WO2023005223A1 - 轨迹规划方法、装置、存储介质、设备及计算机程序产品 - Google Patents

轨迹规划方法、装置、存储介质、设备及计算机程序产品 Download PDF

Info

Publication number
WO2023005223A1
WO2023005223A1 PCT/CN2022/081449 CN2022081449W WO2023005223A1 WO 2023005223 A1 WO2023005223 A1 WO 2023005223A1 CN 2022081449 W CN2022081449 W CN 2022081449W WO 2023005223 A1 WO2023005223 A1 WO 2023005223A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
target
longitudinal displacement
obstacle
trajectory
Prior art date
Application number
PCT/CN2022/081449
Other languages
English (en)
French (fr)
Inventor
邢学韬
任冬淳
王志超
白钰
夏华夏
Original Assignee
北京三快在线科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 北京三快在线科技有限公司 filed Critical 北京三快在线科技有限公司
Publication of WO2023005223A1 publication Critical patent/WO2023005223A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0011—Planning or execution of driving tasks involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles

Definitions

  • the embodiments of the present application relate to the technical field of automatic driving, and in particular to a trajectory planning method, device, storage medium, electronic equipment, and computer program product.
  • autonomous driving technology mainly includes three components: perception module, planning module and control module.
  • the perception module is used to perceive the vehicle and the surrounding environment information of the vehicle;
  • the planning module is used to optimize the designed weights according to the conditions of the vehicle, the surrounding environment information and the constraints of the vehicle, obstacle interference, comfort and track length. function to generate a safe, comfortable and drivable locally optimal trajectory from the current state to the desired state, which is input into the control module as a reference signal; and the control module is used to control the The vehicle is moving.
  • the decoupling method of path planning and speed planning is adopted, that is, the path and speed are planned through independent algorithms.
  • This method cannot consider the compound constraints of path and speed, and due to obstacles such as other vehicles
  • the motion state of the vehicle may change at any time, and it does not support real-time response to dynamic obstacles, resulting in the planned trajectory becoming unreasonable, unable to effectively adapt to the changing actual driving environment, and the trajectory planning efficiency is low.
  • Embodiments of the present application provide a trajectory planning method, device, storage medium, electronic equipment, and computer program product, so as to partially solve the above-mentioned problems existing in related technologies.
  • the first aspect of the embodiment of the present application provides a trajectory planning method, which is applied to an automatic driving vehicle, and the method includes:
  • a preliminary planned driving area of the vehicle is obtained, and the preliminary planned driving area includes at least one lateral width interval;
  • a target planning trajectory of the vehicle within a time period formed by the plurality of future moments is obtained.
  • determining the drivable trajectory interval of the vehicle at each of the future moments according to the preliminary planned driving area, position information of each dynamic obstacle at multiple future moments, and obstacle avoidance decisions include:
  • the obstacle avoidance decision includes detour to the left and right of the obstacle, and according to the position information and the obstacle avoidance decision of each of the dynamic obstacles at a plurality of the future moments, the The preliminary planned driving area is corrected to obtain the revised planned driving area of the vehicle at each of the future moments, including:
  • each of the dynamic obstacles as a target obstacle one by one, taking a plurality of the future times as a target time one by one, and calculating the position occupied by the target obstacle according to the position information of the target obstacle at the target time
  • the area of the target obstacle extends laterally to the boundary of the corresponding lateral width interval in the direction opposite to the detour direction indicated by the obstacle avoidance decision of the target obstacle, to obtain the target obstacle area;
  • the target obstacle area is removed from the preliminary planned driving area to obtain a revised planned driving area of the vehicle at the target moment.
  • the determining the drivable trajectory interval of the vehicle at each of the future moments according to the revised planned driving area and the estimated longitudinal displacement includes:
  • the blocking position is not included, then based on the functional relationship between the longitudinal displacement and the lateral displacement of the vehicle, determine the lateral displacement interval of the vehicle corresponding to the estimated longitudinal displacement at the target moment, and obtain the The drivable trajectory interval of the vehicle at the target moment.
  • the determining the drivable trajectory interval of the vehicle at each of the future moments according to the revised planned driving area and the estimated longitudinal displacement further includes:
  • the target longitudinal displacement based on the functional relationship, determine the lateral displacement interval of the vehicle corresponding to the estimated longitudinal displacement at the target moment, and obtain the drivable trajectory of the vehicle at the target moment interval.
  • the determining the target longitudinal displacement of the vehicle matching the passing decision at the target moment according to the estimated longitudinal displacement, the passing decision and the longitudinal displacement threshold includes:
  • the estimated longitudinal displacement is stretched to obtain a displacement greater than or equal to the longitudinal displacement threshold, and this displacement is used as the distance between the vehicle at the target moment and the Longitudinal displacement of the target for antecedent decision matching.
  • the determining the target longitudinal displacement of the vehicle matching the passing decision at the target moment according to the estimated longitudinal displacement, the passing decision and the longitudinal displacement threshold further includes:
  • the passing decision is a yielding decision
  • compress the estimated longitudinal displacement to obtain a displacement less than or equal to the longitudinal displacement threshold, and use this displacement as the distance between the vehicle at the target moment and the Target longitudinal displacement for yield decision matching.
  • the obtaining the target planning trajectory of the vehicle within the period formed by the plurality of future moments according to the drivable trajectory interval includes:
  • Continuity constraints are performed on the drivable trajectory intervals according to the sequence of the future time to obtain the target planning trajectory.
  • the second aspect of the embodiment of the present application provides a trajectory planning device, which is applied to an automatic driving vehicle, and the device includes:
  • the obtaining module is used to obtain the vehicle's current positioning information, map information and static obstacle information on the road where the vehicle is located;
  • a first determining module configured to obtain a preliminary planned driving area of the vehicle according to the positioning information, the map information and the static obstacle information, and the preliminary planned driving area includes at least one lateral width interval;
  • the second determining module is used to obtain the position information of each dynamic obstacle on the road where the vehicle is located at multiple future moments, and according to the preliminary planned driving area, the position of each dynamic obstacle at multiple future moments Information and obstacle avoidance decision-making, determining the drivable trajectory interval of the vehicle at each of the future moments;
  • the third determining module is configured to obtain, according to the drivable trajectory interval, a target planning trajectory of the vehicle within a time period formed by the plurality of future moments.
  • the second determining module determines the drivable trajectory interval of the vehicle at each future moment in the following manner:
  • the obstacle avoidance decision includes detouring to the left and detouring to the right of the obstacle, and the second determination module uses the following method to correct the preliminary planned driving area to obtain the The revised planning driving area at the said future moment:
  • each said dynamic obstacle is taken as a target obstacle one by one, and each of said multiple future moments is taken as a target moment one by one, according to said The position information of the target obstacle at the target moment, and extend the area occupied by the target obstacle to the direction opposite to the detour direction indicated by the obstacle avoidance decision of the target obstacle to the corresponding lateral width The boundary of the interval to obtain the target obstacle area;
  • the target obstacle area is removed from the preliminary planned driving area to obtain a revised planned driving area of the vehicle at the target moment.
  • the second determining module determines the drivable trajectory interval of the vehicle at each future moment in the following manner:
  • a plurality of the future times are set as target times one by one, and each lateral width interval included in the modified planned driving area of the vehicle at the target time is combined with Comparing the vehicle width of the vehicle to determine whether the corrected planned driving area of the vehicle at the target moment includes a blocking position with insufficient traffic width;
  • the blocking position is not included, then based on the functional relationship between the longitudinal displacement and the lateral displacement of the vehicle, determine the lateral displacement interval of the vehicle corresponding to the estimated longitudinal displacement at the target moment, and obtain the The drivable trajectory interval of the vehicle at the target moment.
  • the second determination module is further configured to determine the drivable trajectory interval of the vehicle at each future moment according to the revised planned driving area and the estimated longitudinal displacement in the following manner:
  • the target longitudinal displacement based on the functional relationship, determine the lateral displacement interval of the vehicle corresponding to the estimated longitudinal displacement at the target moment, and obtain the drivable trajectory of the vehicle at the target moment interval.
  • the second determining module determines the target of the vehicle matching the passing decision at the target time according to the estimated longitudinal displacement, the passing decision and the longitudinal displacement threshold in the following manner Longitudinal displacement:
  • the estimated longitudinal displacement is stretched to obtain a displacement greater than or equal to the longitudinal displacement threshold, and this displacement is used as the distance between the vehicle at the target moment and the Longitudinal displacement of the target for antecedent decision matching.
  • the second determining module is further configured to determine, according to the estimated longitudinal displacement, the passing decision and the longitudinal displacement threshold, the vehicle at the target moment and the passing decision Matched target longitudinal displacement:
  • the passing decision is a yielding decision
  • compress the estimated longitudinal displacement to obtain a displacement less than or equal to the longitudinal displacement threshold, and use this displacement as the distance between the vehicle at the target moment and the Target longitudinal displacement for yield decision matching.
  • the third determination module obtains the target planning trajectory of the vehicle within the time period formed by the plurality of future times according to the drivable trajectory interval in the following manner:
  • Continuity constraints are performed on the drivable trajectory intervals according to the sequence of the future time to obtain the target planning trajectory.
  • the third aspect of the embodiments of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps in the method described in the first aspect of the present application are implemented.
  • the fourth aspect of the embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and operable on the processor, and the processor implements the method described in the first aspect of the present application when executed A step of.
  • a fifth aspect of the embodiments of the present application provides a computer program product, including computer readable codes, which, when the computer readable codes are run on a computing processing device, cause the computing processing device to execute the trajectory planning method described above.
  • the trajectory planning method of this application After determining the preliminary planned driving area of the vehicle including at least one lateral width interval, by responding to the dynamic obstacles on the road where the vehicle is located in real time, the real-time acquisition of each dynamic obstacle on the road where the vehicle is located at multiple future moments Position information, according to the preliminary planning driving area, the position information of each dynamic obstacle at multiple future moments and the obstacle avoidance decision, determine the drivable trajectory interval of the vehicle at each future moment, thus, the trajectory planning method of this application
  • the path and speed can be optimized at one time according to the vertical and horizontal joint constraints under a unified time frame, which improves the vehicle traffic efficiency and avoidance ability.
  • Fig. 1 is a flowchart of a trajectory planning method according to an embodiment of the present application.
  • Fig. 2 is a schematic diagram of a road reference coordinate system according to an embodiment of the present application.
  • Fig. 3 is a schematic diagram showing a lateral width interval of a driving area according to an embodiment of the present application.
  • Fig. 4 is an example diagram showing a drivable trajectory interval of a vehicle at each future moment according to an embodiment of the present application.
  • Fig. 5 is a block diagram of a trajectory planning device according to an embodiment of the present application.
  • Fig. 6 is a block diagram of an electronic device according to an embodiment of the present application.
  • Fig. 1 is a flowchart of a trajectory planning method according to an embodiment of the present application. As shown in Fig. 1 , the trajectory planning method includes the following steps.
  • step S11 the current location information of the vehicle, map information and static obstacle information of the road where the vehicle is located are obtained.
  • the positioning information of the vehicle, map information and static obstacle information can be obtained through high-precision maps, and the static obstacle information can include the shape and size of the obstacle and the location information of the obstacle.
  • step S12 according to the positioning information, the map information and the static obstacle information, the preliminary planning driving area of the vehicle is obtained, and the preliminary planning driving area includes at least one transverse width interval.
  • the preliminary planned driving area may be a path area in which static obstacles are removed in the path area where the autonomous driving vehicle travels.
  • the lateral width section may be a width between boundaries of the vehicle travel path area.
  • a reference coordinate system may be determined based on the road where the vehicle is located.
  • the road reference coordinate system may be a Frenet coordinate system.
  • Fig. 2 is a schematic diagram of a road reference coordinate system according to an embodiment of the present application.
  • the road coordinate system includes a reference line (S axis), which can be smoothed according to the road centerline to generate a (group) line for vehicles to drive, and the road coordinate system also includes a line perpendicular to the reference line horizontal line (L-axis).
  • the road coordinate system also includes an origin, for example, the origin may be the starting point of the vehicle.
  • Fig. 3 is a schematic diagram showing a lateral width section L(S) of a driving area according to an embodiment of the present application.
  • the transverse width interval L(S) of the driving area is between the left boundary and the right boundary of the road as an example, the left boundary based on the longitudinal displacement can be written as L lf,sta (S), the right boundary can be recorded as L rt,sta (S), for example, that is, there is a convex function relationship between the transverse width interval L(S) and the longitudinal displacement s, and the transverse width interval L(S) and The functional relationship between longitudinal displacement S can be recorded as: L rt,sta (S) ⁇ L(S) ⁇ L lf,sta (S).
  • step S13 the location information of each dynamic obstacle on the road where the vehicle is located at multiple future moments is obtained, and according to the preliminary planning driving area, the location information of each dynamic obstacle at multiple future moments and the obstacle avoidance decision, Determine the drivable trajectory interval of the vehicle at each future moment.
  • the multiple future time points may be consecutive time points with a unit of 0.1 ms, for example.
  • Obstacle avoidance decisions include detours to the left and detours to the right.
  • the position of the preliminary planning driving area occupied by the dynamic obstacle at each moment is also different, and the preliminary planning driving area at each moment is also different.
  • the drivable area of the vehicles in the zone will also be different.
  • the planning is carried out by decoupling the path planning and the speed planning, without considering the changes caused by the real-time movement position of the dynamic obstacle to the drivable trajectory interval of the vehicle, and the planned trajectory cannot be adjusted for the dynamic obstacle.
  • the position information of each dynamic obstacle on the road where the vehicle is located at multiple future moments can be obtained.
  • the position information of each dynamic obstacle at multiple future moments and the obstacle avoidance decision Determine the drivable trajectory interval of the vehicle at each future moment.
  • the drivable trajectory interval of the vehicle at each future moment can be determined in the following manner:
  • the preliminary planned driving area is corrected to obtain the corrected planned driving area of the vehicle at each future moment.
  • the preliminary planned driving area is corrected in the following way to obtain the corrected planned driving area of the vehicle at each future moment:
  • Each dynamic obstacle is taken as the target obstacle one by one, and multiple future moments are taken as the target time one by one.
  • the area occupied by the target obstacle is directed towards the obstacle avoidance
  • the direction opposite to the detour direction indicated by the decision is extended laterally to the boundary of the corresponding lateral width interval to obtain the target obstacle area, and the target obstacle area is removed from the preliminary planned driving area to obtain the corrected planned driving area of the vehicle at the target moment.
  • the longitudinal displacement determines the drivable trajectory interval of the vehicle at each future moment.
  • the drivable trajectory interval of the vehicle at each future moment can be determined in the following way:
  • the lateral displacement interval corresponding to the estimated longitudinal displacement of the vehicle at the target time is determined, and the drivable trajectory interval of the vehicle at the target time is obtained.
  • the longitudinal displacement threshold is determined according to the blocking position, and the vehicle's passing decision at the target time is obtained. Among them, the longitudinal displacement threshold can represent the value of the longitudinal displacement that can avoid the blocking position and pass the corrected planning driving area smoothly at the target moment. If the traffic decision is the first decision, the longitudinal displacement threshold is the minimum longitudinal displacement that can avoid the blocking position and pass the corrected planning driving area smoothly. If the traffic decision is a yield decision, the longitudinal displacement threshold is the maximum longitudinal displacement that can avoid the blocking position and pass the corrected planning driving area smoothly.
  • the estimated longitudinal displacement, traffic decision and longitudinal displacement threshold determine the target longitudinal displacement of the vehicle matching the traffic decision at the target time, according to the target longitudinal displacement, based on the functional relationship between the vehicle’s longitudinal displacement and lateral displacement, determine the vehicle’s
  • the lateral displacement interval corresponding to the estimated longitudinal displacement at the target moment is used to obtain the drivable trajectory interval of the vehicle at the target moment.
  • the estimated longitudinal displacement is stretched to obtain a displacement greater than or equal to the longitudinal displacement threshold, and this displacement is used as the target longitudinal displacement of the vehicle matching the first decision at the target time. If the passing decision is a yield decision, the estimated longitudinal displacement is compressed to obtain a displacement less than or equal to the longitudinal displacement threshold, and this displacement is used as the target longitudinal displacement of the vehicle matching the yield decision at the target time.
  • stretching or compressing the estimated longitudinal displacement can be to estimate a variable speed coefficient, by multiplying the variable speed coefficient and the estimated longitudinal displacement, and obtaining the value after the product operation to meet the target longitudinal displacement matched with the prior decision, Or meet the target longitudinal displacement matching the yield decision.
  • Fig. 4 is an example diagram showing a drivable trajectory interval of a vehicle at each future moment according to an embodiment of the present application. In Fig. 4, it includes the prior planned trajectory of the vehicle at the future time t 2 , t 3 and t 4 , the position information of the dynamic obstacle at the future time t 2 , t 3 and t 4 , and the vehicle’s future The revised planned driving area at time t 2 , t 3 and t 4 .
  • the estimated longitudinal displacement at the time t2 required for the calculation of the current frame of the planning module can be obtained from the position at the time t2 of the track calculated in the last frame of the planning module, and so on, the required displacement at the time t3 required for the calculation of this frame
  • the estimated longitudinal displacement can be obtained from the position at time t3 of the trajectory calculated by the last frame of the planning module.
  • the estimated longitudinal displacement at time t4 needed for the calculation of this frame can be obtained from the position at time t4 of the trajectory calculated in the last frame of the planning module .
  • each lateral width section included at the future time t2 is compared with the vehicle width of the vehicle, and it is determined that the corrected planning driving area of the vehicle at the future time t2 does not include the blocked position with insufficient traffic width, Therefore, at the future time t2 , the vehicle's drivable track interval ( L 2 lf ( ), L 2 rt ( )).
  • the estimated longitudinal displacement S3 at the future time t3 is stretched, so that the stretched target longitudinal displacement ⁇ S 3 ot , according to the obtained target longitudinal displacement, based on the functional relationship between the longitudinal displacement and lateral displacement of the vehicle, the target longitudinal displacement of the vehicle at the future time t3 and after stretching is obtained.
  • the corresponding lateral displacement interval (L 3 lf ( ), L 3 rt ( )).
  • the corrected planned driving area at future time t4 also includes blocked positions with insufficient traffic width, and even the revised planned driving area at future time t4 has been disconnected .
  • the longitudinal displacement threshold S 4 ot is determined, and the longitudinal displacement threshold S 4 ot is a value of longitudinal displacement that can avoid the blocking position and pass through the corrected planning driving area smoothly.
  • the estimated longitudinal displacement at the future time t 4 Stretch to make the target longitudinal displacement after stretching ⁇ S 4 ot , according to the obtained target longitudinal displacement, based on the functional relationship between the longitudinal displacement and lateral displacement of the vehicle, the target longitudinal displacement of the vehicle at the future time t 4 and after stretching is obtained.
  • the corresponding lateral displacement interval (L 4 lf ( ), L 4 rt ( )).
  • step S14 according to the drivable trajectory interval, the target planning trajectory of the vehicle within the time period formed by multiple future moments is obtained.
  • the continuity constraints can be performed on the drivable trajectory intervals according to the order of future time to obtain the target planning trajectory.
  • the planning module sends the target planning trajectory to the control module, and the control module controls the driving of the vehicle according to the local optimal trajectory provided by the planning module.
  • the continuity constraints within each future moment and between multiple future moments can be supplemented, as well as the penalty function constructed from the reference lateral position, reference speed and other objectives, and the optimal planning trajectory can be obtained with the help of convex optimization tools.
  • the vehicle after determining that the vehicle includes at least one preliminary planned driving area with a lateral width interval, by responding to the dynamic obstacles on the road where the vehicle is located in real time, that is, to obtain in real time the time of each dynamic obstacle on the road where the vehicle is located at multiple future moments
  • the location information of each dynamic obstacle at multiple future moments and the obstacle avoidance decision determine the drivable trajectory interval of the vehicle at each future moment, thus, the trajectory of this application
  • the planning method can optimize the path and speed at one time according to the vertical and horizontal joint constraints under a unified time frame, which improves the vehicle traffic efficiency and avoidance ability.
  • Fig. 5 is a block diagram 500 of a trajectory planning device according to an embodiment of the present application.
  • the trajectory planning device is applied to an automatic driving vehicle, and the device includes:
  • An acquisition module 501 configured to acquire the vehicle's current location information, map information, and static obstacle information on the road where the vehicle is located;
  • the first determination module 502 is used to obtain the preliminary planning driving area of the vehicle according to the positioning information, map information and static obstacle information, and the preliminary planning driving area includes at least one lateral width interval;
  • the second determination module 503 is used to obtain the position information of each dynamic obstacle on the road where the vehicle is located at multiple future moments, and according to the preliminary planning driving area, the position information of each dynamic obstacle at multiple future moments and the avoidance Obstacle decision-making to determine the drivable trajectory interval of the vehicle at each future moment;
  • the third determining module 504 is configured to obtain the target planning trajectory of the vehicle within a time period formed by multiple future moments according to the drivable trajectory interval.
  • the second determination module 503 determines the drivable track interval of the vehicle at each future moment in the following manner:
  • the preliminary planning driving area the position information of each dynamic obstacle at multiple future moments and the obstacle avoidance decision, and according to the position information and obstacle avoidance decision of each dynamic obstacle at multiple future moments, the preliminary planning driving area is carried out Correction, to obtain the corrected planned driving area of the vehicle at each future moment;
  • the obstacle avoidance decision includes detour to the left and right of the obstacle
  • the second determination module 503 adopts the following method to correct the preliminary planned driving area to obtain the corrected planned driving area of the vehicle at each future moment area:
  • each dynamic obstacle is taken as the target obstacle one by one, and the multiple future moments are taken as the target moment one by one, and according to the position information of the target obstacle at the target moment , extending the area occupied by the target obstacle to the direction opposite to the detour direction indicated by the obstacle avoidance decision of the target obstacle to the boundary of the corresponding lateral width interval to obtain the target obstacle area;
  • the target obstacle area is removed from the preliminary planned driving area, and the corrected planned driving area of the vehicle at the target moment is obtained.
  • the second determination module 503 determines the drivable trajectory interval of the vehicle at each future moment in the following manner:
  • each lateral width interval included in the corrected planned driving area of the vehicle at the target time is compared with the width of the vehicle to determine that the vehicle is at Whether the corrected planned driving area at the target moment includes the blocking position with insufficient traffic width;
  • the lateral displacement interval corresponding to the estimated longitudinal displacement of the vehicle at the target time is determined, and the drivable trajectory interval of the vehicle at the target time is obtained.
  • the second determination module 503 is further configured to determine the drivable trajectory interval of the vehicle at each future moment according to the revised planned driving area and the estimated longitudinal displacement in the following manner:
  • the longitudinal displacement threshold is determined according to the blocking position
  • the estimated longitudinal displacement, traffic decision and longitudinal displacement threshold determine the target longitudinal displacement of the vehicle matching the traffic decision at the target moment
  • the lateral displacement interval corresponding to the estimated longitudinal displacement of the vehicle at the target time is determined, and the drivable trajectory interval of the vehicle at the target time is obtained.
  • the second determining module 503 determines the target longitudinal displacement of the vehicle matching the passing decision at the target moment according to the estimated longitudinal displacement, the passing decision and the longitudinal displacement threshold in the following manner:
  • the estimated longitudinal displacement is stretched to obtain a displacement greater than or equal to the longitudinal displacement threshold, and this displacement is used as the target longitudinal displacement of the vehicle matching the first decision at the target time.
  • the second determining module 503 is also configured to determine the target longitudinal displacement of the vehicle matching the passing decision at the target moment according to the estimated longitudinal displacement, the passing decision and the longitudinal displacement threshold in the following manner:
  • the passing decision is a yield decision
  • the estimated longitudinal displacement is compressed to obtain a displacement less than or equal to the longitudinal displacement threshold, and this displacement is used as the target longitudinal displacement of the vehicle matching the yield decision at the target time.
  • the third determination module 504 obtains the target planning trajectory of the vehicle within a time period formed by multiple future moments according to the drivable trajectory interval in the following manner:
  • Continuity constraints are performed on the drivable trajectory interval according to the order of future time, and the target planning trajectory is obtained.
  • Fig. 6 is a block diagram of an electronic device 700 according to an embodiment of the present application.
  • the electronic device 700 may include: a processor 701 and a memory 702 .
  • the electronic device 700 may also include one or more of a multimedia component 703 , an input/output (I/O) interface 704 , and a communication component 705 .
  • I/O input/output
  • the processor 701 is used to control the overall operation of the electronic device 700, so as to complete all or part of the steps in the above XXXXX method.
  • the memory 702 is used to store various types of data to support the operation of the electronic device 700, for example, these data may include instructions for any application or method operating on the electronic device 700, and application-related data, Such as contact data, sent and received messages, pictures, audio, video, etc.
  • the memory 702 can be realized by any type of volatile or non-volatile memory device or their combination, such as Static Random Access Memory (Static Random Access Memory, referred to as SRAM), Electrically Erasable Programmable Read-Only Memory (EPROM) Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), Erasable Programmable Read-Only Memory (Erasable Programmable Read-Only Memory, referred to as EPROM), Programmable Read-Only Memory (Programmable Read-Only Memory, referred to as PROM), read-only Memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk.
  • Multimedia components 703 may include screen and audio components.
  • the screen can be, for example, a touch screen, and the audio component is used for outputting and/or inputting audio signals.
  • an audio component may include a microphone for receiving external audio signals.
  • the received audio signal may be further stored in memory 702 or sent via communication component 705 .
  • the audio component also includes at least one speaker for outputting audio signals.
  • the I/O interface 704 provides an interface between the processor 701 and other interface modules, which may be a keyboard, a mouse, buttons, and the like. These buttons can be virtual buttons or physical buttons.
  • the communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices.
  • Wireless communication such as Wi-Fi, Bluetooth, Near Field Communication (NFC for short), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or one or more of them Combinations are not limited here. Therefore, the corresponding communication component 705 may include: a Wi-Fi module, a Bluetooth module, an NFC module and the like.
  • the electronic device 700 may be implemented by one or more application-specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), digital signal processors (Digital Signal Processor, DSP for short), digital signal processing equipment (Digital Signal Processing Device, referred to as DSPD), programmable logic device (Programmable Logic Device, referred to as PLD), field programmable gate array (Field Programmable Gate Array, referred to as FPGA), controller, microcontroller, microprocessor or other electronic components Implementation, used to execute the above-mentioned trajectory planning method.
  • ASIC Application Specific Integrated Circuit
  • DSP Digital Signal Processor
  • DSPD Digital Signal Processing Device
  • PLD programmable logic device
  • FPGA Field Programmable Gate Array
  • controller microcontroller
  • microprocessor or other electronic components Implementation used to execute the above-mentioned trajectory planning method.
  • another embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored.
  • the program is executed by a processor, the trajectory planning method described in any of the above-mentioned embodiments of the present application is implemented.
  • the computer-readable storage medium may be the above-mentioned memory 702 including program instructions, and the above-mentioned program instructions can be executed by the processor 701 of the electronic device 700 to complete the above-mentioned trajectory planning method.
  • an electronic device including a memory, a processor, and a computer program stored on the memory and operable on the processor.
  • the steps in the trajectory planning method described in the embodiment may be the above-mentioned electronic device 700, including a memory 702, a processor 701, and a computer program stored in the memory 702 and operable on the processor 701.
  • the above program instructions may be executed by the processor 701 of the electronic device 700 to Complete the trajectory planning method described above.
  • the description is relatively simple, and for related parts, please refer to the part of the description of the method embodiment.
  • embodiments of the embodiments of the present application may be provided as methods, devices, or computer program products. Therefore, the embodiment of the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • Embodiments of the present application are described with reference to flowcharts and/or block diagrams of methods, terminal devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and a combination of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions.
  • an embodiment of the present application further provides a computer program product, including computer readable codes, and when the computer readable codes are run on a computing processing device, the computing processing device can cause the computing processing device to execute the program described in any one of the embodiments of the present application. Any one of the trajectory planning methods explained.
  • these computer program instructions may be provided to a general purpose computer, a special purpose computer, an embedded processor, or a processor of other programmable data processing terminal equipment to produce a machine such that the computer or other programmable data processing terminal equipment processor
  • the executed instructions generate means for implementing the functions specified in the flow chart or flow charts and/or the block diagram block or blocks.
  • These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the The instruction means implements the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Human Computer Interaction (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种轨迹规划方法，应用于自动驾驶车辆，轨迹规划方法包括：获取车辆当前的定位信息、地图信息和车辆所在道路的静态障碍物信息（S11）；根据定位信息、地图信息和和静态障碍物信息，得到车辆的初步规划行驶区域，初步规划行驶区域包括至少一个横向宽度区间（S12）；获取车辆所在道路的每个动态障碍物在多个未来时刻下的位置信息，并根据初步规划行驶区域、每个动态障碍物在多个未来时刻的位置信息和避障决策，确定车辆在每个未来时刻下的可行驶轨迹区间（S13）；根据可行驶轨迹区间，得到车辆在由多个未来时刻形成的时段内的目标规划轨迹（S14）。通过本申请，可提高车辆通行效率和避让能力。

Description

轨迹规划方法、装置、存储介质、设备及计算机程序产品
本申请要求在2021年7月27日提交中国专利局、申请号为202110852875.4、发明名称为“轨迹规划方法、装置、存储介质及电子设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及自动驾驶技术领域，尤其涉及一种轨迹规划方法、装置、存储介质、电子设备及计算机程序产品。
背景技术
现阶段，自动驾驶技术主要包括感知模块、规划模块和控制模块这三个组成部分。其中，感知模块用于感知车辆及车辆周边环境信息；规划模块用于根据自车状况、周边环境信息以及车辆所受约束、障碍物干扰、舒适性和轨迹长度等因素，通过优化所设计的权重函数，生成一条由当前状态到期望状态的安全、舒适且可行驶的局部最优轨迹，作为参考信号输入到控制模块中；而控制模块则用于根据规划模块所提供的局部最优轨迹，控制车辆行驶。
目前通过规划模块规划车辆未来轨迹时，采用路径规划和速度规划相解耦的方式，即将路径与速度通过独立算法进行规划，此方式无法考虑路径和速度的复合约束，且由于其他车辆等障碍物的运动状态可能随时会发生变化，也不支持对动态障碍物的实时响应，导致所规划的轨迹变得不合理，无法有效适应不断变化的实际驾驶环境，轨迹规划效率低下。
发明内容
本申请实施例提供一种轨迹规划方法、装置、存储介质、电子设备及计算机程序产品，以部分地解决相关技术中存在的上述问题。
为了实现上述目的，本申请实施例第一方面提供一种轨迹规划方法， 应用于自动驾驶车辆，所述方法包括：
获取车辆当前的定位信息、地图信息和车辆所在道路的静态障碍物信息；
根据所述定位信息、所述地图信息和和所述静态障碍物信息，得到所述车辆的初步规划行驶区域，所述初步规划行驶区域包括至少一个横向宽度区间；
获取所述车辆所在道路的每个动态障碍物在多个未来时刻下的位置信息，并根据所述初步规划行驶区域、每个动态障碍物在多个未来时刻的位置信息和避障决策，确定所述车辆在每个所述未来时刻下的可行驶轨迹区间；
根据所述可行驶轨迹区间，得到所述车辆在由所述多个未来时刻形成的时段内的目标规划轨迹。
可选地，所述根据所述初步规划行驶区域、每个动态障碍物在多个未来时刻的位置信息和避障决策，确定所述车辆在每个所述未来时刻下的可行驶轨迹区间，包括：
根据每个所述动态障碍物在多个所述未来时刻的位置信息和避障决策，对所述初步规划行驶区域进行修正，得到所述车辆在每个所述未来时刻下的修正规划行驶区域；
获取所述车辆在每个所述未来时刻下的预估纵向位移，并根据所述修正规划行驶区域和所述预估纵向位移，确定所述车辆在每个所述未来时刻下的可行驶轨迹区间。
可选地，所述避障决策包括对障碍物向左绕行和向右绕行，所述根据每个所述动态障碍物在多个所述未来时刻的位置信息和避障决策，对所述初步规划行驶区域进行修正，得到所述车辆在每个所述未来时刻下的修正规划行驶区域，包括：
将每个所述动态障碍物逐一作为目标障碍物，将多个所述未来时刻逐一作为目标时刻，根据所述目标障碍物在所述目标时刻的位置信息，将所述目标障碍物所占位置的区域向与所述目标障碍物的避障决策所指示的绕 行方向相反的方向横向延伸至对应横向宽度区间的边界，得到目标障碍物区域；
从所述初步规划行驶区域中去除所述目标障碍物区域，得到所述车辆在所述目标时刻下的修正规划行驶区域。
可选地，所述根据所述修正规划行驶区域和所述预估纵向位移，确定所述车辆在每个所述未来时刻下的可行驶轨迹区间，包括：
将多个所述未来时刻逐一作为目标时刻，将所述车辆在所述目标时刻下的修正规划行驶区域包括的每个横向宽度区间与所述车辆的车宽进行比较，确定所述车辆在所述目标时刻下的修正规划行驶区域是否包括通行宽度不足的阻塞位置；
若不包括所述阻塞位置，则基于所述车辆的纵向位移和横向位移之间的函数关系，确定所述车辆在所述目标时刻下与所述预估纵向位移对应的横向位移区间，得到所述车辆在所述目标时刻下的可行驶轨迹区间。
可选地，所述根据所述修正规划行驶区域和所述预估纵向位移，确定所述车辆在每个所述未来时刻下的可行驶轨迹区间，还包括：
若包括所述阻塞位置，则根据所述阻塞位置，确定纵向位移阈值；
获取在所述目标时刻下所述车辆的通行决策；
根据所述预估纵向位移、所述通行决策和所述纵向位移阈值，确定所述车辆在所述目标时刻下与所述通行决策匹配的目标纵向位移；
根据所述目标纵向位移，基于所述函数关系，确定所述车辆在所述目标时刻下与所述预估纵向位移对应的横向位移区间，得到所述车辆在所述目标时刻下的可行驶轨迹区间。
可选地，所述根据所述预估纵向位移、所述通行决策和所述纵向位移阈值，确定所述车辆在所述目标时刻下与所述通行决策匹配的目标纵向位移，包括：
若所述通行决策为先行决策，则对所述预估纵向位移进行拉伸，得到大于或等于所述纵向位移阈值的位移，并将该位移作为所述车辆在所述目标时刻下与所述先行决策匹配的目标纵向位移。
可选地，所述根据所述预估纵向位移、所述通行决策和所述纵向位移阈值，确定所述车辆在所述目标时刻下与所述通行决策匹配的目标纵向位移，还包括：
若所述通行决策为让行决策，则对所述预估纵向位移进行压缩，得到小于或等于所述纵向位移阈值的位移，并将该位移作为所述车辆在所述目标时刻下与所述让行决策匹配的目标纵向位移。
可选地，所述根据所述可行驶轨迹区间，得到所述车辆在由所述多个未来时刻形成的时段内的目标规划轨迹，包括：
对所述可行驶轨迹区间按照所述未来时刻的先后顺序进行连续性约束，得到所述目标规划轨迹。
本申请实施例第二方面提供一种轨迹规划装置，应用于自动驾驶车辆，所述装置包括：
获取模块，用于获取车辆当前的定位信息、地图信息和车辆所在道路的静态障碍物信息；
第一确定模块，用于根据所述定位信息、所述地图信息和和所述静态障碍物信息，得到所述车辆的初步规划行驶区域，所述初步规划行驶区域包括至少一个横向宽度区间；
第二确定模块，用于获取所述车辆所在道路的每个动态障碍物在多个未来时刻下的位置信息，并根据所述初步规划行驶区域、每个动态障碍物在多个未来时刻的位置信息和避障决策，确定所述车辆在每个所述未来时刻下的可行驶轨迹区间；
第三确定模块，用于根据所述可行驶轨迹区间，得到所述车辆在由所述多个未来时刻形成的时段内的目标规划轨迹。
可选地，所述第二确定模块采用如下方式确定所述车辆在每个所述未来时刻下的可行驶轨迹区间：
根据所述初步规划行驶区域、每个动态障碍物在多个未来时刻的位置信息和避障决策，并根据每个所述动态障碍物在多个所述未来时刻的位置信息和避障决策，对所述初步规划行驶区域进行修正，得到所述车辆在每 个所述未来时刻下的修正规划行驶区域；
获取所述车辆在每个所述未来时刻下的预估纵向位移，并根据所述修正规划行驶区域和所述预估纵向位移，确定所述车辆在每个所述未来时刻下的可行驶轨迹区间。
可选地，所述避障决策包括对障碍物向左绕行和向右绕行，所述第二确定模块采用如下方式，对所述初步规划行驶区域进行修正，得到所述车辆在每个所述未来时刻下的修正规划行驶区域：
根据每个所述动态障碍物在多个所述未来时刻的位置信息和避障决策将每个所述动态障碍物逐一作为目标障碍物，将多个所述未来时刻逐一作为目标时刻，根据所述目标障碍物在所述目标时刻的位置信息，将所述目标障碍物所占位置的区域向与所述目标障碍物的避障决策所指示的绕行方向相反的方向横向延伸至对应横向宽度区间的边界，得到目标障碍物区域；
从所述初步规划行驶区域中去除所述目标障碍物区域，得到所述车辆在所述目标时刻下的修正规划行驶区域。
可选地，所述第二确定模块采用如下方式确定所述车辆在每个所述未来时刻下的可行驶轨迹区间：
根据所述修正规划行驶区域和所述预估纵向位移，将多个所述未来时刻逐一作为目标时刻，将所述车辆在所述目标时刻下的修正规划行驶区域包括的每个横向宽度区间与所述车辆的车宽进行比较，确定所述车辆在所述目标时刻下的修正规划行驶区域是否包括通行宽度不足的阻塞位置；
若不包括所述阻塞位置，则基于所述车辆的纵向位移和横向位移之间的函数关系，确定所述车辆在所述目标时刻下与所述预估纵向位移对应的横向位移区间，得到所述车辆在所述目标时刻下的可行驶轨迹区间。
可选地，所述第二确定模块还用于采用如下方式根据所述修正规划行驶区域和所述预估纵向位移，确定所述车辆在每个所述未来时刻下的可行驶轨迹区间：
若包括所述阻塞位置，则根据所述阻塞位置，确定纵向位移阈值；
获取在所述目标时刻下所述车辆的通行决策；
根据所述预估纵向位移、所述通行决策和所述纵向位移阈值，确定所述车辆在所述目标时刻下与所述通行决策匹配的目标纵向位移；
根据所述目标纵向位移，基于所述函数关系，确定所述车辆在所述目标时刻下与所述预估纵向位移对应的横向位移区间，得到所述车辆在所述目标时刻下的可行驶轨迹区间。
可选地，所述第二确定模块采用如下方式根据所述预估纵向位移、所述通行决策和所述纵向位移阈值，确定所述车辆在所述目标时刻下与所述通行决策匹配的目标纵向位移：
若所述通行决策为先行决策，则对所述预估纵向位移进行拉伸，得到大于或等于所述纵向位移阈值的位移，并将该位移作为所述车辆在所述目标时刻下与所述先行决策匹配的目标纵向位移。
可选地，所述第二确定模块还用于采用如下方式根据所述预估纵向位移、所述通行决策和所述纵向位移阈值，确定所述车辆在所述目标时刻下与所述通行决策匹配的目标纵向位移：
若所述通行决策为让行决策，则对所述预估纵向位移进行压缩，得到小于或等于所述纵向位移阈值的位移，并将该位移作为所述车辆在所述目标时刻下与所述让行决策匹配的目标纵向位移。
可选地，所述第三确定模块采用如下方式根据所述可行驶轨迹区间，得到所述车辆在由所述多个未来时刻形成的时段内的目标规划轨迹：
对所述可行驶轨迹区间按照所述未来时刻的先后顺序进行连续性约束，得到所述目标规划轨迹。
本申请实施例第三方面提供一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现如本申请第一方面所述的方法中的步骤。
本申请实施例第四方面提供一种电子设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行时实现本申请第一方面所述的方法的步骤。
本申请实施例第五方面提供一种计算机程序产品，包括计算机可读代码，当所述计算机可读代码在计算处理设备上运行时，导致所述计算处理设备执行上述所述的轨迹规划方法。
上述说明仅是本发明技术方案的概述，为了能够更清楚了解本发明的技术手段，而可依照说明书的内容予以实施，并且为了让本发明的上述和其它目的、特征和优点能够更明显易懂，以下特举本发明的具体实施方式。
通过上述技术方案，确定车辆包括至少一个横向宽度区间的初步规划行驶区域之后，通过实时响应车辆所在道路的动态障碍物，即实时获取车辆所在道路的每个动态障碍物在多个未来时刻下的位置信息，根据初步规划行驶区域、每个动态障碍物在多个未来时刻的位置信息和避障决策，确定车辆在每个未来时刻下的可行驶轨迹区间，由此，本申请的轨迹规划方法可在统一的时间框架下依据纵横联合约束一次性优化路径和速度，提高了车辆通行效率和避让能力。
本本申请实施例的其他特征和优点将在随后的具体实施方式部分予以详细说明。
附图说明
为了更清楚地说明本申请实施例的技术方案，下面将对本申请实施例的描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1是根据本申请实施例示出的一种轨迹规划方法的流程图。
图2是根据本申请实施例示出的一种道路参考坐标系的示意图。
图3是根据本申请实施例示出的一种行驶区域的横向宽度区间的示意图。
图4是根据本申请实施例示出的一种车辆在每个所述未来时刻下的可行驶轨迹区间的示例图。
图5是根据本申请实施例示出的一种轨迹规划装置的框图。
图6是根据本申请一实施例示出的一种电子设备的框图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
需要说明的是，本申请实施例中所有获取信号、信息或数据的动作都是在遵照所在地国家相应的数据保护法规政策的前提下，并获得由相应装置所有者给予授权的情况下进行的。
图1是根据本申请实施例示出的一种轨迹规划方法的流程图，如图1所示，轨迹规划方法，包括以下步骤。
在步骤S11中，获取车辆当前的定位信息、地图信息和车辆所在道路的静态障碍物信息。
其中，车辆的定位信息、地图信息和静态障碍物信息可以通过高精度地图获取，静态障碍物信息可以包括障碍物的形状大小和障碍物的位置信息。
在步骤S12中，根据定位信息、地图信息和和静态障碍物信息，得到车辆的初步规划行驶区域，初步规划行驶区域包括至少一个横向宽度区间。
本申请中，初步规划行驶区域可以是自动驾驶车辆行驶的路径区域中，除去静态障碍物的路径区域。横向宽度区间可以是车辆行驶路径区域边界之间的宽度。
为了准确描述车辆的初步规划行驶区域，一种实施方式中，可基于车辆所在道路确定参考坐标系。该道路参考坐标系可以为弗莱纳(Frenet)坐标系。图2是根据本申请实施例示出的一种道路参考坐标系的示意图。在 图1中，该道路坐标系包括参考线(S轴)，该参考线可以为根据道路中心线进行平滑生成可供车辆行驶的一条(组)线，该道路坐标系还包括与参考线垂直的横线(L轴)。该道路坐标系还包括原点，例如该原点可以为车辆的起始点。
[根据细则91更正 12.04.2022]　

图3是根据本申请实施例示出的一种行驶区域的横向宽度区间L(S)的示意图。在图3中，以未示出包括静态障碍物的位置区域，行驶区域的横向宽度区间L(S)介于道路左边界和右边界之间为例，基于纵向位移的左边界例如可以记为Llf,sta(S)，右边界例如可以记为Lrt,sta(S)，即横向宽度区间L(S)与纵向位移s之间具有凸函数的关系，横向宽度区间L(S)与纵向位移S之间的函数关系可以记为：Lrt,sta(S)≤L(S)≤Llf,sta(S)。
在步骤S13中，获取车辆所在道路的每个动态障碍物在多个未来时刻下的位置信息，并根据初步规划行驶区域、每个动态障碍物在多个未来时刻的位置信息和避障决策，确定车辆在每个未来时刻下的可行驶轨迹区间。
其中，多个未来时刻例如可以是以0.1ms为单位的连续的时刻。避障决策包括对障碍物向左绕行和向右绕行。
在车辆行驶的过程中，由于动态障碍物在每一时刻的位置均处于变化中，使得动态障碍物在每一时刻所占用初步规划行驶区域的位置也不同，进而在每一时刻的初步规划行驶区域中车辆的可行驶区域也会不同。
而相关技术中，通过将路径规划和速度规划相解耦的方式进行规划，未将动态障碍物实时的运动位置对车辆的可行驶轨迹区间造成的变化进行考量，规划轨迹不能对动态障碍物进行响应，出现类似死板的让速不让道的情况。例如车辆在行驶中遇到逆行的非机动车，在车辆行驶道路的右侧空间仍然充裕的情况下，车辆不是向右绕行非机动车、反而是停车，使得规划的车辆的可行驶轨迹区间变得不合理，无法有效适应不断变化的实际驾驶环境。
故本申请中，可获取车辆所在道路的每个动态障碍物在多个未来时刻下的位置信息，根据初步规划行驶区域、每个动态障碍物在多个未来时刻 的位置信息和避障决策，确定车辆在每个未来时刻下的可行驶轨迹区间。
一种实施方式中，例如可通过如下方式确定车辆在每个未来时刻下的可行驶轨迹区间：
根据每个动态障碍物在多个未来时刻的位置信息和避障决策，对初步规划行驶区域进行修正，得到车辆在每个未来时刻下的修正规划行驶区域。获取车辆在每个未来时刻下的预估纵向位移，并根据修正规划行驶区域和预估纵向位移，确定车辆在每个未来时刻下的可行驶轨迹区间。
其中，例如通过如下方式对初步规划行驶区域进行修正，得到车辆在每个未来时刻下的修正规划行驶区域：
将每个动态障碍物逐一作为目标障碍物，将多个未来时刻逐一作为目标时刻，根据目标障碍物在目标时刻的位置信息，将目标障碍物所占位置的区域向与目标障碍物的避障决策所指示的绕行方向相反的方向横向延伸至对应横向宽度区间的边界，得到目标障碍物区域，从初步规划行驶区域中去除目标障碍物区域，得到车辆在目标时刻下的修正规划行驶区域。
由此，本申请实施例中，可对每一时刻动态障碍物的位置进行响应，实时确定每一时刻下的修正规划行驶区域，根据每个时刻下的修正规划行驶区域、和车辆的预估纵向位移，确定车辆在每个未来时刻下的可行驶轨迹区间。
其中，根据每个时刻下的修正规划行驶区域、和车辆的预估纵向位移，例如可通过如下方式确定车辆在每个未来时刻下的可行驶轨迹区间：
将多个未来时刻逐一作为目标时刻，将车辆在目标时刻下的修正规划行驶区域包括的每个横向宽度区间与车辆的车宽进行比较，确定车辆在目标时刻下的修正规划行驶区域是否包括通行宽度不足的阻塞位置。
若不包括阻塞位置，则基于车辆的纵向位移和横向位移之间的函数关系，确定车辆在目标时刻下与预估纵向位移对应的横向位移区间，得到车辆在目标时刻下的可行驶轨迹区间。
若包括阻塞位置，则根据阻塞位置，确定纵向位移阈值，并获取在目标时刻下车辆的通行决策。其中，纵向位移阈值可以表示在目标时刻下能 够避开阻塞位置顺利通过修正规划行驶区域的纵向位移的值。若通行决策为先行决策，则纵向位移阈值为能够避开阻塞位置顺利通过修正规划行驶区域的最小纵向位移。若通行决策为让行决策，则纵向位移阈值为能够避开阻塞位置顺利通过修正规划行驶区域的最大纵向位移。
根据预估纵向位移、通行决策和纵向位移阈值，确定车辆在目标时刻下与通行决策匹配的目标纵向位移，根据目标纵向位移，基于车辆的纵向位移和横向位移之间的函数关系，确定车辆在目标时刻下与预估纵向位移对应的横向位移区间，得到车辆在目标时刻下的可行驶轨迹区间。
若通行决策为先行决策，则对预估纵向位移进行拉伸，得到大于或等于纵向位移阈值的位移，并将该位移作为车辆在目标时刻下与先行决策匹配的目标纵向位移。若通行决策为让行决策，则对预估纵向位移进行压缩，得到小于或等于纵向位移阈值的位移，并将该位移作为车辆在目标时刻下与让行决策匹配的目标纵向位移。
其中，对预估纵向位移进行拉伸或者压缩可以是预估一个变速系数，通过将变速系数与预估纵向位移进行乘积运算，并得到乘积运算后的数值满足与先行决策匹配的目标纵向位移，或者满足与让行决策匹配的目标纵向位移。
[根据细则91更正 12.04.2022]　
图4是根据本申请实施例示出的一种车辆在每个未来时刻下的可行驶轨迹区间的示例图。在图4中，包括车辆在未来时刻t2、t3和t4时刻下的先验规划轨迹、动态障碍物在未来时刻t2、t3和t4时刻下的位置信息，和车辆在未来时刻t2、t3和t4时刻下的修正规划行驶区域。
[根据细则91更正 12.04.2022]　
其中，规划模块本帧计算所需的t2时刻下的预估纵向位移，可由规划模块上帧计算所得轨迹的t2时刻位置获取，以此类推，本帧计算所需的t3时刻下的预估纵向位移，可由规划模块上帧计算所得轨迹的t3时刻位置获取。本帧计算所需的t4时刻下的预估纵向位移，可由规划模块上帧计算所得轨迹的t4时刻位置获取。
从图4可以看出，动态障碍物(方块表示)由右侧逐渐向车辆靠近，避障决策可以是对障碍物的向左绕行，根据纵向位移S和未来时刻t的先验 信息将{(St，Lt)丨Ltrt(St)≤Lt≤Ltlf(St)}函数形式的修正规划行驶区域包括的横向宽度区间转化为数值形式：
[根据细则91更正 12.04.2022]　

{(St，Lt)丨Ltrt(St)≤Lt≤Ltlf(St)}，并且只要S-t的先验信息与最终优化得到的计划轨迹St*相差不大(即
Figure WO-DOC-FIGURE-1
)，这一转化就是近似等价的。进而在图4中，将未来时刻t2下的包括的每个横向宽度区间与车辆的车宽进行比较，确定车辆在未来时刻t2下的修正规划行驶区域不包括通行宽度不足的阻塞位置，故在未来时刻t2下可根据未来时刻t2下的预估纵向位移S2，得到车辆在未来时刻t2下的可行驶轨迹区间(L2 lf(
Figure WO-DOC-FIGURE-2
)，L2 rt(
Figure WO-DOC-FIGURE-2
))。
[根据细则91更正 12.04.2022]　
将未来时刻t3下的包括的每个横向宽度区间与车辆的车宽进行比较，确定车辆在未来时刻t3下的修正规划行驶区域包括通行宽度不足的阻塞位置，故在未来时刻t3下可根据阻塞位置，确定纵向位移阈值S3 ot，该纵向位移阈值S3 ot为能够避开阻塞位置顺利通过修正规划行驶区域的纵向位移的值。根据获取的通行决策为先行决策，对未来时刻t3下的预估纵向位移S3进行拉伸，使得拉伸后的目标纵向位移
Figure WO-DOC-FIGURE-3
≥S3 ot，根据得到的目标纵向位移，基于车辆的纵向位移和横向位移之间的函数关系，得到车辆在未来时刻t3下与拉伸后的目标纵向位移
Figure WO-DOC-FIGURE-3
对应的横向位移区间(L3 lf(
Figure WO-DOC-FIGURE-3
)，L3 rt(
Figure WO-DOC-FIGURE-3
))。
[根据细则91更正 12.04.2022]　
同样，在未来时刻t4下的修正规划行驶区域也包括通行宽度不足的阻塞位置，甚至在未来时刻t4下的修正规划行驶区域已经出现断开的情况，同样在未来时刻t4下可根据阻塞位置，确定纵向位移阈值S4 ot，该纵向位移阈值S4 ot为能够避开阻塞位置顺利通过修正规划行驶区域的纵向位移的值。根据获取的通行决策为先行决策，对未来时刻t4下的预估纵向位移
Figure WO-DOC-FIGURE-4
进行拉伸，使得拉伸后的目标纵向位移
Figure WO-DOC-FIGURE-4
≥S4 ot，根据得到的目标纵向位移，基于车辆的纵向位移和横向位移之间的函数关系，得到车辆在未来时刻t4下与拉伸后的目标纵向位移
Figure WO-DOC-FIGURE-4
对应的横向位移区间(L4 lf(
Figure WO-DOC-FIGURE-4
)，L4 rt(
Figure WO-DOC-FIGURE-4
))。
在步骤S14中，根据可行驶轨迹区间，得到车辆在由多个未来时刻形成的时段内的目标规划轨迹。
一种实施方式中，根据车辆的可行驶轨迹区间，例如可对可行驶轨迹区间按照未来时刻的先后顺序进行连续性约束，得到目标规划轨迹。之后，规划模块将目标规划轨迹下发给控制模块，通过控制模块根据规划模块所提供的局部最优轨迹，控制车辆行驶。
例如，可补充每个未来时刻内、多个未来时刻之间的连续性约束，以及由参考横向位置、参考速度等目标构造得到的惩罚函数，即可借助凸优化工具得到最优的计划轨迹。
在本申请实施例中，确定车辆包括至少一个横向宽度区间的初步规划行驶区域之后，通过实时响应车辆所在道路的动态障碍物，即实时获取车辆所在道路的每个动态障碍物在多个未来时刻下的位置信息，根据初步规划行驶区域、每个动态障碍物在多个未来时刻的位置信息和避障决策，确定车辆在每个未来时刻下的可行驶轨迹区间，由此，本申请的轨迹规划方法可在统一的时间框架下依据纵横联合约束一次性优化路径和速度，提高了车辆通行效率和避让能力。
图5是根据本申请实施例示出的一种轨迹规划装置的框图500。参照图5，轨迹规划装置，应用于自动驾驶车辆，装置包括：
获取模块501，用于获取车辆当前的定位信息、地图信息和车辆所在道路的静态障碍物信息；
第一确定模块502，用于根据定位信息、地图信息和和静态障碍物信息，得到车辆的初步规划行驶区域，初步规划行驶区域包括至少一个横向宽度区间；
第二确定模块503，用于获取车辆所在道路的每个动态障碍物在多个未来时刻下的位置信息，并根据初步规划行驶区域、每个动态障碍物在多个未来时刻的位置信息和避障决策，确定车辆在每个未来时刻下的可行驶轨迹区间；
第三确定模块504，用于根据可行驶轨迹区间，得到车辆在由多个未来时刻形成的时段内的目标规划轨迹。
可选地，第二确定模块503采用如下方式确定车辆在每个未来时刻下 的可行驶轨迹区间：
根据初步规划行驶区域、每个动态障碍物在多个未来时刻的位置信息和避障决策，并根据每个动态障碍物在多个未来时刻的位置信息和避障决策，对初步规划行驶区域进行修正，得到车辆在每个未来时刻下的修正规划行驶区域；
获取车辆在每个未来时刻下的预估纵向位移，并根据修正规划行驶区域和预估纵向位移，确定车辆在每个未来时刻下的可行驶轨迹区间。
可选地，避障决策包括对障碍物向左绕行和向右绕行，第二确定模块503采用如下方式，对初步规划行驶区域进行修正，得到车辆在每个未来时刻下的修正规划行驶区域：
根据每个动态障碍物在多个未来时刻的位置信息和避障决策将每个动态障碍物逐一作为目标障碍物，将多个未来时刻逐一作为目标时刻，根据目标障碍物在目标时刻的位置信息，将目标障碍物所占位置的区域向与目标障碍物的避障决策所指示的绕行方向相反的方向横向延伸至对应横向宽度区间的边界，得到目标障碍物区域；
从初步规划行驶区域中去除目标障碍物区域，得到车辆在目标时刻下的修正规划行驶区域。
可选地，第二确定模块503采用如下方式确定车辆在每个未来时刻下的可行驶轨迹区间：
根据修正规划行驶区域和预估纵向位移，将多个未来时刻逐一作为目标时刻，将车辆在目标时刻下的修正规划行驶区域包括的每个横向宽度区间与车辆的车宽进行比较，确定车辆在目标时刻下的修正规划行驶区域是否包括通行宽度不足的阻塞位置；
若不包括阻塞位置，则基于车辆的纵向位移和横向位移之间的函数关系，确定车辆在目标时刻下与预估纵向位移对应的横向位移区间，得到车辆在目标时刻下的可行驶轨迹区间。
可选地，第二确定模块503还用于采用如下方式根据修正规划行驶区域和预估纵向位移，确定车辆在每个未来时刻下的可行驶轨迹区间：
若包括阻塞位置，则根据阻塞位置，确定纵向位移阈值；
获取在目标时刻下车辆的通行决策；
根据预估纵向位移、通行决策和纵向位移阈值，确定车辆在目标时刻下与通行决策匹配的目标纵向位移；
根据目标纵向位移，基于函数关系，确定车辆在目标时刻下与预估纵向位移对应的横向位移区间，得到车辆在目标时刻下的可行驶轨迹区间。
可选地，第二确定模块503采用如下方式根据预估纵向位移、通行决策和纵向位移阈值，确定车辆在目标时刻下与通行决策匹配的目标纵向位移：
若通行决策为先行决策，则对预估纵向位移进行拉伸，得到大于或等于纵向位移阈值的位移，并将该位移作为车辆在目标时刻下与先行决策匹配的目标纵向位移。
可选地，第二确定模块503还用于采用如下方式根据预估纵向位移、通行决策和纵向位移阈值，确定车辆在目标时刻下与通行决策匹配的目标纵向位移：
若通行决策为让行决策，则对预估纵向位移进行压缩，得到小于或等于纵向位移阈值的位移，并将该位移作为车辆在目标时刻下与让行决策匹配的目标纵向位移。
可选地，第三确定模块504采用如下方式根据可行驶轨迹区间，得到车辆在由多个未来时刻形成的时段内的目标规划轨迹：
对可行驶轨迹区间按照未来时刻的先后顺序进行连续性约束，得到目标规划轨迹。
关于上述实施例中的装置，其中各个模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不做详细阐述说明。
图6是根据本申请实施例示出的一种电子设备700的框图。如图6所示，该电子设备700可以包括：处理器701，存储器702。该电子设备700还可以包括多媒体组件703，输入/输出(I/O)接口704，以及通信组件705中的一者或多者。
其中，处理器701用于控制该电子设备700的整体操作，以完成上述的XXXXX方法中的全部或部分步骤。存储器702用于存储各种类型的数据以支持在该电子设备700的操作，这些数据例如可以包括用于在该电子设备700上操作的任何应用程序或方法的指令，以及应用程序相关的数据，例如联系人数据、收发的消息、图片、音频、视频等等。该存储器702可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，例如静态随机存取存储器(Static Random Access Memory，简称SRAM)，电可擦除可编程只读存储器(Electrically Erasable Programmable Read-Only Memory，简称EEPROM)，可擦除可编程只读存储器(Erasable Programmable Read-Only Memory，简称EPROM)，可编程只读存储器(Programmable Read-Only Memory，简称PROM)，只读存储器(Read-Only Memory，简称ROM)，磁存储器，快闪存储器，磁盘或光盘。多媒体组件703可以包括屏幕和音频组件。其中屏幕例如可以是触摸屏，音频组件用于输出和/或输入音频信号。例如，音频组件可以包括一个麦克风，麦克风用于接收外部音频信号。所接收的音频信号可以被进一步存储在存储器702或通过通信组件705发送。音频组件还包括至少一个扬声器，用于输出音频信号。I/O接口704为处理器701和其他接口模块之间提供接口，上述其他接口模块可以是键盘，鼠标，按钮等。这些按钮可以是虚拟按钮或者实体按钮。通信组件705用于该电子设备700与其他设备之间进行有线或无线通信。无线通信，例如Wi-Fi，蓝牙，近场通信(Near Field Communication，简称NFC)，2G、3G、4G、NB-IOT、eMTC、或其他5G等等，或它们中的一种或几种的组合，在此不做限定。因此相应的该通信组件705可以包括：Wi-Fi模块，蓝牙模块，NFC模块等等。
在一示例性实施例中，电子设备700可以被一个或多个应用专用集成电路(Application Specific Integrated Circuit，简称ASIC)、数字信号处理器(Digital Signal Processor，简称DSP)、数字信号处理设备(Digital Signal Processing Device，简称DSPD)、可编程逻辑器件(Programmable Logic Device，简称PLD)、现场可编程门阵列(Field Programmable Gate  Array，简称FPGA)、控制器、微控制器、微处理器或其他电子元件实现，用于执行上述的轨迹规划方法。
基于同一发明构思，本申请另一实施例提供一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现如本申请上述任一实施例所述的轨迹规划方法中的步骤。例如，该计算机可读存储介质可以为上述包括程序指令的存储器702，上述程序指令可由电子设备700的处理器701执行以完成上述的轨迹规划方法。
基于同一发明构思，本申请另一实施例提供一种电子设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行时实现本申请上述任一实施例所述的轨迹规划方法中的步骤。例如，该电子设备可以为上述电子设备700，包括存储器702、处理器701及存储在存储器702上并可在处理器701上运行的计算机程序，上述程序指令可由电子设备700的处理器701执行以完成上述的轨迹规划方法。
对于装置实施例而言，由于其与方法实施例基本相似，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。
本说明书中的各个实施例均采用递进的方式描述，每个实施例重点说明的都是与其他实施例的不同之处，各个实施例之间相同相似的部分互相参见即可。
本领域内的技术人员应明白，本申请实施例的实施例可提供为方法、装置、或计算机程序产品。因此，本申请实施例可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请实施例可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请实施例是参照根据本申请实施例的方法、终端设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。
因此，本申请实施例还提供一种计算机程序产品，包括计算机可读代码，当所述计算机可读代码在计算处理设备上运行时，可以导致所述计算处理设备执行本申请任意一个实施例所阐释的任意一种轨迹规划方法。具体地，可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理终端设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理终端设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理终端设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理终端设备上，使得在计算机或其他可编程终端设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程终端设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
尽管已描述了本申请实施例的优选实施例，但本领域内的技术人员一旦得知了基本创造性概念，则可对这些实施例做出另外的变更和修改。所以，所附权利要求意欲解释为包括优选实施例以及落入本申请实施例范围的所有变更和修改。
最后，还需要说明的是，在本文中，诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者终端设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者终端设备所固有的要素。在没有更多限制的情况下，由语句 “包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、物品或者终端设备中还存在另外的相同要素。
本技术领域技术人员可以理解，本申请中已经讨论过的各种操作、方法、流程中的步骤、措施、方案可以被交替、更改、组合或删除。进一步地，具有本申请中已经讨论过的各种操作、方法、流程中的其他步骤、措施、方案也可以被交替、更改、重排、分解、组合或删除。进一步地，现有技术中的具有与本申请中公开的各种操作、方法、流程中的步骤、措施、方案也可以被交替、更改、重排、分解、组合或删除。
以上对本申请所提供的一种轨迹规划方法、装置、存储介质及电子设备，进行了详细介绍，本文中应用了具体个例对本申请的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本申请的方法及其核心思想；同时，对于本领域的一般技术人员，依据本申请的思想，在具体实施方式及应用范围上均会有改变之处，综上所述，本说明书内容不应理解为对本申请的限制。本领域技术人员在不脱离本申请的精神和范围的前提下，可进行各种变更与修改，这些变更与修改均将落入本发明的保护范围。

Claims (12)

  1. 一种轨迹规划方法，应用于自动驾驶车辆，其特征在于，所述方法包括：
    获取车辆当前的定位信息、地图信息和车辆所在道路的静态障碍物信息；
    根据所述定位信息、所述地图信息和和所述静态障碍物信息，得到所述车辆的初步规划行驶区域，所述初步规划行驶区域包括至少一个横向宽度区间；
    获取所述车辆所在道路的每个动态障碍物在多个未来时刻下的位置信息，并根据所述初步规划行驶区域、每个动态障碍物在多个未来时刻的位置信息和避障决策，确定所述车辆在每个所述未来时刻下的可行驶轨迹区间；
    根据所述可行驶轨迹区间，得到所述车辆在由所述多个未来时刻形成的时段内的目标规划轨迹。
  2. 根据权利要求1所述的方法，其特征在于，所述根据所述初步规划行驶区域、每个动态障碍物在多个未来时刻的位置信息和避障决策，确定所述车辆在每个所述未来时刻下的可行驶轨迹区间，包括：
    根据每个所述动态障碍物在多个所述未来时刻的位置信息和避障决策，对所述初步规划行驶区域进行修正，得到所述车辆在每个所述未来时刻下的修正规划行驶区域；
    获取所述车辆在每个所述未来时刻下的预估纵向位移，并根据所述修正规划行驶区域和所述预估纵向位移，确定所述车辆在每个所述未来时刻下的可行驶轨迹区间。
  3. 根据权利要求2所述的方法，其特征在于，所述避障决策包括对障碍物向左绕行和向右绕行，所述根据每个所述动态障碍物在多个所述未来时刻的位置信息和避障决策，对所述初步规划行驶区域进行修正，得到所 述车辆在每个所述未来时刻下的修正规划行驶区域，包括：
    将每个所述动态障碍物逐一作为目标障碍物，将多个所述未来时刻逐一作为目标时刻，根据所述目标障碍物在所述目标时刻的位置信息，将所述目标障碍物所占位置的区域向与所述目标障碍物的避障决策所指示的绕行方向相反的方向横向延伸至对应横向宽度区间的边界，得到目标障碍物区域；
    从所述初步规划行驶区域中去除所述目标障碍物区域，得到所述车辆在所述目标时刻下的修正规划行驶区域。
  4. 根据权利要求2所述的方法，其特征在于，所述根据所述修正规划行驶区域和所述预估纵向位移，确定所述车辆在每个所述未来时刻下的可行驶轨迹区间，包括：
    将多个所述未来时刻逐一作为目标时刻，将所述车辆在所述目标时刻下的修正规划行驶区域包括的每个横向宽度区间与所述车辆的车宽进行比较，确定所述车辆在所述目标时刻下的修正规划行驶区域是否包括通行宽度不足的阻塞位置；
    若不包括所述阻塞位置，则基于所述车辆的纵向位移和横向位移之间的函数关系，确定所述车辆在所述目标时刻下与所述预估纵向位移对应的横向位移区间，得到所述车辆在所述目标时刻下的可行驶轨迹区间。
  5. 根据权利要求4所述的方法，其特征在于，所述根据所述修正规划行驶区域和所述预估纵向位移，确定所述车辆在每个所述未来时刻下的可行驶轨迹区间，还包括：
    若包括所述阻塞位置，则根据所述阻塞位置，确定纵向位移阈值；
    获取在所述目标时刻下所述车辆的通行决策；
    根据所述预估纵向位移、所述通行决策和所述纵向位移阈值，确定所述车辆在所述目标时刻下与所述通行决策匹配的目标纵向位移；
    根据所述目标纵向位移，基于所述函数关系，确定所述车辆在所述目 标时刻下与所述预估纵向位移对应的横向位移区间，得到所述车辆在所述目标时刻下的可行驶轨迹区间。
  6. 根据权利要求5所述的方法，其特征在于，所述根据所述预估纵向位移、所述通行决策和所述纵向位移阈值，确定所述车辆在所述目标时刻下与所述通行决策匹配的目标纵向位移，包括：
    若所述通行决策为先行决策，则对所述预估纵向位移进行拉伸，得到大于或等于所述纵向位移阈值的位移，并将该位移作为所述车辆在所述目标时刻下与所述先行决策匹配的目标纵向位移。
  7. 根据权利要求5所述的方法，其特征在于，所述根据所述预估纵向位移、所述通行决策和所述纵向位移阈值，确定所述车辆在所述目标时刻下与所述通行决策匹配的目标纵向位移，还包括：
    若所述通行决策为让行决策，则对所述预估纵向位移进行压缩，得到小于或等于所述纵向位移阈值的位移，并将该位移作为所述车辆在所述目标时刻下与所述让行决策匹配的目标纵向位移。
  8. 根据权利要求1-7中任一项所述的方法，其特征在于，所述根据所述可行驶轨迹区间，得到所述车辆在由所述多个未来时刻形成的时段内的目标规划轨迹，包括：
    对所述可行驶轨迹区间按照所述未来时刻的先后顺序进行连续性约束，得到所述目标规划轨迹。
  9. 一种轨迹规划装置，应用于自动驾驶车辆，其特征在于，所述装置包括：
    获取模块，用于获取车辆当前的定位信息、地图信息和车辆所在道路的静态障碍物信息；
    第一确定模块，用于根据所述定位信息、所述地图信息和和所述静态 障碍物信息，得到所述车辆的初步规划行驶区域，所述初步规划行驶区域包括至少一个横向宽度区间；
    第二确定模块，用于获取所述车辆所在道路的每个动态障碍物在多个未来时刻下的位置信息，并根据所述初步规划行驶区域、每个动态障碍物在多个未来时刻的位置信息和避障决策，确定所述车辆在每个所述未来时刻下的可行驶轨迹区间；
    第三确定模块，用于根据所述可行驶轨迹区间，得到所述车辆在由所述多个未来时刻形成的时段内的目标规划轨迹。
  10. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，该程序被处理器执行时实现权利要求1-8中任一项所述轨迹规划方法的步骤。
  11. 一种电子设备，其特征在于，包括：
    存储器，其上存储有计算机程序；
    处理器，用于执行所述存储器中的所述计算机程序，以实现权利要求1-8中任一项所述轨迹规划方法的步骤。
  12. 一种计算机程序产品，包括计算机可读代码，当所述计算机可读代码在计算处理设备上运行时，所述计算处理设备执行根据权利要求1-8中任一项所述轨迹规划方法。
PCT/CN2022/081449 2021-07-27 2022-03-17 轨迹规划方法、装置、存储介质、设备及计算机程序产品 WO2023005223A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110852875.4A CN113799797B (zh) 2021-07-27 2021-07-27 轨迹规划方法、装置、存储介质及电子设备
CN202110852875.4 2021-07-27

Publications (1)

Publication Number Publication Date
WO2023005223A1 true WO2023005223A1 (zh) 2023-02-02

Family

ID=78893185

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/081449 WO2023005223A1 (zh) 2021-07-27 2022-03-17 轨迹规划方法、装置、存储介质、设备及计算机程序产品

Country Status (2)

Country Link
CN (1) CN113799797B (zh)
WO (1) WO2023005223A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115892076A (zh) * 2023-02-23 2023-04-04 福思(杭州)智能科技有限公司 车道障碍物筛选方法、装置和域控制器
CN116088538A (zh) * 2023-04-06 2023-05-09 禾多科技（北京）有限公司 车辆轨迹信息生成方法、装置、设备和计算机可读介质
CN116442991A (zh) * 2023-04-25 2023-07-18 广州汽车集团股份有限公司 自动泊车规划方法、装置、车辆及存储介质
CN116729384A (zh) * 2023-06-27 2023-09-12 广州小鹏自动驾驶科技有限公司 车道保持状态下的绕行规划方法、装置及车辆

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113799797B (zh) * 2021-07-27 2022-07-12 北京三快在线科技有限公司 轨迹规划方法、装置、存储介质及电子设备
CN114312305A (zh) * 2021-12-22 2022-04-12 东软睿驰汽车技术（沈阳）有限公司 行驶提示方法、车辆、计算机可读存储介质
CN114299758A (zh) * 2021-12-30 2022-04-08 阿波罗智联(北京)科技有限公司 车辆控制方法及装置、设备、介质和产品
CN114397897A (zh) * 2022-01-20 2022-04-26 阿维塔科技(重庆)有限公司 一种车辆可行驶区域边界曲线生成方法、装置及存储介质
CN114590252A (zh) * 2022-04-01 2022-06-07 广州文远知行科技有限公司 自动驾驶车辆避障控制方法、装置、设备及可读存储介质
CN115583367B (zh) * 2022-10-09 2023-05-30 哈尔滨工业大学 一种基于分布式序列凸优化的卫星集群重构控制方法
CN115355916B (zh) * 2022-10-24 2023-03-03 北京智行者科技股份有限公司 移动工具的轨迹规划方法、设备和计算机可读存储介质
CN117962917A (zh) * 2022-10-24 2024-05-03 北京三快在线科技有限公司 自动驾驶决策规划方法及自动驾驶车辆
CN115892075B (zh) * 2023-01-06 2023-06-09 阿里巴巴达摩院(杭州)科技有限公司 轨迹规划方法、自动驾驶设备及计算机存储介质

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2562049A (en) * 2017-05-02 2018-11-07 Kompetenzzentrum Das Virtuelle Fahrzeug Improved pedestrian prediction by using enhanced map data in automated vehicles
CN109901575A (zh) * 2019-02-20 2019-06-18 百度在线网络技术（北京）有限公司 车辆路线规划调试方法、装置、设备及计算机可读介质
CN109934164A (zh) * 2019-03-12 2019-06-25 杭州飞步科技有限公司 基于轨迹安全度的数据处理方法和装置
CN109960261A (zh) * 2019-03-22 2019-07-02 北京理工大学 一种基于碰撞检测的动态障碍物避让方法
CN110550029A (zh) * 2019-08-12 2019-12-10 华为技术有限公司 障碍物避让方法及装置
US20200089239A1 (en) * 2018-09-14 2020-03-19 The Boeing Company Computer-Implemented Method and a System for Defining a Path for a Vehicle Within an Environment With Obstacles
CN112519770A (zh) * 2019-08-28 2021-03-19 哲内提 用于自主和半自主车辆的路径规划
CN113799797A (zh) * 2021-07-27 2021-12-17 北京三快在线科技有限公司 轨迹规划方法、装置、存储介质及电子设备

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107622684B (zh) * 2017-09-14 2020-07-28 华为技术有限公司 信息传输方法、交通控制单元和车载单元
DE102018222611A1 (de) * 2018-12-20 2020-06-25 Robert Bosch Gmbh Verfahren zum Betreiben eines automatisierten Fahrzeugs
WO2020249989A1 (ja) * 2019-06-13 2020-12-17 日産自動車株式会社 車両の走行制御方法及び走行制御装置
CN111942372B (zh) * 2020-07-27 2022-02-22 广州汽车集团股份有限公司 一种自动泊车方法及系统
CN112498366B (zh) * 2020-11-20 2022-04-05 苏州智加科技有限公司 自动驾驶车辆、控制方法、装置、设备及存储介质
CN112526999B (zh) * 2020-12-22 2023-04-28 北京百度网讯科技有限公司 速度规划方法、装置、电子设备和存储介质
CN113138597A (zh) * 2021-03-31 2021-07-20 深圳市优必选科技股份有限公司 一种智能小车的避障方法及智能小车
CN113071523A (zh) * 2021-04-23 2021-07-06 银隆新能源股份有限公司 无人驾驶车辆的控制方法及控制装置、无人驾驶车辆
CN113104033B (zh) * 2021-05-11 2022-06-03 东风柳州汽车有限公司 低速自动驾驶方法、装置、设备及存储介质

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2562049A (en) * 2017-05-02 2018-11-07 Kompetenzzentrum Das Virtuelle Fahrzeug Improved pedestrian prediction by using enhanced map data in automated vehicles
US20200089239A1 (en) * 2018-09-14 2020-03-19 The Boeing Company Computer-Implemented Method and a System for Defining a Path for a Vehicle Within an Environment With Obstacles
CN109901575A (zh) * 2019-02-20 2019-06-18 百度在线网络技术（北京）有限公司 车辆路线规划调试方法、装置、设备及计算机可读介质
CN109934164A (zh) * 2019-03-12 2019-06-25 杭州飞步科技有限公司 基于轨迹安全度的数据处理方法和装置
CN109960261A (zh) * 2019-03-22 2019-07-02 北京理工大学 一种基于碰撞检测的动态障碍物避让方法
CN110550029A (zh) * 2019-08-12 2019-12-10 华为技术有限公司 障碍物避让方法及装置
CN112519770A (zh) * 2019-08-28 2021-03-19 哲内提 用于自主和半自主车辆的路径规划
CN113799797A (zh) * 2021-07-27 2021-12-17 北京三快在线科技有限公司 轨迹规划方法、装置、存储介质及电子设备

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115892076A (zh) * 2023-02-23 2023-04-04 福思(杭州)智能科技有限公司 车道障碍物筛选方法、装置和域控制器
CN115892076B (zh) * 2023-02-23 2023-05-23 福思(杭州)智能科技有限公司 车道障碍物筛选方法、装置和域控制器
CN116088538A (zh) * 2023-04-06 2023-05-09 禾多科技（北京）有限公司 车辆轨迹信息生成方法、装置、设备和计算机可读介质
CN116088538B (zh) * 2023-04-06 2023-06-13 禾多科技（北京）有限公司 车辆轨迹信息生成方法、装置、设备和计算机可读介质
CN116442991A (zh) * 2023-04-25 2023-07-18 广州汽车集团股份有限公司 自动泊车规划方法、装置、车辆及存储介质
CN116729384A (zh) * 2023-06-27 2023-09-12 广州小鹏自动驾驶科技有限公司 车道保持状态下的绕行规划方法、装置及车辆
CN116729384B (zh) * 2023-06-27 2024-01-09 广州小鹏自动驾驶科技有限公司 车道保持状态下的绕行规划方法、装置及车辆

Also Published As

Publication number Publication date
CN113799797A (zh) 2021-12-17
CN113799797B (zh) 2022-07-12

Similar Documents

Publication Publication Date Title
WO2023005223A1 (zh) 轨迹规划方法、装置、存储介质、设备及计算机程序产品
CN111426330B (zh) 路径生成方法和设备、无人化运输系统和存储介质
JP6982897B2 (ja) ライダ、レーダ及びカメラセンサのデータを使用する強化学習に基づく自律走行時の最適化されたリソース割当てのための方法及び装置
JP6845874B2 (ja) 自動運転車のための経路及び速度の最適化フォールバックメカニズム
US9821801B2 (en) System and method for controlling semi-autonomous vehicles
CN112020014B (zh) 一种换道轨迹规划方法、装置、服务器及存储介质
EP3730370A1 (en) Method and device for acquiring automatic driving track
CN113405558B (zh) 自动驾驶地图的构建方法及相关装置
DE102018100182A1 (de) Insassenpräferenzen einbindendes autonomes Fahrzeugsteuersystem und -Verfahren
CN111830979A (zh) 一种轨迹优化方法和装置
CN111768647A (zh) 一种基于移动边缘计算的自主泊车方法和装置
US11449058B2 (en) Traveling track determination processing and automated drive device
EP3915857B1 (en) A parking assist apparatus and a method of controlling the parking assist apparatus
CN110553660A (zh) 一种基于a*算法和人工势场的无人车轨迹规划方法
CN113252027B (zh) 井下无人驾驶车辆局部路径规划方法、装置、设备及存储介质
JP7312728B2 (ja) 車両を制御する方法、装置、機器及び記憶媒体
CN112327826A (zh) 一种路径规划方法、装置、设备和介质
JP2019010967A (ja) 自動制御装置およびその制御方法
CN114527761A (zh) 一种基于融合算法的智能汽车局部路径规划方法
CN114715192A (zh) 一种解耦的自动驾驶车辆实时轨迹规划方法、装置及系统
CN112612267A (zh) 自动驾驶的路径规划方法和装置
CN113759892A (zh) 无人车障碍物绕行方法、装置、无人车及存储介质
CN114763133A (zh) 车辆泊车规划方法、装置、设备及计算机存储介质
CN109556623B (zh) 融合触须算法与切线图法的迭代式路径规划算法
CN115535003A (zh) 自动驾驶车辆的路口控制方法、装置、电子设备和介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22847843

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE