning a driving space, planning a parking space and calculating a parking expected pose; the planning of the travelable area refers to that FreeStace information output by the perception fusion module is used as an original path and is subjected to grid integration, the expected target traveling track and a static target are mapped to a FreeStace grid obtained through grid integration, and a real traveling space is planned;
the motion planning module is used for planning a driving path, a parking path and longitudinal planning;
the transverse and longitudinal control module is used for transverse and longitudinal control of parking and driving;
the data management module is used for realizing video cloud-on, APP control and feedback, OTA and vehicle information cloud-on functions;
the safety monitoring module is used for functional safety, check monitoring and control arbitration;
the parking APP module is used for parking mobile phone operation, information display and feedback;
the diagnosis module is used for diagnosing E2E information, monitoring the state of each module and recording fault codes;
the data recording module is used for recording data in various abnormal states;
the Input module is used for inputting vehicle information;
and the cloud platform is used for the parking APP of the mobile terminal to carry out information transmission with the system.
The states of the remote agent parking function comprise closing, standby, activation and failure.
Finally, the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all of them should be covered in the claims of the present invention.
Claims (10)
1. A remote passenger-riding parking method is characterized in that: the method specifically comprises the following steps:
s1: a user issues a parking starting instruction on a parking APP module, the instruction request is sent to a data management module through a cloud platform, the data management module continues to send the instruction request to a state management module, and the state management module receives the instruction request and sets the state to be activated from a standby state;
s2: the behavior decision module carries out function decision and outputs a mode selection state after receiving that the system state output by the state management module is activated, if the decision result is parking, a parking function mode is output, the behavior decision module plans a parking space, calculates the position and the posture of the vehicle which finally stops, and executes S3; if the decision result is driving, outputting a driving function mode until the decision result is parking;
s3: after receiving the parking function mode output by the behavior decision module, the motion planning module decides to enter a parking planning mode and outputs the parking planning mode to the transverse and longitudinal control module, and meanwhile, parking path parameter calculation is carried out according to the position and the posture in the step S2;
s4: and the transverse and longitudinal control module receives the parking planning mode output by the motion planning module to decide the control mode as parking control, determines control tracking under the track according to the parking path parameters in the step S3, and outputs the current action enable of the vehicle execution mechanism as brake enable to finish parking.
2. The remote valet parking method according to claim 1, wherein: step S1 is preceded by step S0,
s0: the sensing module acquires information and outputs the information to the sensing fusion module and the state management module, and the sensing fusion module receives the information from the sensing module, performs fusion processing and outputs the fused information; and meanwhile, the state management module carries out filtering processing and logic judgment on the information output by the sensing module, and finally, the state management module integrates the information processed by the Input module, the sensing module and the self module to judge whether the current state is in a system design operation range, and if the current state is in the system design operation range, the state management module sets the state as standby and waits for a user to send a parking instruction at the parking APP module.
3. The remote valet parking method according to claim 2, wherein: in step S0:
the information output by the sensing module comprises lane lines, guardrails, road edge coefficients and attribute information, and also comprises ambient temperature, rainfall, illumination, visibility, target attribute information, all original point cloud information, FreeStpace information, parking space information and state information of each sensor in the sensing module;
the perception fusion module carries out fusion processing on information from the perception module, wherein the fusion processing comprises preprocessing and fusion of lane lines, road edges and guardrails, and also comprises preprocessing of targets, clock synchronization, target association, associated target fusion, target rationality detection, target selection and FreeScae fusion; the information output by the perception fusion module comprises lane lines, guardrails, road edge coefficients and attribute information after fusion, and also comprises target attribute information, point cloud information, FreeStace information and parking space state;
the state management module carries out filtering processing and logic judgment on the ambient temperature, rainfall, illuminance and visibility output by the sensing module, divides the rainfall into a large grade, a medium grade and a small grade, divides the visibility into a high grade and a low grade, and divides the illumination into a strong grade, a normal grade and a weak grade; the state management module simultaneously carries out filtering processing and logic judgment on the state of the vehicle door, the opening degree of an accelerator, a brake switch, a steering wheel corner and the torque of a steering hand, and divides the operation of a driver into three states of overtaking, taking over and non-operation;
and finally, the state management module integrates the rainfall level, the visibility level, the illumination level, the driver operation, the vehicle information Input by the Input module and the state information of each sensor output by the sensing module to judge whether the vehicle information is in the system design operation range currently.
4. The remote valet parking method according to claim 1, wherein: in step S2, when the behavior decision module makes a functional decision:
when the parking space state output by the perception fusion module is sometimes and the parking space information is an effective parking space, the behavior decision module makes a parking function decision and outputs a parking function mode;
when the parking space state output by the perception fusion module is absent, the behavior decision module makes a driving function decision and outputs a driving function mode; when the parking space is in the driving function mode, if the parking space state output by the perception fusion module is changed from non-existence to sometimes and the parking space information is an effective parking space, the behavior decision module makes a decision to be changed from a driving function decision to a parking function decision.
5. The remote valet parking method according to claim 4, wherein: when the vehicle is in the running function mode,
the behavior decision module predicts a target expected driving track according to the target vehicle attribute, lane line information and FreeScace information output by the perception fusion module, then judges whether vehicles exist in the region of interest, whether the vehicles approach or not and whether the vehicles press lines or not, and screens out a scene danger level decision target, a following target and a static target;
meanwhile, the behavior decision module takes FreeStace information output by the perception fusion module as an original path and is subjected to gridding, the target expected driving track and the static target are mapped to a FreeStace grid obtained through gridding, and a trip vehicle space is planned.
6. The remote valet parking method according to claim 5, wherein:
when the motion planning module receives a driving function mode output by the behavior decision module, entering a driving planning mode, and performing scene decision and path planning according to a driving space output by the behavior decision module and target attribute information output by the perception fusion module, wherein the path planning comprises current lane keeping path planning, escape path planning, obstacle detouring path planning and following path planning; the motion planning module makes a path selection decision and outputs a final path parameter;
the motion planning module calculates the target acceleration of the vehicle during cruising according to the vehicle following target and the target attribute output by the behavior decision module, the vehicle speed signal output by the Input module and the vehicle ramp acceleration signal, and carries out acceleration planning according to the scene danger level decision target output by the behavior decision module to complete the target acceleration planning, control and output.
7. The remote valet parking method according to claim 6, wherein: the transverse and longitudinal control module decides a control mode as driving control according to the driving planning mode output by the motion planning module, realizes control tracking under a determined track according to the final path parameter output by the motion planning module, and outputs the current action enable of the vehicle executing mechanism to switch between brake enable and torque enable.
8. A remote valet parking method according to any one of claims 1 to 7, wherein: when the system state output by the state management module is activated, the safety supervision module, the diagnosis module, the data recording module and the functional state decision module all start to work;
the safety supervision module checks all information output by the perception fusion module, all information output by the behavior decision module, the track planned by the motion planning module and the control mode decided by the transverse and longitudinal control modules, checks all calculated values for correctness and safety, judges the correctness of the opportunity at the same time, and outputs a control instruction to the execution mechanism if the judgment result passes; if the judgment result is wrong, controlling according to the value calculated by the safety monitoring module;
the diagnosis module carries out state diagnosis and records fault information;
the data recording module records all relevant data for accident judgment and function upgrade;
the functional state decision module controls light and a wiper according to the rainfall level, the visibility level and the illumination level output by the state management module, and displays the working state according to the state output by the state management module;
the data management module uploads the video output by the perception fusion module and the state output by the state management module to the cloud platform, and the cloud platform transmits the information from the data management module to the parking APP module to display the information in the parking process.
9. A long-distance passenger-replacing parking system is characterized in that: the method comprises the following steps:
the sensing module is used for identifying lane lines, road edges, guardrails, target obstacles, parking spaces, traffic identification signs, characters, numbers, external weather environment and vehicle information;
the perception fusion module is used for fusing lane lines, fusion targets and fusion FreeScace;
the state management module is used for state preprocessing and state machine management and managing the state transfer of the remote passenger-replacing parking function;
the functional state decision module is used for vehicle body control and HMI display alarm decision;
the behavior decision module is used for planning a travelable area, predicting an expected target traveling track, selecting a car following target, identifying a potential risk target, planning a driving space, planning a parking space and calculating a parking expected pose;
the motion planning module is used for planning a driving path, a parking path and longitudinal planning;
the transverse and longitudinal control module is used for transverse and longitudinal control of parking and driving;
the data management module is used for realizing video cloud-on, APP control and feedback, OTA and vehicle information cloud-on functions;
the safety monitoring module is used for functional safety, check monitoring and control arbitration;
the parking APP module is used for parking mobile phone operation, information display and feedback;
the diagnosis module is used for diagnosing E2E information, monitoring the state of each module and recording fault codes;
the data recording module is used for recording data in various abnormal states;
the Input module is used for inputting vehicle information;
and the cloud platform is used for the parking APP of the mobile terminal to carry out information transmission with the system.
10. The remote valet parking system of claim 9, wherein: the states of the remote valet parking function include off, standby, active, and fault.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210296147.4A CN114690750B (en) | 2022-03-24 | 2022-03-24 | Remote bus-substituting parking method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210296147.4A CN114690750B (en) | 2022-03-24 | 2022-03-24 | Remote bus-substituting parking method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114690750A true CN114690750A (en) | 2022-07-01 |
| CN114690750B CN114690750B (en) | 2024-09-17 |
Family
ID=82139181
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210296147.4A Active CN114690750B (en) | 2022-03-24 | 2022-03-24 | Remote bus-substituting parking method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114690750B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9811085B1 (en) * | 2016-08-18 | 2017-11-07 | Allstate Insurance Company | Generating and transmitting parking instructions for autonomous and non-autonomous vehicles |
| CN109910872A (en) * | 2019-03-18 | 2019-06-21 | 中国汽车工程研究院股份有限公司 | A parking scene extraction system and method based on natural driving data |
| CN110599793A (en) * | 2019-08-16 | 2019-12-20 | 深圳市智绘科技有限公司 | Intelligent internet-oriented autonomous parking system and method for vehicle |
| CN111063214A (en) * | 2019-12-16 | 2020-04-24 | 驭势科技（北京）有限公司 | Vehicle positioning method, vehicle-mounted equipment and storage medium |
| CN111415523A (en) * | 2020-03-06 | 2020-07-14 | 北京智行者科技有限公司 | Autonomous passenger-riding-substituting parking method and system |
| WO2021036862A1 (en) * | 2019-08-30 | 2021-03-04 | 华为技术有限公司 | Vehicle control method, related device, and computer storage medium |
| EP3971863A1 (en) * | 2020-09-17 | 2022-03-23 | Ningbo Geely Automobile Research & Development Co. Ltd. | A method for operating a vehicle hazardous parking warning system |
-
2022
- 2022-03-24 CN CN202210296147.4A patent/CN114690750B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9811085B1 (en) * | 2016-08-18 | 2017-11-07 | Allstate Insurance Company | Generating and transmitting parking instructions for autonomous and non-autonomous vehicles |
| CN109910872A (en) * | 2019-03-18 | 2019-06-21 | 中国汽车工程研究院股份有限公司 | A parking scene extraction system and method based on natural driving data |
| CN110599793A (en) * | 2019-08-16 | 2019-12-20 | 深圳市智绘科技有限公司 | Intelligent internet-oriented autonomous parking system and method for vehicle |
| WO2021036862A1 (en) * | 2019-08-30 | 2021-03-04 | 华为技术有限公司 | Vehicle control method, related device, and computer storage medium |
| CN111063214A (en) * | 2019-12-16 | 2020-04-24 | 驭势科技（北京）有限公司 | Vehicle positioning method, vehicle-mounted equipment and storage medium |
| CN111415523A (en) * | 2020-03-06 | 2020-07-14 | 北京智行者科技有限公司 | Autonomous passenger-riding-substituting parking method and system |
| EP3971863A1 (en) * | 2020-09-17 | 2022-03-23 | Ningbo Geely Automobile Research & Development Co. Ltd. | A method for operating a vehicle hazardous parking warning system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114690750B (en) | 2024-09-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111540237B (en) | Method for automatically generating vehicle safety driving guarantee scheme based on multi-data fusion | |
| CN111240328B (en) | Vehicle driving safety monitoring method and device and unmanned vehicle | |
| US11842638B2 (en) | Parallel remote control driving system for intelligent network vehicle | |
| CN111524362B (en) | Vehicle safety driving guarantee system and method based on multi-data fusion | |
| CN109532719B (en) | Electric automobile based on multisensor information fusion | |
| CN113022540B (en) | Real-time remote driving system and method for monitoring multiple vehicle states | |
| CN107458243A (en) | A kind of scram control method driven for new-energy automobile Intelligent unattended | |
| US11662735B2 (en) | Method and system for updating a control model for automatic control of at least one mobile unit | |
| CN108445885A (en) | A kind of automated driving system and its control method based on pure electric vehicle logistic car | |
| CN108710368B (en) | Unmanned driving system and electric automobile | |
| CN108769950A (en) | The car networking information system of connection automobile is netted towards V2X | |
| US11496707B1 (en) | Fleet dashcam system for event-based scenario generation | |
| CN113844465B (en) | Automatic driving method and system | |
| CN111882924A (en) | Vehicle testing system, driving behavior judgment control method and accident early warning method | |
| CN109491380A (en) | A kind of intelligent automobile Unmanned Systems and application method | |
| CN112829762A (en) | A method for generating vehicle speed and related equipment | |
| CN117022146B (en) | Dual-domain electronic and electrical architecture of a passenger vehicle, working method and passenger vehicle | |
| CN114822048A (en) | Cloud planning service system and method for Internet vehicles | |
| CN114489004A (en) | Unmanned driving test method and system | |
| CN110083099B (en) | An autonomous driving architecture system and working method compliant with automotive functional safety standards | |
| CN116901875A (en) | Perception fusion system, vehicle and control method | |
| CN118538055A (en) | Intelligent obstacle avoidance system of intelligent network-connected automobile | |
| Pechinger et al. | Benefit of smart infrastructure on urban automated driving-using an av testing framework | |
| US20230147357A1 (en) | Vehicle control system, apparatus, and method | |
| JP6796679B2 (en) | Vehicle control system and method, and driving support server |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |