WO2023097874A1

WO2023097874A1 - Method and device for planning driving track

Info

Publication number: WO2023097874A1
Application number: PCT/CN2022/071336
Authority: WO
Inventors: 黄超; 叶玥
Original assignee: 上海仙途智能科技有限公司
Priority date: 2021-12-01
Filing date: 2022-01-11
Publication date: 2023-06-08
Also published as: CN115230719A; CN115230719B

Abstract

A method and device for planning a driving track. The method comprises: acquiring road information obtained by collecting information of a road (102); planning a normal driving track of a vehicle according to the road information to obtain the normal driving track, and planning a rollback driving track of the vehicle to obtain the rollback driving track, the driving track of the vehicle being a planned normal driving track, and the planned driving distance of the rollback driving track being shorter than the planned driving distance of the normal driving track (104); and in response to failure of the normal driving track, converting the driving track of the vehicle into the rollback driving track (106). According to the method, not only a normal driving track is generated, but also a rollback driving track is generated. When the vehicle cannot drive in the normal driving track, the vehicle switches to the rollback driving track, so that the accident occurrence probability can be reduced.

Description

Method and device for driving trajectory planning

technical field

The present disclosure relates to the technical field of intelligent driving, and in particular to a method and a device for driving trajectory planning.

Background technique

In the intelligent driving system, the planning module is responsible for integrating the contents of multiple modules such as perception, prediction, positioning, map, and vehicle to generate fast, safe, and feasible trajectories for intelligent driving vehicles.

Trajectory planning is roughly divided into decision-making, path planning and speed planning. The decision-making module gives macro-decisions based on road conditions, such as lane keeping, lane changing, and borrowing. Path planning is based on upper-level decisions, considering static obstacles and low-speed dynamic obstacles, and generating multiple safe and collision-free paths. Speed planning is based on path planning, considering dynamic obstacles at higher speeds, making decisions such as overtaking, car following, parking and avoidance, and producing corresponding ST (distance time, longitudinal displacement time) diagrams. Finally, multiple trajectories are obtained by merging path planning and speed planning, and an optimal safe, collision-free and comfortable driving trajectory is obtained by screening. Among them, the path obtained by path planning only contains spatial position information, while the driving trajectory contains spatiotemporal information, that is, the position on the driving trajectory corresponds to the time point of reaching the position.

However, in complex road scenarios such as cities, planning failures may occur due to the large number of traffic participants, large behavioral uncertainties, or low algorithm accuracy of the intelligent driving system itself. At this time, because the speed of the vehicle may be high, operations such as steering and avoidance cannot be completed when the planning fails, resulting in dangerous consequences. For example, in path planning, the planned driving distance is relatively long, and multiple paths may be planned under different decisions. Therefore, in order to ensure the planning frequency, the accuracy of path planning will be sacrificed. In scenarios requiring high precision, planning failures will occur. Case.

Contents of the invention

In view of this, the embodiments of the present disclosure provide at least one driving trajectory planning method and device.

Specifically, the embodiments of the present disclosure are achieved through the following technical solutions:

In a first aspect, a method for planning a driving trajectory is provided, the method comprising: acquiring road information obtained by collecting road information; planning a normal driving trajectory of a vehicle according to the road information to obtain the normal driving trajectory, and planning the backtracking track of the vehicle to obtain the backtracking track, the track of the vehicle is a planned normal track, and the planned traveling distance of the backtracking track is shorter than the normal The planned travel distance of the driving trajectory; in response to failure to plan the normal driving trajectory, changing the vehicle's driving trajectory to a fallback driving trajectory.

In a second aspect, a driving trajectory planning device is provided, the device comprising: a road information acquisition module, configured to obtain road information obtained by collecting road information; a driving trajectory planning module, configured to Plan the normal driving trajectory of the vehicle to obtain the normal driving trajectory, and plan the rolling back driving trajectory of the vehicle to obtain the rolling back driving trajectory, the driving trajectory of the vehicle is the planned normal driving trajectory, so The planned traveling distance of the backtracking trajectory is shorter than the planned traveling distance of the normal traveling trajectory; the traveling trajectory control module is configured to change the traveling trajectory of the vehicle into a retreating one in response to failure in planning the normal traveling trajectory driving track.

In a third aspect, an electronic device is provided, the device includes a memory and a processor, the memory is used to store computer instructions executable on the processor, and the processor is used to implement the present disclosure when executing the computer instructions The driving trajectory planning method described in any one of the embodiments.

In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the driving trajectory planning method described in any embodiment of the present disclosure is implemented.

The driving trajectory planning method provided by the technical solution provided by the embodiments of the present disclosure not only generates a normal driving trajectory but also generates a backtracking driving trajectory when planning a vehicle driving trajectory. When the vehicle cannot drive according to the normal trajectory, switching to the fallback trajectory greatly reduces the probability of accidents, and can be applied to the existing trajectory planning framework; wherein, the planned travel distance of the fallback trajectory is shorter than the normal one. The planned driving distance of the driving trajectory ensures the success rate and planning accuracy of planning the retreating driving trajectory. By combining the two planning methods, the safety of the vehicle under complex road conditions can be greatly improved.

Description of drawings

In order to more clearly illustrate the technical solutions in one or more embodiments of the present disclosure or related technologies, the following will briefly introduce the drawings that need to be used in the descriptions of the embodiments or related technologies. Obviously, the accompanying drawings in the following description The drawings are only some embodiments described in one or more embodiments of the present disclosure, and those skilled in the art can obtain other drawings based on these drawings without any creative effort.

Fig. 1 is a flowchart of a driving trajectory planning method shown in at least one embodiment of the present disclosure;

Fig. 2 is a flowchart of another driving trajectory planning method shown in at least one embodiment of the present disclosure;

Fig. 3 is a block diagram of a method for reversing a driving path according to at least one embodiment of the present disclosure;

Fig. 3A is a schematic diagram of a Cartesian coordinate system and a reference line coordinate system shown in at least one embodiment of the present disclosure;

Fig. 3B is a schematic diagram of another Cartesian coordinate system and a reference line coordinate system shown in at least one embodiment of the present disclosure;

Fig. 4 is a block diagram of another driving trajectory planning device shown in at least one embodiment of the present disclosure;

Fig. 5 is a schematic diagram of a hardware structure of an electronic device according to at least one embodiment of the present disclosure.

Detailed ways

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with this specification. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present specification as recited in the appended claims.

The terms used in this specification are for the purpose of describing particular embodiments only, and are not intended to limit the specification. As used in this specification and the appended claims, the singular forms "a", "the", and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It should also be understood that the term "and/or" as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

It should be understood that although the terms first, second, third, etc. may be used in this specification to describe various information, the information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this specification, first information may also be called second information, and similarly, second information may also be called first information. Depending on the context, the word "if" as used herein may be interpreted as "at" or "when" or "in response to a determination."

As shown in Figure 1, Figure 1 is a flow chart of a driving trajectory planning method shown in at least one embodiment of the present disclosure. This method can be used in the intelligent driving system of the vehicle itself, and can also be used in cloud servers or terminal devices such as mobile phones. , the vehicle may be an unmanned vehicle or a manned vehicle, and the method includes the following steps: In step 102, road information obtained by collecting road information is obtained.

The road information obtained by collecting information on the road may be information obtained by collecting information on the road by sensors on the vehicle. For example, traffic signal information, lane line information, and obstacle information such as pedestrians and other vehicles are captured by the on-board camera, and the distance between the vehicle and surrounding environmental objects is measured by on-board radar or lidar.

The road information obtained by collecting road information may also be information obtained by other devices collecting road information. For example, GPS (Global Positioning System, Global Positioning System) signal information, or pre-made high-precision map information, high-precision map information contains a lot of driving assistance information, such as intersection layout, road sign location, road speed limit and The location where the left-turn lane begins, etc.

In one example, the road information includes at least one of the following: obstacle information, traffic signal information, map information, road speed limit information, and lane line information.

In step 104, according to the road information, the normal driving trajectory of the vehicle is planned to obtain the normal driving trajectory, and the backward driving trajectory of the vehicle is planned to obtain the backward driving trajectory.

In this embodiment, the planning of the normal driving trajectory and the retreating driving trajectory are all local planning, that is, the normal driving trajectory and the retreating driving trajectory planned each time are not from the current position of the vehicle to the position of the final destination, but from the position of the vehicle For a short segment of driving trajectory starting from the current location, multiple driving trajectory planning is required in order to reach the final destination.

This embodiment does not limit the triggering condition of the driving trajectory planning, which may be at intervals, every frame of image captured by the vehicle-mounted camera, or every time the vehicle travels a certain distance. When the trigger conditions are met, it is necessary to re-plan the normal driving trajectory and the retreating driving trajectory, and update the planned normal driving trajectory and the retreating driving trajectory respectively. It should be noted that this embodiment does not limit the actual order of planning the normal driving trajectory and the backtracking driving trajectory, and the two may be performed simultaneously or successively.

When the driving trajectory of the vehicle is the planned normal driving trajectory, the vehicle can drive according to the speed and direction indicated by the normal driving trajectory, and perform operations such as changing lanes, overtaking or parking according to the instructions. The normal driving trajectory is stored after planning and stored. Update after the next planning is complete.

The planning methods adopted for planning the normal driving trajectory of the vehicle and the planning for the backtracking driving trajectory may be different, and the road information based thereon may also be different. In this solution, the planned driving distance of the backtracking trajectory is shorter than the planned driving distance of the normal driving trajectory.

Generally speaking, the planning frequency needs to be very frequent to ensure driving safety in road scenarios with a large number of traffic participants and large behavioral uncertainties. For the planning of the normal driving trajectory of the vehicle, since the planned length is relatively long, and there may be multiple paths under different decisions, in order to ensure the planning frequency, the planning accuracy will be sacrificed. For scenarios requiring high precision, in path planning This step is very likely to be impossible to plan, which will lead to planning failure, and the vehicle will get stuck or lose control if there is no basis for the driving trajectory, posing a threat to traffic safety.

In this step, planning the normal driving trajectory of the vehicle to obtain the normal driving trajectory, and planning the rolling back driving trajectory of the vehicle to obtain the rolling back driving trajectory can use commonly used planning algorithms, such as dynamic programming algorithms and optimization algorithms , lattice algorithm, etc.

When planning the backtracking track, a shorter planning distance than the normal track can be set, so that when planning the backtracking track, within a limited time, higher planning accuracy can be used, and Considering richer road information to obtain the fallback driving trajectory, while ensuring that the planning success rate is higher than that of the normal driving trajectory.

For example, the planned driving distance of the normal driving trajectory can be set to 100 meters. When planning the normal driving trajectory, it is necessary to plan a driving path of 100 meters from the current vehicle position to the destination; and the planned driving distance of the retreating driving trajectory is 20 meters. , when planning the backtracking trajectory, it is necessary to plan a 20-meter driving path from the current vehicle position to the destination.

In one example, the planned driving distance can also be influenced by setting the planned driving time. For example, the planned driving time of the normal driving trajectory can be set to 30 seconds. When planning the normal driving trajectory, it is necessary to start from the current vehicle position to the destination within 30 seconds of the vehicle's driving path; and the planned driving time of the retreating driving trajectory is 10 seconds. seconds, when planning the backtracking trajectory, it is necessary to plan the driving path of the vehicle within 10 seconds from the current vehicle position to the destination. By setting a shorter planned travel time for the fallback travel trajectory, the planned travel distance can be made shorter.

In step 106, in response to failure in planning the normal driving trajectory, the vehicle's driving trajectory is changed to a fallback driving trajectory.

The planning of the normal driving trajectory requires the planning of a longer planned driving distance, and the success rate is lower than that of the planning of the backtracking driving trajectory. When the planning of the normal driving trajectory fails, in order to prevent the driving vehicle from losing the normal driving trajectory In case of being stuck or out of control caused by the inability to continue driving after the guidance, the vehicle's driving trajectory is changed to a retreating trajectory, thereby avoiding the occurrence of dangerous accidents.

When the driving trajectory of the vehicle changes to the backward driving trajectory, the vehicle drives according to the planned backward driving trajectory. At this time, the vehicle is still planning the normal driving trajectory and the backward driving trajectory. If it still fails, the vehicle can continue to drive according to the planned backtracking trajectory.

In an example, in the case that the vehicle's driving trajectory is a regressing driving trajectory, in response to successful planning of the normal driving trajectory, the vehicle's driving trajectory is changed to a normal driving trajectory.

The driving trajectory planning method provided by the embodiments of the present disclosure not only generates a normal driving trajectory, but also generates a backtracking driving trajectory when planning the driving trajectory of a vehicle. When the vehicle cannot drive according to the normal driving track, it switches to the fallback track, which greatly reduces the probability of accidents; among them, the planned driving distance of the rollback track is shorter than the planned driving distance of the normal track, which ensures the safety of the rollback The success rate and planning accuracy of driving trajectory planning can greatly improve the safety of vehicles in complex road conditions by combining the two planning methods.

In the current technology, driving trajectory planning is roughly divided into decision-making, path planning, and speed planning. In addition to path planning failures that may be caused by high-precision scenarios, there are other reasons for planning failures. For example, the above-mentioned planning method in which path planning and speed planning are separated, although the planning speed is relatively fast, there may be situations where the two plans are incompatible. For example, only a part of dynamic obstacles (i.e., low-speed dynamic obstacles) are considered in path planning, and a feasible path is planned, but after speed planning considers all dynamic obstacles, for a certain dynamic obstacle, it is difficult to speed up and overtake. The limitation limited by vehicle acceleration cannot be completed, and the limitation of vehicle deceleration cannot be completed if the vehicle wants to slow down and avoid, so the speed planning cannot be performed for this feasible path, resulting in planning failure.

Based on this, the present disclosure provides yet another driving trajectory planning method. As shown in FIG. 2 , FIG. 2 is a flow chart of a driving trajectory planning method according to at least one embodiment of the present disclosure. The method includes the following processes, and the same steps as those in FIG. 1 are not repeated here.

In step 202, road information obtained by collecting road information is obtained.

In this embodiment, the road information includes at least obstacle information, and the obstacle information includes static obstacle information, low-speed dynamic obstacle information, and high-speed dynamic obstacle information; wherein, the low-speed dynamic obstacle information is a dynamic obstacle whose speed is less than a speed threshold The high-speed dynamic obstacle information is the information of the dynamic obstacle whose speed is not less than the speed threshold. This embodiment does not limit the setting of the speed threshold, for example, it can be set to 20km/h.

In step 204 , according to the static obstacle information, the low-speed dynamic obstacle information and the high-speed dynamic obstacle information, path planning is performed on the backtracking driving path of the vehicle to obtain at least one backtracking driving path.

When planning the normal driving path of the vehicle, the traditional planning method can still be used, that is, according to the upper-level decision-making, static obstacles and low-speed dynamic obstacles are considered to generate multiple safe and collision-free paths. In the subsequent speed planning, consider high-speed dynamic obstacles.

In the path planning of the vehicle's backtracking path, in addition to considering static obstacles and low-speed dynamic obstacles, it is also necessary to consider high-speed dynamic obstacles that only need to be considered in the speed planning of the normal driving trajectory, so as to avoid due to path planning and There may be incompatibility problems that may arise due to different obstacle information based on the speed planning separation method. That is to say, in this embodiment, the backtracking path obtained by performing path planning on the backtracking path of the vehicle includes not only spatial information but also time information, that is, the time when the vehicle arrives at some waypoints on the backtracking path Points are required.

Whether it is planning the backtracking trajectory or the normal driving trajectory, it is necessary to determine the planned driving time and planned driving distance first. According to the planned driving time and planned driving distance, it is possible to know what time range of road information to consider and how far away it is Road information within the range for planning. The planned traveling distance of the backtracking trajectory is shorter than the planned traveling distance of the normal traveling trajectory, and the planned traveling time of the retreating trajectory may also be shorter than the planned traveling time of the normal traveling trajectory.

In one example, the planned driving time and planned driving distance of the backtracking driving trajectory or the normal driving trajectory may adopt a default setting or a value set by a user.

In an example, before this step, the planned travel time and planned travel distance of the backtracking trajectory may also be determined according to the travel speed and deceleration of the vehicle.

The planned traveling time of the backward traveling track is the planned traveling time of the vehicle starting from the current vehicle position, and the planned traveling distance of the backward traveling track is the planned traveling distance of the vehicle starting from the current vehicle position. Since the backtracking trajectory is used as an emergency route, it can be planned with a large deceleration. Under the constraints of dynamics, the maximum deceleration of the vehicle is α. Assuming that the current driving speed of the vehicle is υ, the planned driving time

t=υ/α,

This is the shortest planned travel time under emergency braking, and can be calculated to get the shortest planned travel distance

The planned driving time and the planned driving distance may be determined according to the shortest planned driving time and the shortest planned driving distance, that is, the determined planned driving time and planned driving distance cannot be smaller than the shortest planned driving time and planned driving distance.

In an example, at least one movement trajectory of each dynamic obstacle within the planned driving distance within the planned driving time may be predicted according to the low-speed dynamic obstacle information and the high-speed dynamic obstacle information, and the dynamic obstacles include A low-speed dynamic obstacle and a high-speed dynamic obstacle; according to the information of the static obstacle and the trajectory of the dynamic obstacle, path planning is performed on the backtracking path of the vehicle to obtain at least one backtracking path.

In order to avoid obstacles on the driving path, it is necessary to calculate all possible positions of dynamic obstacles in the future driving planning time when planning the backtracking driving path. For example, the perception and prediction module in the intelligent driving system predicts the trajectory of each dynamic obstacle within the planned driving distance within the planned driving time in the future. Usually, the trajectory of each dynamic obstacle will have multiple , and give it to the planning module, the planning module performs path planning on the backtracking path of the vehicle according to the known static obstacle information and the trajectory of the dynamic obstacle, and obtains at least one collision-free backtracking path.

In actual implementation, the movement trajectories of illegal dynamic obstacles can be filtered out through traffic rules such as traffic lights, driving on the right, and prohibition of changing lanes across solid lines, while retaining legal trajectories. In an example, the above-mentioned shortest planned travel time t may be used to determine the position envelope formed by all legal movement trajectories of the dynamic obstacle within the time period t. It is worth noting that the longer the time period t, the greater the uncertainty of the trajectory, and the formed position envelope will expand rapidly, while the shortest planned travel time t or the planned travel time we set will be relatively short. Thus overexpansion of the envelope is prevented. In this way, the uncertainty of the behavior of the dynamic obstacle itself and the uncertainty of the prediction module can be eliminated, and the success rate and accuracy of planning the backtracking trajectory can be improved. And, we have overestimated all the legal behaviors of dynamic obstacles in the future, so that the safety of the backtracking trajectory is fully guaranteed.

The following is a detailed description of the specific process for obtaining at least one of the retreating travel paths according to the static obstacle information and the motion trajectory of the dynamic obstacle, the path planning of the vehicle's retreating travel path, as shown in FIG. 3 , including In the following steps, it should be noted that there is no restriction on the order in which the following steps and other processing steps in this embodiment are performed.

In step 302, global planning is performed according to the current position and the target position of the vehicle to obtain a global planned driving route.

When doing global planning, it is not necessary to consider obstacle information. For example, the global path planning module of the intelligent driving system can directly obtain the route from the current location to the target location according to the map information, that is, the global planning driving route.

In step 304, the centerline of the global planned driving road is extracted, and a reference line is obtained according to the centerline.

After extracting the centerline of the global planning driving road, the centerline is preprocessed, and the preprocessing includes but not limited to offset, smoothing and other processing methods. After preprocessing, use spline curves, such as cubic spline curves and quintic spline curves, to obtain reference lines. Using spline curve processing can ensure that the first-order derivatives and second-order derivatives of the reference lines are continuous and smooth.

In step 306, a reference line coordinate system is established according to the tangential direction and the normal direction of the reference line.

In order to facilitate the planning and visual display of the driving trajectory, a Frenet coordinate system, that is, a reference line coordinate system can be established for planning, or the previous Cartesian coordinate system can be converted into a reference line coordinate system. The reference line coordinate system describes the position of the vehicle relative to the road. In the Frenet coordinate system, as shown in Figure 3A, s represents the distance along the road, which is the tangential direction along the reference line, also known as the ordinate. d represents the displacement from the longitudinal line, which is the current normal direction of the reference line, also known as the abscissa. At each point of the road, the horizontal and vertical axes are vertical. The ordinate represents the driving distance on the road, and the abscissa represents the distance of the vehicle from the center line. As shown in FIG. 3A and FIG. 3B , the difference between the Cartesian coordinate system and the reference line coordinate system is shown.

In step 308, the obstacle positions of the static obstacle and the dynamic obstacle in the reference line coordinate system are determined according to the static obstacle information and the movement trajectory of the dynamic obstacle.

By converting the position information in the obstacle information from the Cartesian coordinate system to the reference line coordinate system, the position of the obstacle in the reference line coordinate system can be obtained.

In step 310, an obstacle map based on a reference line coordinate system is generated according to the planned travel distance, the obstacle location and the current location of the vehicle.

For example, a high-precision grid map can be generated according to the planned driving distance and the current position of the vehicle, and the obstacle position can be filled into the grid map to obtain an obstacle map based on the reference line coordinate system.

In step 312 , according to the obstacle map based on the reference line coordinate system, path planning is performed on the backtracking driving path of the vehicle to obtain at least one backtracking driving path.

Commonly used planning algorithms can be used, not limited to dynamic programming algorithms, optimization algorithms, lattice algorithms and other algorithms to calculate a collision-free fallback driving path that conforms to vehicle dynamics. The fallback driving path includes not only spatial information, but also time information. In order to avoid the position where the dynamic obstacle may appear at a certain future time.

In step 206, for any one of the fallback travel paths, according to the high-speed dynamic obstacle information, speed planning is performed on the speed of each path point of the vehicle on the fallback travel path to obtain the fallback Longitudinal displacement time diagram corresponding to the driving path.

During the speed planning of the backtracking path, the speed of each waypoint of the vehicle on the backtracking path can be determined. Here, the speed of each waypoint is not a single speed value, but a speed range, or a series of speeds , some waypoints of the backtracking driving path obtained in the previous step may already have speed information, and here the speed of each waypoint can be optimized such as smoothing to ensure that the vehicle runs smoothly.

For each retreat travel path, its corresponding longitudinal displacement time map can be obtained, the vertical coordinate is the longitudinal displacement, and the abscissa is time, which is used to represent the speed of each path point on each retreat travel route.

In step 208, the backward driving path and the longitudinal displacement time map corresponding to the backward driving path are fused to obtain a candidate backward driving trajectory.

Fusion of the backtracking path and the longitudinal displacement time map corresponding to the backtracking path, determining the precise speed of each path point, and obtaining candidate backtracking trajectories, each backtracking path can obtain at least one candidate backtracking trajectories.

In step 210 , according to the evaluation results of each of the candidate backtracking trajectories, the highest-evaluated candidate backtracking trajectories is selected as the backtracking trajectories.

This embodiment does not limit the evaluation method of the candidate backtracking trajectories. For example, candidates can be ranked based on at least one of deviation from the center of the lane, distance from obstacles, changes in speed and curvature, stress on the vehicle, safety, fuel consumption, and any other factor the developer wants to consider. Roll back the driving trajectory for evaluation. The highest-evaluated candidate backtracking trajectory is used as the backtracking trajectory. Of course, other candidate backtracking trajectories may not be selected as the highest-evaluated candidate backtracking trajectory.

The driving trajectory planning method provided by the embodiments of the present disclosure has a short planned driving distance when performing a backtracking driving trajectory, which can improve planning accuracy and avoid jamming caused by accuracy problems. In addition, since both dynamic and static obstacles are considered during path planning, the stuck problem caused by the inconsistency caused by the separation of path planning and speed planning can be avoided.

As shown in FIG. 4, FIG. 4 is a block diagram of a driving trajectory planning device shown in at least one embodiment of the present disclosure, and the device includes:

The road information acquisition module 41 is used to obtain the road information obtained by collecting information on the road; the driving trajectory planning module 42 is used to plan the normal driving trajectory of the vehicle according to the road information to obtain the normal driving trajectory, and planning the backtracking track of the vehicle to obtain the backtracking track, the track of the vehicle is a planned normal track, and the planned traveling distance of the backtracking track is shorter than the normal track The planned traveling distance of the trajectory; the traveling trajectory control module 43, configured to change the traveling trajectory of the vehicle into a backward traveling trajectory in response to failure in planning the normal traveling trajectory.

In an example, the driving track control module 43 is further configured to: in the case that the driving track of the vehicle is a regressive driving track, in response to successful planning of the normal driving track, adjust the driving track of the vehicle to The track changes to the normal driving track.

In one example, the road information includes at least obstacle information, and the obstacle information includes static obstacle information, low-speed dynamic obstacle information, and high-speed dynamic obstacle information; wherein, the low-speed dynamic obstacle information is a speed less than The information of the dynamic obstacle of the speed threshold, the high-speed dynamic obstacle information is the information of the dynamic obstacle whose speed is not less than the speed threshold; the driving trajectory planning module 42 is used for When planning the backward driving trajectory of the vehicle, when the backward driving trajectory is obtained, it is specifically used to: according to the static obstacle information, low-speed dynamic obstacle information and high-speed dynamic obstacle information, route the vehicle's backward driving path planning to obtain at least one of the backtracking travel paths; for any one of the backtracking travel paths, according to the high-speed dynamic obstacle information, the speed of each way point of the vehicle on the backtracking travel path is calculated. Planning to obtain the longitudinal displacement time map corresponding to the retreating travel path; fusing the retreating travel route and the longitudinal displacement time map corresponding to the retreating travel path to obtain candidate retreating travel trajectories; according to the As for the evaluation results of the candidate backtracking trajectories, the highest evaluated candidate backtracking trajectories are selected as the backtracking trajectories.

In one example, the driving trajectory planning module 42 is further configured to: perform path planning on the vehicle's backtracking path according to the static obstacle information, low-speed dynamic obstacle information, and high-speed dynamic obstacle information , before obtaining at least one of the reversing travel paths, according to the driving speed and deceleration of the vehicle, determine the planned travel time and the planned travel distance of the reversing travel trajectory.

In one example, the driving trajectory planning module 42 is used to perform path planning on the retreating driving path of the vehicle according to the static obstacle information, low-speed dynamic obstacle information and high-speed dynamic obstacle information, and obtain When at least one of the fallback driving paths is used, it is specifically used to: predict at least one dynamic obstacle within the planned driving distance within the planned driving time according to the low-speed dynamic obstacle information and the high-speed dynamic obstacle information. A motion trajectory, the dynamic obstacles include low-speed dynamic obstacles and high-speed dynamic obstacles; according to the static obstacle information and the motion trajectory of the dynamic obstacles, the path planning is performed on the vehicle's backtracking path, and at least A reversing travel path.

In one example, the driving trajectory planning module 42 is used to perform path planning on the retreating driving path of the vehicle according to the static obstacle information and the moving trajectory of the dynamic obstacle, and obtain at least one The fallback driving path is specifically used for: performing global planning according to the current position and the target position of the vehicle to obtain a globally planned driving road; extracting the center line of the globally planned driving road, and obtaining a reference line according to the center line; The tangential direction and the normal direction of the reference line are used to establish a reference line coordinate system; according to the information of the static obstacle and the movement track of the dynamic obstacle, it is determined where the static obstacle and the dynamic obstacle are located. The obstacle position in the reference line coordinate system; according to the planned driving distance, the obstacle position and the current position of the vehicle, generate an obstacle map based on the reference line coordinate system; according to the reference line coordinate system based Obstacle map, performing path planning on the backtracking path of the vehicle to obtain at least one backtracking path.

In an example, the road information includes at least one of the following: obstacle information, traffic signal information, map information, road speed limit information, and lane line information.

For the implementation process of the functions and effects of each module in the above-mentioned device, please refer to the implementation process of the corresponding steps in the above-mentioned method for details, and details will not be repeated here.

An embodiment of the present disclosure also provides an electronic device. As shown in FIG. The device 52 is configured to implement the driving trajectory planning method described in any embodiment of the present disclosure when executing the computer instructions.

An embodiment of the present disclosure further provides a computer program product, which includes a computer program/instruction, and when the computer program/instruction is executed by a processor, implements the driving trajectory planning method described in any embodiment of the present disclosure.

An embodiment of the present disclosure also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the driving trajectory planning method described in any embodiment of the present disclosure is implemented.

As for the device embodiment, since it basically corresponds to the method embodiment, please refer to the part description of the method embodiment for relevant parts. The device embodiments described above are only illustrative, and the modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in One place, or it can be distributed to multiple network modules. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution in this specification. It can be understood and implemented by those skilled in the art without creative effort.

The foregoing describes specific embodiments of this specification. Other implementations are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. Multitasking and parallel processing are also possible or may be advantageous in certain embodiments.

Other embodiments of the description will readily occur to those skilled in the art from consideration of the specification and practice of the invention claimed herein. This description is intended to cover any modification, use or adaptation of this description. These modifications, uses or adaptations follow the general principles of this description and include common knowledge or conventional technical means in this technical field for which this description does not apply . The specification and examples are to be considered exemplary only, with a true scope and spirit of the specification being indicated by the following claims.

It should be understood that this specification is not limited to the precise constructions which have been described above and shown in the accompanying drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the specification is limited only by the appended claims.

The above descriptions are only preferred embodiments of this specification, and are not intended to limit this specification. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of this specification shall be included in this specification. within the scope of protection.

Claims

A driving trajectory planning method, comprising:

Obtain road information obtained by collecting road information;

According to the road information, the normal driving trajectory of the vehicle is planned to obtain the normal driving trajectory, and the backward driving trajectory of the vehicle is planned to obtain the backward driving trajectory. The driving trajectory of the vehicle is A planned normal driving trajectory, the planned driving distance of the fallback driving trajectory is shorter than the planned driving distance of the normal driving trajectory;

In response to failure in planning the normal driving trajectory, changing the vehicle's driving trajectory to a fallback driving trajectory.
The method according to claim 1, further comprising:

In the case that the vehicle's driving trajectory is a regressing driving trajectory, in response to the successful planning of the normal driving trajectory, the vehicle's driving trajectory is changed to a normal driving trajectory.
The method according to claim 1, wherein the road information includes at least obstacle information, and the obstacle information includes static obstacle information, low-speed dynamic obstacle information and high-speed dynamic obstacle information; wherein, the The low-speed dynamic obstacle information is the information of the dynamic obstacle whose speed is less than the speed threshold, and the high-speed dynamic obstacle information is the information of the dynamic obstacle whose speed is not less than the speed threshold;

According to the road information, planning the backtracking trajectory of the vehicle to obtain the backtracking trajectory includes:

performing path planning on the retreating travel path of the vehicle according to the static obstacle information, the low-speed dynamic obstacle information and the high-speed dynamic obstacle information, to obtain at least one of the retreating travel paths;

For any of the fallback travel paths, according to the high-speed dynamic obstacle information, perform speed planning on the speed of each path point of the vehicle on the fallback travel path, and obtain the longitudinal direction corresponding to the fallback travel path Displacement Time Diagram;

fusing the backtracking travel path and the longitudinal displacement time map corresponding to the backtracking travel path to obtain candidate backtracking travel trajectories;

According to the evaluation results of each of the candidate backtracking trajectories, the highest evaluated candidate backtracking trajectories are selected as the backtracking trajectories.
The method according to claim 3, characterized in that, according to the static obstacle information, low-speed dynamic obstacle information and high-speed dynamic obstacle information, path planning is performed on the vehicle's backtracking path to obtain at least one Before the backtracking travel path, the method also includes:

According to the traveling speed and deceleration of the vehicle, the planned traveling time and planned traveling distance of the backtracking traveling track are determined.
The method according to claim 4, characterized in that, according to the static obstacle information, low-speed dynamic obstacle information and high-speed dynamic obstacle information, path planning is performed on the vehicle's backtracking path to obtain at least one Describe the fallback travel path, including:

Predict at least one movement trajectory of each dynamic obstacle within the planned driving distance within the planned driving time according to the low-speed dynamic obstacle information and the high-speed dynamic obstacle information, the dynamic obstacles include low-speed dynamic obstacles and high-speed dynamic obstacles;

According to the static obstacle information and the movement trajectory of the dynamic obstacle, path planning is performed on the backtracking path of the vehicle to obtain at least one backtracking path.
The method according to claim 5, characterized in that, according to the information of the static obstacle and the trajectory of the dynamic obstacle, path planning is performed on the backtracking path of the vehicle to obtain at least one of the backtracking Driving route, including:

Carrying out global planning according to the current position and the target position of the vehicle to obtain the globally planned driving route;

Extracting the center line of the global planning driving road, and obtaining a reference line according to the center line;

Establishing a reference line coordinate system according to the tangential direction and the normal direction of the reference line;

determining obstacle positions of the static obstacle and the dynamic obstacle in the reference line coordinate system according to the static obstacle information and the movement track of the dynamic obstacle;

generating an obstacle map based on a reference line coordinate system according to the planned driving distance, the obstacle position, and the current position of the vehicle;

According to the obstacle map based on the reference line coordinate system, path planning is performed on the backtracking path of the vehicle to obtain at least one backtracking path.
The method according to any one of claims 1 to 6, wherein the road information includes at least one of the following: obstacle information, traffic signal information, map information, road speed limit information and lane line information.
A driving trajectory planning device, comprising:

A road information acquisition module, configured to acquire road information obtained by collecting road information;

a driving trajectory planning module, configured to plan the normal driving trajectory of the vehicle according to the road information to obtain the normal driving trajectory, and plan the backward driving trajectory of the vehicle to obtain the backward driving trajectory, The driving trajectory of the vehicle is a planned normal driving trajectory, and the planned driving distance of the backtracking driving trajectory is shorter than the planned driving distance of the normal driving trajectory;

A driving trajectory control module, configured to change the vehicle's driving trajectory into a fallback driving trajectory in response to failure to plan the normal driving trajectory.
An electronic device comprising:

memory for storing computer instructions executable on the processor; and

A processor configured to implement the method of any one of claims 1 to 7 when executing the computer instructions.
A computer-readable storage medium, on which a computer program is stored, wherein, when the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.