Track planning method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a trajectory planning method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring an environment perception result and map data, and generating a plurality of initial tracks of a vehicle; for each initial track, acquiring a first driving parameter of the vehicle at each moment included in the initial track data, and for any surrounding vehicle, acquiring a second driving parameter of the surrounding vehicle at each moment and a third driving parameter of a target vehicle corresponding to the surrounding vehicle at each moment from an environment sensing result; according to the first driving parameter, the second driving parameter and the third driving parameter, determining each predicted trajectory of the surrounding vehicle under the influence of the initial trajectory based on a preset motion model; and screening each initial trajectory based on each corresponding predicted trajectory to obtain a screened trajectory, and determining a final trajectory in each screened trajectory based on a preset sorting rule. By applying the scheme provided by the embodiment of the invention, the accuracy of trajectory planning can be improved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a trajectory planning method, device, electronic device and storage medium. Background Art

[0002] In autonomous driving technology, when an autonomous driving vehicle is driving on the road, the sensors installed on the vehicle can collect relevant data, such as the camera can capture images of the vehicle's surrounding environment, and lidar (radar) can collect point cloud data around the vehicle. In addition, in the perception link, the perception algorithm can perform target recognition based on the environmental image and point cloud data to obtain target recognition results; in the regulation and control link, the regulation and control algorithm can perform trajectory planning based on the target recognition results to obtain trajectory planning results.

[0003] The known trajectory planning methods only consider the environmental perception results at the current moment. However, in the actual driving process of the autonomous vehicle, the future movement trajectories of other vehicles may also affect the trajectory planning of the autonomous vehicle. In other words, only considering the environmental perception results at the current moment for the trajectory planning of the autonomous vehicle may lead to low accuracy of the trajectory planning results. Therefore, how to improve the accuracy of trajectory planning has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] The present invention provides a trajectory planning method, device, electronic device and storage medium to improve the accuracy of trajectory planning. The specific technical solution is as follows.

[0005] In a first aspect, an embodiment of the present invention provides a trajectory planning method, the method comprising:

[0006] Acquire environmental perception results and map data, and generate multiple initial trajectories of the vehicle based on the environmental perception results and the map data;

[0007] For each of the initial trajectories, a first driving parameter of the vehicle at each moment included in the initial trajectory data is obtained; for any surrounding vehicle, a second driving parameter of the surrounding vehicle at each moment is obtained from the environmental perception result, as well as a third driving parameter of the surrounding vehicle corresponding to the target vehicle at each moment; and according to the first driving parameter, the second driving parameter, and the third driving parameter, based on a preset motion model, each predicted trajectory of the surrounding vehicle under the influence of the initial trajectory is determined;

[0008] Based on the corresponding predicted trajectories, each of the initial trajectories is screened to obtain screened trajectories, and based on a preset sorting rule, a final trajectory is determined from the screened trajectories.

[0009] In an embodiment of the present application, after generating multiple initial trajectories of the ego vehicle based on the environmental perception results and the map data, for each initial trajectory, the predicted trajectory of each surrounding vehicle under the influence of the initial trajectory can be determined. Furthermore, the initial trajectory can be screened based on each predicted trajectory. That is to say, when determining the trajectory of the ego vehicle, not only the environmental perception results at the current moment are considered, but also the influence of the future movement trajectories of other vehicles on the trajectory planning of the ego vehicle is considered. Therefore, the accuracy of the trajectory planning of the ego vehicle can be improved.

[0010] Optionally, the step of determining, according to the first driving parameter, the second driving parameter, and the third driving parameter and based on a preset motion model, each predicted trajectory of the surrounding vehicle under the influence of the initial trajectory comprises:

[0011] According to the first driving parameter, the second driving parameter, and the third driving parameter, determining the acceleration information of the surrounding vehicle based on the longitudinal motion model, and determining the lane change decision of the surrounding vehicle based on the lateral motion model;

[0012] The predicted trajectories of the surrounding vehicles are constructed according to the acceleration information and the lane change decision.

[0013] Optionally, the step of filtering each of the initial trajectories based on the corresponding predicted trajectories to obtain a filtered trajectory includes:

[0014] For each of the initial trajectories, determining whether the initial trajectory satisfies the following conditions at the same time: a preset safety constraint, a preset kinematic constraint, a preset traffic regulation restriction, and no intersection with the corresponding predicted trajectories;

[0015] If yes, the initial trajectory is taken as the post-screening trajectory.

[0016] Optionally, the step of determining a final trajectory from the filtered trajectories based on a preset sorting rule includes:

[0017] Calculate the score of each filtered trajectory based on the ego vehicle speed and acceleration change rate included in each filtered trajectory;

[0018] The screening trajectory with the highest score is taken as the final trajectory.

[0019] Optionally, the step of calculating the score of each filtered trajectory based on the vehicle speed and acceleration change rate included in each filtered trajectory includes:

[0020] For any post-screening trajectory, the score s of the post-screening trajectory is calculated according to the following formula:

[0021]

[0022] Where t represents time, T represents the time length of the filtered trajectory, jerk(t) represents the acceleration change rate at time t, jerk upper bound represents the upper bound of the pre-set jerk, and v ref represents the driver set speed, v lon (t) represents the vehicle speed at time t.

[0023] In a second aspect, an embodiment of the present application provides a trajectory planning device, the device comprising:

[0024] A data acquisition module, used to acquire environmental perception results and map data, and generate multiple initial trajectories of the vehicle based on the environmental perception results and the map data;

[0025] a trajectory planning module, for obtaining, for each of the initial trajectories, a first driving parameter of the vehicle at each moment included in the initial trajectory data, and for any surrounding vehicle, obtaining, from the environmental perception result, a second driving parameter of the surrounding vehicle at each moment, and a third driving parameter of the surrounding vehicle corresponding to the target vehicle at each moment, and determining, based on a preset motion model and according to the first driving parameter, the second driving parameter, and the third driving parameter, each predicted trajectory of the surrounding vehicle under the influence of the initial trajectory;

[0026] The trajectory screening module is used to screen each of the initial trajectories based on the corresponding predicted trajectories to obtain screened trajectories, and determine a final trajectory from each of the screened trajectories based on a preset sorting rule.

[0027] Optionally, the trajectory planning module is specifically used to:

[0028] According to the first driving parameter, the second driving parameter, and the third driving parameter, determining the acceleration information of the surrounding vehicle based on the longitudinal motion model, and determining the lane change decision of the surrounding vehicle based on the lateral motion model;

[0029] The predicted trajectories of the surrounding vehicles are constructed according to the acceleration information and the lane change decision.

[0030] Optionally, the trajectory screening module is specifically used to:

[0031] For each of the initial trajectories, determining whether the initial trajectory satisfies the following conditions at the same time: a preset safety constraint, a preset kinematic constraint, a preset traffic regulation restriction, and no intersection with the corresponding predicted trajectories;

[0032] If yes, the initial trajectory is taken as the post-screening trajectory.

[0033] Optionally, the trajectory screening module includes:

[0034] A score calculation submodule, for calculating the score of each filtered trajectory based on the ego vehicle speed and acceleration change rate included in each filtered trajectory;

[0035] The trajectory determination submodule is used to select the filtered trajectory with the highest score as the final trajectory.

[0036] Optionally, the score calculation submodule is specifically used to:

[0037] For any post-screening trajectory, the score s of the post-screening trajectory is calculated according to the following formula:

[0038]

[0039] Where t represents time, T represents the time length of the filtered trajectory, jerk(t) represents the acceleration change rate at time t, jerk upper bound represents the upper bound of the pre-set jerk, and v ref represents the driver set speed, v lon (t) represents the vehicle speed at time t.

[0040] In a third aspect, an embodiment of the present invention provides an electronic device, including: a memory and a processor, wherein the memory and the processor are coupled;

[0041] The memory is used to store one or more computer instructions;

[0042] The processor is used to execute the one or more computer instructions to implement the trajectory planning method as described in the first aspect above.

[0043] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having one or more computer instructions stored thereon, which are executed by a processor to implement the trajectory planning method as described in the first aspect above.

[0044] In a fifth aspect, the present application provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the trajectory planning method described in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative work.

[0046] Figure 1A schematic diagram of a flow chart of a trajectory planning method provided by an embodiment of the present invention;

[0047] Figure 2 A schematic diagram of the structure of a trajectory planning device provided by an embodiment of the present invention;

[0048] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] It should be noted that the terms "including" and "having" and any variations thereof in the embodiments of the present invention and the accompanying drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.

[0051] The embodiments of the present invention disclose a trajectory planning method, device, electronic device and storage medium, which can improve the accuracy of trajectory planning. The embodiments of the present invention are described in detail below.

[0052] Figure 1 A flow chart of a trajectory planning method provided by an embodiment of the present invention. The method can be applied to an autonomous driving vehicle, and specifically, can be applied to a controller of an autonomous driving vehicle. The method specifically includes the following steps.

[0053] S110: Obtaining environmental perception results and map data, and generating multiple initial trajectories of the vehicle based on the environmental perception results and the map data.

[0054] During the driving process of an autonomous vehicle, various types of sensors installed on the vehicle can collect relevant data, such as cameras that can capture images of the vehicle's surroundings, and lidar (radar) that can collect point cloud data around the vehicle. In addition, in the perception phase, the perception algorithm can perform target recognition based on the environmental image and point cloud data, respectively, to obtain target recognition results, which can also be called environmental perception results. Specifically, the environmental perception results may include relevant information about other vehicles around the vehicle, such as current location, speed, acceleration, and other information.

[0055] After obtaining the environmental perception results, the autonomous driving vehicle can generate multiple initial trajectories based on the environmental perception results and map data. For example, all paths that meet the conditions can be determined based on the map data, relevant information about surrounding vehicles, and the starting point and end point of the vehicle, and all of them are used as the initial trajectory of the vehicle. Each initial trajectory can include all the driving parameters of the vehicle at each moment, such as position, speed, acceleration and other information.

[0056] S120: For each initial trajectory, obtain the first driving parameter of the vehicle at each moment included in the initial trajectory data; for any surrounding vehicle, obtain the second driving parameter of the surrounding vehicle at each moment from the environmental perception result, and the third driving parameter of the surrounding vehicle corresponding to the target vehicle at each moment; and determine the predicted trajectories of the surrounding vehicle under the influence of the initial trajectory based on the preset motion model according to the first driving parameter, the second driving parameter, and the third driving parameter.

[0057] It is understandable that when a vehicle is driving on the road, the driving conditions of any vehicle and its surrounding vehicles affect each other. For example, when the self-vehicle plans to change lanes at the next moment, but the vehicle in front of it in the target lane suddenly slows down, in this case, if the self-vehicle continues to change lanes, it may cause a traffic accident. Therefore, when the self-vehicle is planning its path, if it can fully consider the path planning of surrounding vehicles, it can maximize the accuracy of its path planning, thereby improving the safety of the driving process.

[0058] In the embodiment of the present application, after determining multiple initial trajectories of the self-driving vehicle, the self-driving vehicle can further determine the planned trajectories of the surrounding vehicles under the influence of the initial trajectory of the self-driving vehicle, which can be called predicted trajectories. In other words, it can be determined that when the self-driving vehicle drives according to any initial trajectory at the next moment, the corresponding driving trajectories of other vehicles can be determined. It can be understood that for different initial trajectories of the self-driving vehicle, the corresponding predicted trajectories of the surrounding vehicles are generally different.

[0059] Specifically, the vehicle can determine the predicted trajectories corresponding to each surrounding vehicle for each initial trajectory in turn. For example, the vehicle can obtain the first driving parameter of the vehicle at each moment included in the initial trajectory data for each initial trajectory, obtain the second driving parameter of the surrounding vehicle at each moment from the environmental perception result for any surrounding vehicle, and the third driving parameter of the surrounding vehicle corresponding to the target vehicle at each moment, and determine the predicted trajectories of the surrounding vehicle under the influence of the initial trajectory based on the first driving parameter, the second driving parameter, and the third driving parameter and the preset motion model.

[0060] Among them, the above-mentioned surrounding vehicles may include all vehicles that may have an impact on the driving of the vehicle, which are selected according to preset selection rules with the vehicle as the center. For example, it can be the two vehicles in front and behind the vehicle in the lane where the vehicle is currently located, and the two vehicles closest to the vehicle in the adjacent lanes of the lane where the vehicle is currently located, that is, a total of six vehicles. Alternatively, it can be determined according to other rules, which is all possible, and the embodiments of the present application do not make specific limitations on this. Similarly, the target vehicle corresponding to the surrounding vehicles can also be determined according to the same rules, and the embodiments of the present application do not limit its specific selection rules.

[0061] That is to say, in the embodiment of the present application, the predicted trajectory of the surrounding vehicle can be determined based on the driving parameters of the vehicle itself, the driving parameters of any surrounding vehicle itself, and the driving parameters of the target vehicle corresponding to the surrounding vehicle.

[0062] In one implementation, the vehicle can, for any surrounding vehicle, first determine the acceleration information of the surrounding vehicle based on the longitudinal motion model according to the first driving parameter, the second driving parameter, and the third driving parameter, and determine the lane change decision of the surrounding vehicle based on the lateral motion model; and then construct each predicted trajectory of the surrounding vehicle according to the acceleration information and the lane change decision.

[0063] The longitudinal motion model may include, for example, IDM (Intelligent Driver Model). This model can perform longitudinal modeling on surrounding vehicles to obtain corresponding acceleration information. The lateral motion model may include MOBIL (Minimizing Overall Braking Induced by Lane changes, i.e., a model that determines when to change lanes based on minimizing the number of braking times when changing lanes) to obtain corresponding lane change decisions, i.e., output decisions on whether surrounding vehicles should change lanes.

[0064] S130: Based on the corresponding predicted trajectories, each initial trajectory is screened to obtain screened trajectories, and based on a preset sorting rule, a final trajectory is determined from the screened trajectories.

[0065] Determine the predicted trajectories of the surrounding vehicles, and each predicted trajectory will in turn impose certain constraints on the initial trajectory. Therefore, in an embodiment of the present application, each initial trajectory can be screened based on the corresponding predicted trajectories. For example, for each initial trajectory, it can be determined whether the initial trajectory satisfies the following conditions at the same time: preset safety constraints, preset kinematic constraints, preset traffic regulations restrictions, and no intersections with the corresponding predicted trajectories; if so, the initial trajectory is used as the screened trajectory.

[0066] There may be multiple filtered trajectories. In this case, the multiple filtered trajectories can be sorted to determine a final trajectory. For example, the scores of each filtered trajectory can be calculated based on the vehicle speed and acceleration change rate included in each filtered trajectory; the filtered trajectory with the highest score is used as the final trajectory.

[0067] It is understandable that the vehicle speed and acceleration rate may directly affect the riding experience. For example, if the acceleration rate is too large, that is, there will be a rapid acceleration or deceleration process, which will lead to a poor riding experience. Therefore, by sorting the filtered trajectories based on speed and acceleration rate, the final trajectory with better user experience can be selected.

[0068] Specifically, for any filtered trajectory, the score s of the filtered trajectory can be calculated according to the following formula:

[0069]

[0070] Where t represents time, T represents the time length of the filtered trajectory, jerk(t) represents the acceleration change rate at time t, jerk upper bound represents the upper bound of the pre-set jerk, and v ref represents the driver set speed, v lon (t) represents the vehicle speed at time t.

[0071] In an embodiment of the present application, after generating multiple initial trajectories of the ego vehicle based on the environmental perception results and the map data, for each initial trajectory, the predicted trajectory of each surrounding vehicle under the influence of the initial trajectory can be determined. Furthermore, the initial trajectory can be screened based on each predicted trajectory. That is to say, when determining the trajectory of the ego vehicle, not only the environmental perception results at the current moment are considered, but also the influence of the future movement trajectories of other vehicles on the trajectory planning of the ego vehicle is considered. Therefore, the accuracy of the trajectory planning of the ego vehicle can be improved.

[0072] Figure 2 A schematic diagram of the structure of a trajectory planning device provided in an embodiment of the present application, the device comprising:

[0073] A data acquisition module 210, configured to acquire environmental perception results and map data, and generate a plurality of initial trajectories of the vehicle based on the environmental perception results and the map data;

[0074] The trajectory planning module 220 is used to obtain, for each of the initial trajectories, a first driving parameter of the vehicle at each moment included in the initial trajectory data, and for any surrounding vehicle, obtain, from the environmental perception result, a second driving parameter of the surrounding vehicle at each moment, and a third driving parameter of the surrounding vehicle corresponding to the target vehicle at each moment, and determine, based on the first driving parameter, the second driving parameter, and the third driving parameter, each predicted trajectory of the surrounding vehicle under the influence of the initial trajectory based on a preset motion model;

[0075] The trajectory screening module 230 is used to screen each of the initial trajectories based on the corresponding predicted trajectories to obtain screened trajectories, and determine a final trajectory from the screened trajectories based on a preset sorting rule.

[0076] Optionally, the trajectory planning module 220 is specifically used to:

[0077] According to the first driving parameter, the second driving parameter, and the third driving parameter, determining the acceleration information of the surrounding vehicle based on the longitudinal motion model, and determining the lane change decision of the surrounding vehicle based on the lateral motion model;

[0078] The predicted trajectories of the surrounding vehicles are constructed according to the acceleration information and the lane change decision.

[0079] Optionally, the trajectory screening module 230 is specifically used to:

[0080] For each of the initial trajectories, determining whether the initial trajectory satisfies the following conditions at the same time: a preset safety constraint, a preset kinematic constraint, a preset traffic regulation restriction, and no intersection with the corresponding predicted trajectories;

[0081] If yes, the initial trajectory is taken as the post-screening trajectory.

[0082] Optionally, the trajectory screening module 230 includes:

[0083] A score calculation submodule, for calculating the score of each filtered trajectory based on the ego vehicle speed and acceleration change rate included in each filtered trajectory;

[0084] The trajectory determination submodule is used to select the filtered trajectory with the highest score as the final trajectory.

[0085] Optionally, the score calculation submodule is specifically used to:

[0086] For any post-screening trajectory, the score s of the post-screening trajectory is calculated according to the following formula:

[0087]

[0088] Where t represents time, T represents the time length of the filtered trajectory, jerk(t) represents the acceleration change rate at time t, jerk upper bound represents the upper bound of the pre-set jerk, and v ref represents the driver set speed, v lon (t) represents the vehicle speed at time t.

[0089] In an embodiment of the present application, after generating multiple initial trajectories of the ego vehicle based on the environmental perception results and the map data, for each initial trajectory, the predicted trajectory of each surrounding vehicle under the influence of the initial trajectory can be determined. Furthermore, the initial trajectory can be screened based on each predicted trajectory. That is to say, when determining the trajectory of the ego vehicle, not only the environmental perception results at the current moment are considered, but also the influence of the future movement trajectories of other vehicles on the trajectory planning of the ego vehicle is considered. Therefore, the accuracy of the trajectory planning of the ego vehicle can be improved.

[0090] The above device embodiment corresponds to the method embodiment and has the same technical effect as the method embodiment. For specific description, please refer to the method embodiment. The device embodiment is obtained based on the method embodiment. For specific description, please refer to the method embodiment part, which will not be repeated here.

[0091] Next, an electronic device provided by an embodiment of the present application is introduced. Figure 3 , Figure 3 A schematic diagram of a structure of a server provided in an embodiment of the present application, the server comprising:

[0092] one or more processors 40;

[0093] The processor 40 is coupled to a storage device 41, and the storage device 41 is used to store one or more programs.

[0094] When the one or more programs are executed by the one or more processors 40, the electronic device implements the following Figure 1 A technical solution of the trajectory planning method.

[0095] The present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the following is achieved: Figure 1 The trajectory planning method described.

[0096] The present application provides a computer program product, the computer program product comprising a computer program, the computer program when executed by a processor to achieve the following Figure 1 The trajectory planning method described.

[0097] Those skilled in the art can understand that the accompanying drawings are only schematic diagrams of an embodiment, and the modules or processes in the accompanying drawings are not necessarily required to implement the present invention.

[0098] Those skilled in the art can understand that the modules in the device in the embodiment can be distributed in the device in the embodiment according to the description of the embodiment, or can be changed accordingly and located in one or more devices different from the embodiment. The modules in the above embodiment can be combined into one module, or can be further divided into multiple sub-modules.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A trajectory planning method, characterized in that: The method comprises: Acquire environmental perception results and map data, and generate multiple initial trajectories of the vehicle based on the environmental perception results and the map data; For each of the initial trajectories, a first driving parameter of the vehicle at each moment included in the initial trajectory data is obtained; for any surrounding vehicle, a second driving parameter of the surrounding vehicle at each moment is obtained from the environmental perception result, as well as a third driving parameter of the surrounding vehicle corresponding to the target vehicle at each moment; and according to the first driving parameter, the second driving parameter, and the third driving parameter, based on a preset motion model, each predicted trajectory of the surrounding vehicle under the influence of the initial trajectory is determined; Based on the corresponding predicted trajectories, each of the initial trajectories is screened to obtain screened trajectories, and based on a preset sorting rule, a final trajectory is determined from the screened trajectories.

2. The method according to claim 1, characterized in that The step of determining the predicted trajectories of the surrounding vehicles under the influence of the initial trajectory based on the preset motion model according to the first driving parameter, the second driving parameter, and the third driving parameter comprises: According to the first driving parameter, the second driving parameter, and the third driving parameter, determining the acceleration information of the surrounding vehicle based on the longitudinal motion model, and determining the lane change decision of the surrounding vehicle based on the lateral motion model; The predicted trajectories of the surrounding vehicles are constructed according to the acceleration information and the lane change decision.

3. The method according to claim 1, characterized in that: The step of screening each of the initial trajectories based on the corresponding predicted trajectories to obtain a screened trajectory comprises: For each of the initial trajectories, determining whether the initial trajectory satisfies the following conditions at the same time: a preset safety constraint, a preset kinematic constraint, a preset traffic regulation restriction, and no intersection with the corresponding predicted trajectories; If yes, the initial trajectory is taken as the post-screening trajectory.

4. The method according to any one of claims 1 to 3, characterized in that: The step of determining a final track from the screened tracks based on a preset sorting rule comprises: Calculate the score of each filtered trajectory based on the ego vehicle speed and acceleration change rate included in each filtered trajectory; The screening trajectory with the highest score is taken as the final trajectory.

5. The method according to claim 4, characterized in that The step of calculating the score of each filtered trajectory based on the vehicle speed and acceleration change rate included in each filtered trajectory includes: For any post-screening trajectory, the score s of the post-screening trajectory is calculated according to the following formula: Where t represents time, T represents the time length of the filtered trajectory, jerk(t) represents the acceleration change rate at time t, jerkupperbound represents the upper bound of the pre-set jerk, and v ref represents the driver set speed, v lon (t) represents the vehicle speed at time t.

6. A trajectory planning device, characterized in that: The device comprises: A data acquisition module, used to acquire environmental perception results and map data, and generate multiple initial trajectories of the vehicle based on the environmental perception results and the map data; a trajectory planning module, for obtaining, for each of the initial trajectories, a first driving parameter of the vehicle at each moment included in the initial trajectory data, and for any surrounding vehicle, obtaining, from the environmental perception result, a second driving parameter of the surrounding vehicle at each moment, and a third driving parameter of the surrounding vehicle corresponding to the target vehicle at each moment, and determining, based on a preset motion model and according to the first driving parameter, the second driving parameter, and the third driving parameter, each predicted trajectory of the surrounding vehicle under the influence of the initial trajectory; The trajectory screening module is used to screen each of the initial trajectories based on the corresponding predicted trajectories to obtain screened trajectories, and determine a final trajectory from each of the screened trajectories based on a preset sorting rule.

7. The device according to claim 6, characterized in that The trajectory planning module is specifically used for: According to the first driving parameter, the second driving parameter, and the third driving parameter, determining the acceleration information of the surrounding vehicle based on the longitudinal motion model, and determining the lane change decision of the surrounding vehicle based on the lateral motion model; The predicted trajectories of the surrounding vehicles are constructed according to the acceleration information and the lane change decision.

8. The device according to claim 6, characterized in that The trajectory screening module is specifically used for: For each of the initial trajectories, determining whether the initial trajectory satisfies the following conditions at the same time: a preset safety constraint, a preset kinematic constraint, a preset traffic regulation restriction, and no intersection with the corresponding predicted trajectories; If yes, the initial trajectory is taken as the post-screening trajectory.

9. The device according to any one of claims 6 to 8, characterized in that: The trajectory screening module comprises: A score calculation submodule, for calculating the score of each filtered trajectory based on the ego vehicle speed and acceleration change rate included in each filtered trajectory; The trajectory determination submodule is used to select the filtered trajectory with the highest score as the final trajectory.

10. The device according to claim 9, characterized in that The score calculation submodule is specifically used for: For any post-screening trajectory, the score s of the post-screening trajectory is calculated according to the following formula: Where t represents time, T represents the time length of the filtered trajectory, jerk(t) represents the acceleration change rate at time t, jerkupperbound represents the upper bound of the pre-set jerk, and v ref represents the driver set speed, v lon (t) represents the vehicle speed at time t.

11. An electronic device, characterized in that: include: A memory and a processor, wherein the memory and the processor are coupled; The memory is used to store one or more computer instructions; The processor is used to execute the one or more computer instructions to implement the trajectory planning method as described in any one of claims 1 to 5.

12. A computer-readable storage medium having one or more computer instructions stored thereon, characterized in that: The instruction is executed by a processor to implement the trajectory planning method as described in any one of claims 1 to 5.

Images