Vehicle trajectory planning method, device, equipment, medium and product

Abstract

This application discloses a vehicle trajectory planning method, apparatus, device, medium, and product, belonging to the field of autonomous driving technology. The method includes: acquiring a set of future trajectories for a target vehicle; determining the target predicted driving trajectory corresponding to each drivable trajectory in the future trajectory set for surrounding vehicles based on the future trajectory set, the historical trajectories of surrounding vehicles, and current traffic environment information; wherein the target predicted driving trajectory is obtained by adjusting the initial predicted driving trajectories of surrounding vehicles based on the drivable trajectories; the initial predicted driving trajectory is obtained based on historical trajectories and current traffic environment information; determining the target score of the drivable trajectory based on the drivable trajectories and the target predicted driving trajectories corresponding to the drivable trajectories of surrounding vehicles, and outputting the drivable trajectory with the highest target score in the future trajectory set. This application can improve the autonomy and flexibility of trajectory planning for the target vehicle, and also improve the traffic efficiency of the target vehicle.

Description

Technical Field

[0001] This application belongs to the field of autonomous driving technology, and in particular relates to a vehicle driving trajectory planning method, device, equipment, medium and product. Background Technology

[0002] With the development of autonomous driving technology, more and more vehicles are equipped with different levels of intelligent driving functions to support assisted driving or autonomous driving.

[0003] For vehicles supporting assisted or autonomous driving, the future state of the surrounding environment can be predicted in real time, just like a human driver, to achieve safe and efficient driving. Currently, the vehicle trajectory planning systems of these vehicles are generally designed to first predict the movement trajectories of surrounding targets and then select the vehicle's driving action. Such vehicle trajectory planning systems result in the vehicle always being in a passive state, leading to low traffic efficiency. For example, the vehicle's future drivable area is often occupied by surrounding traffic participants, especially in situations where there is a risk of conflict between the vehicle and other vehicles, such as lane changing scenarios, intersection scenarios, and scenarios where roads merge. After losing drivable space, the vehicle can only slow down to avoid the other vehicle or wait for it to leave. It is evident that the current vehicle trajectory planning has low autonomy and flexibility. Summary of the Invention

[0004] This application provides a vehicle trajectory planning method, apparatus, device, medium, and product that can improve the autonomy and flexibility of vehicle trajectory planning.

[0005] In a first aspect, embodiments of this application provide a vehicle trajectory planning method, the method comprising:

[0006] Obtain the set of future trajectories of the target vehicle;

[0007] If the number of drivable trajectories included in the future trajectory set is greater than 1, the target predicted driving trajectory corresponding to each drivable trajectory in the future trajectory set is determined based on the future trajectory set, the historical trajectories of surrounding vehicles of the target vehicle, and the current traffic environment information of the target vehicle. The target predicted driving trajectory corresponding to each drivable trajectory of the surrounding vehicles is obtained by adjusting the initial predicted driving trajectory of the surrounding vehicles based on the drivable trajectories. The initial predicted driving trajectory is obtained based on the historical trajectory and the current traffic environment information.

[0008] For each drivable trajectory in the future trajectory set, based on the drivable trajectory and the target prediction trajectories of surrounding vehicles corresponding to the drivable trajectory, determine the target score of the drivable trajectory, and output the drivable trajectory with the highest target score in the future trajectory set.

[0009] Secondly, embodiments of this application provide a vehicle driving trajectory planning device, the device comprising:

[0010] The acquisition module is used to acquire the set of future trajectories of the target vehicle;

[0011] The determination module is used to determine the target predicted driving trajectory of the surrounding vehicles corresponding to each drivable trajectory in the future trajectory set when the number of drivable trajectories included in the future trajectory set is greater than 1, based on the future trajectory set, the historical trajectories of the surrounding vehicles, and the current traffic environment information of the target vehicle. The target predicted driving trajectory of the surrounding vehicles corresponding to each drivable trajectory is obtained by adjusting the initial predicted driving trajectory of the surrounding vehicles based on the drivable trajectories; the initial predicted driving trajectory is obtained based on historical trajectories and current traffic environment information.

[0012] The output module is used to determine the target score of each drivable trajectory in the future trajectory set based on the drivable trajectory and the target predicted trajectories of surrounding vehicles corresponding to the drivable trajectory, and output the drivable trajectory with the highest target score in the future trajectory set.

[0013] Thirdly, embodiments of this application provide a vehicle driving trajectory planning device, the device comprising:

[0014] Processor and memory storing computer program instructions;

[0015] When the processor executes the computer program instructions, it implements the vehicle trajectory planning method as described in the first aspect.

[0016] Fourthly, embodiments of this application provide a computer storage medium storing computer program instructions, which, when executed by a processor, implement the vehicle trajectory planning method as described in the first aspect.

[0017] Fifthly, embodiments of this application provide a computer program product in which instructions, when executed by a processor of an electronic device, cause the electronic device to perform the vehicle trajectory planning method as described in the first aspect.

[0018] In this embodiment, the future trajectory set of the target vehicle can be obtained first. If the number of drivable trajectories included in the future trajectory set of the target vehicle is greater than 1, the target predicted driving trajectory corresponding to each drivable trajectory in the future trajectory set of the target vehicle can be determined based on the future trajectory set of the target vehicle, the historical trajectories of surrounding vehicles, and the current traffic environment information of the target vehicle. The target predicted driving trajectory corresponding to each drivable trajectory of the surrounding vehicles is obtained by adjusting the initial predicted driving trajectory of the surrounding vehicles based on the drivable trajectory. The initial predicted driving trajectory of the surrounding vehicles is obtained based on the historical trajectories of the surrounding vehicles and the current traffic environment information of the target vehicle. Then, based on the future trajectory set and the target predicted trajectories corresponding to each drivable trajectory in the future trajectory set of the surrounding vehicles, the target score of each drivable trajectory in the future trajectory set is obtained. Finally, the driving trajectory with the highest target score in the future trajectory set is output for autonomous driving or assisted driving. As can be seen, this embodiment first obtains the drivable trajectories of the target vehicle; then, it predicts the trajectories of surrounding vehicles based on the drivable trajectories of the target vehicle, and the prediction of the trajectories of surrounding vehicles takes into account the impact of the target vehicle's behavior on surrounding vehicles; finally, it scores each drivable trajectory of the target vehicle based on the predicted results of the drivable trajectories of the target vehicle and the corresponding trajectories of surrounding vehicles, obtains the target score for each drivable trajectory, and then outputs the drivable trajectory with the highest target score in the future trajectory set for autonomous driving or assisted driving. In this way, the trajectory planning of the target vehicle can fully consider the interaction between the target vehicle and its surrounding vehicles, which can improve the autonomy and flexibility of the trajectory planning of the target vehicle, and also improve the traffic efficiency of the target vehicle. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1a This is one of the schematic diagrams of the vehicle driving trajectory planning scheme provided in the embodiments of this application;

[0021] Figure 1b This is a second schematic diagram of the vehicle trajectory planning scheme provided in the embodiments of this application;

[0022] Figure 2 This is one of the flowcharts illustrating the vehicle trajectory planning method provided in the embodiments of this application;

[0023] Figure 3 This is a logical schematic diagram of the trajectory prediction model provided in the embodiments of this application;

[0024] Figure 4 This is a second flowchart illustrating the vehicle trajectory planning method provided in the embodiments of this application;

[0025] Figure 5 This is a schematic diagram of the drivable trajectory of the target vehicle provided in the embodiments of this application;

[0026] Figure 6 This is a schematic diagram of the vehicle trajectory planning device provided in the embodiments of this application;

[0027] Figure 7 This is a schematic diagram of the vehicle trajectory planning device provided in the embodiments of this application. Detailed Implementation

[0028] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0029] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0030] Related technologies for vehicle trajectory planning, such as Figure 1a As shown, the vehicle trajectory planning scheme is characterized by prediction followed by planning. Specifically, it can include the following steps: first, predicting the trajectories of other vehicles (i.e., vehicles surrounding the target vehicle); then, planning the behavior of the target vehicle (i.e., the target vehicle) based on the predicted trajectories of other vehicles; and finally, controlling the target vehicle based on the planned behavior.

[0031] This vehicle trajectory planning scheme lacks interaction between the vehicle's behavior and the predicted results of surrounding vehicles. Specifically, when facing surrounding vehicles with a certain risk of conflict, the vehicle typically slows down to avoid them, or fails to automatically change lanes when there are vehicles approaching from the side or rear. The trajectory planning does not consider the actions the vehicle can take, or the possible reactions of surrounding vehicles under different actions. For example, in a lane-changing scenario, under the premise of ensuring safety, after the vehicle begins to change lanes, vehicles from the side and rear will slow down to ensure the vehicle can change lanes safely. Therefore, Figure 1a The vehicle trajectory planning scheme shown has low autonomy and flexibility, which can easily lead to overly conservative intelligent driving, thus seriously affecting the traffic efficiency of vehicles.

[0032] Based on this, the embodiments of this application provide a new vehicle trajectory planning method, and the vehicle trajectory planning scheme can be, but is not limited to, as shown in the example. Figure 1b As shown, the vehicle trajectory planning scheme can be represented as follows: planning first, then prediction, with multiple planned trajectories of the vehicle added as interactive information during the prediction process. Specifically, it can include the following steps: first, performing vehicle behavior planning; then, based on the various planned behaviors of the vehicle, predicting the trajectories of other vehicles; next, based on the vehicle's planned behaviors and their corresponding predicted trajectories of other vehicles, making vehicle behavior decisions; and finally, based on the vehicle's behavior decisions, obtaining the optimal driving trajectory for vehicle control.

[0033] Compared to Figure 1a The vehicle trajectory planning scheme shown is as follows: Figure 1b The vehicle trajectory planning scheme shown can take into account various behaviors of the vehicle as much as possible, such as continuing straight, changing lanes to the left or right, while ensuring safety. It also takes into account the impact of the vehicle's behavior on surrounding vehicles and the possible reactions of other traffic participants under different behaviors. In this way, the autonomy and flexibility of vehicle trajectory planning can be improved, thereby improving the traffic efficiency of vehicles.

[0034] The vehicle trajectory planning method provided in this application will be described in detail below with reference to the accompanying drawings and through some embodiments and application scenarios.

[0035] The vehicle trajectory planning method of this application embodiment can be applied to a vehicle trajectory planning device. Specifically, the method can be executed by the vehicle trajectory planning device, or by components of the vehicle trajectory planning device, such as the processor, chip, or chip system of the vehicle trajectory planning device, or by a logic module or software that implements all or part of the functions of the vehicle trajectory planning device. In practical applications, the vehicle trajectory planning device can be a vehicle or an electronic device. The electronic device can be a terminal, server, service platform, cloud, distributed system, Internet of Things, vehicle network system, etc. Furthermore, the terminal can be a smartphone, tablet computer, laptop computer, desktop computer, etc.

[0036] See Figure 2 , Figure 2 This is one of the flowcharts for the vehicle trajectory planning method provided in the embodiments of this application. For example... Figure 2 As shown, the vehicle trajectory planning method may include the following steps:

[0037] Step 201: Obtain the set of future trajectories of the target vehicle.

[0038] The set of future trajectories of the target vehicle can be understood as the set of future drivable trajectories of the target vehicle, which may include one or more drivable trajectories. The specific trajectories can be determined according to the actual situation, and this application embodiment does not limit this.

[0039] In this embodiment of the application, in order to plan the driving trajectory of the target vehicle, the set of future trajectories of the target vehicle can be obtained first.

[0040] However, it is worth noting that the embodiments of this application do not limit the method of obtaining the set of future trajectories of the target vehicle. In some embodiments, the set of future trajectories of the target vehicle can be input by the user into the vehicle driving trajectory planning device. In other embodiments, such as Figure 1b As shown, the vehicle trajectory planning device can perform behavior planning for the target vehicle and obtain the set of future trajectories of the target vehicle. For details on its implementation, please refer to the relevant content below, which will not be described here.

[0041] If the number of drivable trajectories included in the future trajectory set is equal to 1, the drivable trajectory can be directly output for intelligent driving, such as assisted driving or autonomous driving.

[0042] If the number of drivable trajectories included in the future trajectory set is greater than 1, step 202 can be executed to fully consider the impact of the target vehicle on surrounding vehicles and obtain the prediction results of the driving trajectories of surrounding vehicles under different drivable trajectories of the target vehicle, namely the target predicted driving trajectory as follows.

[0043] The surrounding vehicles of the target vehicle (also referred to as the surrounding vehicles) may include at least one of the following: the vehicles that are closest to the target vehicle in the left adjacent lane, right adjacent lane, and current lane.

[0044] Step 202: If the number of drivable trajectories included in the future trajectory set is greater than 1, determine the target predicted driving trajectory of the surrounding vehicles corresponding to each drivable trajectory in the future trajectory set based on the future trajectory set, the historical trajectories of the surrounding vehicles, and the current traffic environment information of the target vehicle; wherein, the target predicted driving trajectory of the surrounding vehicles corresponding to each drivable trajectory is obtained by adjusting the initial predicted driving trajectory of the surrounding vehicles based on the drivable trajectories; the initial predicted driving trajectory is obtained based on the historical trajectory and the current traffic environment information.

[0045] In this embodiment, the influence of the target vehicle on surrounding vehicles is fully considered during the prediction of the target vehicle's trajectory. Specifically, this is achieved by first obtaining the initial predicted trajectories of surrounding vehicles based on their historical trajectories and the target vehicle's current traffic environment information. Then, the initial predicted trajectories of the surrounding vehicles are adjusted using each drivable trajectory of the target vehicle, resulting in the target predicted trajectories corresponding to each drivable trajectory. This ensures that the target predicted trajectories corresponding to each drivable trajectory of the target vehicle reflect the interaction between the target vehicle and its surroundings, thereby improving the accuracy of trajectory prediction for the target vehicle's surrounding vehicles.

[0046] For details on obtaining the target predicted driving trajectory corresponding to each drivable trajectory of surrounding vehicles and the target vehicle, please refer to the relevant content below, which will not be described here.

[0047] This application does not limit the form in which the current traffic information of the target vehicle is represented. In some embodiments, the current traffic environment information of the target vehicle may be represented as (L, S, V), where L represents the lane line point set, S represents traffic light information, and V represents road speed limit information. In other embodiments, the current traffic environment information of the target vehicle may be represented as map information of the target vehicle's current location.

[0048] Step 203: For each drivable trajectory in the future trajectory set, determine the target score of the drivable trajectory based on the drivable trajectory and the target predicted trajectories of surrounding vehicles corresponding to the drivable trajectory, and output the drivable trajectory with the highest target score in the future trajectory set.

[0049] After obtaining the drivable trajectories of the target vehicle and the target predicted trajectories of the target vehicle corresponding to each trajectories, each drivable trajectory can be scored based on the drivable trajectory and the target predicted trajectories of the target vehicle. Then, the drivable trajectory with the highest score in the future trajectory set is output as the optimal drivable trajectory, so that the target vehicle can perform intelligent driving based on the optimal trajectories, thereby improving the reliability of vehicle trajectory planning.

[0050] The embodiments of this application do not limit the method of obtaining the target score of the drivable trajectory.

[0051] In some embodiments, driving simulations of the target vehicle can be performed using each driving trajectory and its corresponding predicted target driving trajectory to obtain the values ​​of the target indicators of the target vehicle under different drivable trajectory simulations. Then, based on the values ​​of the target indicators of the target vehicle under different drivable trajectory simulations, a score is obtained for each drivable trajectory. Target indicators may include, but are not limited to, the target vehicle's travel time, driving safety, and driving stability, etc., wherein travel time is negatively correlated with the score, while driving safety and driving stability are positively correlated with the score. That is, if the vehicle performs intelligent driving based on a certain drivable trajectory, the shorter the vehicle's travel time, the higher the driving safety and driving stability, and the higher the score of that drivable trajectory, and vice versa.

[0052] In other embodiments, for each drivable trajectory, a preset algorithm can be used to calculate a score for the drivable trajectory based on the drivable trajectory and the target predicted drivable trajectory of the corresponding target vehicle. For details, please refer to the relevant content below, which will not be described here.

[0053] The vehicle trajectory planning method in this embodiment first obtains the future trajectory set of the target vehicle. If the number of drivable trajectories included in the future trajectory set of the target vehicle is greater than 1, the target predicted driving trajectory corresponding to each drivable trajectory in the future trajectory set of the target vehicle can be determined based on the future trajectory set of the target vehicle, the historical trajectories of surrounding vehicles, and the current traffic environment information of the target vehicle. The target predicted driving trajectory corresponding to each drivable trajectory of the surrounding vehicles is obtained by adjusting the initial predicted driving trajectory of the surrounding vehicles based on the drivable trajectory. The initial predicted driving trajectory of the surrounding vehicles is obtained based on the historical trajectories of the surrounding vehicles and the current traffic environment information of the target vehicle. Then, based on the future trajectory set and the target predicted trajectories corresponding to each drivable trajectory in the future trajectory set of the surrounding vehicles, the target score of each drivable trajectory in the future trajectory set is obtained. Finally, the driving trajectory with the highest target score in the future trajectory set is output for autonomous driving or assisted driving. As can be seen, this embodiment first obtains the drivable trajectories of the target vehicle; then, it predicts the trajectories of surrounding vehicles based on the drivable trajectories of the target vehicle, and the prediction of the trajectories of surrounding vehicles takes into account the impact of the target vehicle's behavior on surrounding vehicles; finally, it scores each drivable trajectory of the target vehicle based on the predicted results of the drivable trajectories of the target vehicle and the corresponding trajectories of surrounding vehicles, obtains the target score for each drivable trajectory, and then outputs the drivable trajectory with the highest target score in the future trajectory set for autonomous driving or assisted driving. In this way, the trajectory planning of the target vehicle can fully consider the interaction between the target vehicle and its surrounding vehicles, which can improve the autonomy and flexibility of the trajectory planning of the target vehicle, and also improve the traffic efficiency of the target vehicle.

[0054] The implementation of step 202 will be explained in detail below.

[0055] In some embodiments, step 202 may include:

[0056] The future trajectory set, the historical trajectories of surrounding vehicles of the target vehicle, and the current traffic environment information of the target vehicle are input into the trajectory prediction model. The target operation is executed through the trajectory prediction model to obtain the target's predicted driving trajectory.

[0057] The target operations include:

[0058] Encode the future trajectory set, the historical trajectories of surrounding vehicles of the target vehicle, and the current traffic environment information of the target vehicle to obtain the drivable trajectory tensor of the target vehicle corresponding to the future trajectory set, the historical trajectory tensor of surrounding vehicles corresponding to the historical trajectory, and the traffic environment tensor corresponding to the current traffic environment information.

[0059] Use the historical trajectory tensor of surrounding vehicles as the first query matrix, and the traffic environment tensor as the first key matrix and the first value matrix.

[0060] A first predicted trajectory tensor is generated using a first cross-attention network based on a first query matrix, a first key matrix, and a first value matrix; the first predicted trajectory tensor includes an initial predicted driving trajectory.

[0061] Use the first predicted trajectory tensor as the second query matrix, and use the target vehicle's drivable trajectory tensor as the second key matrix and the second value matrix.

[0062] The second predicted trajectory tensor is generated using the second cross-attention network based on the second query matrix, the second key matrix, and the second value matrix.

[0063] Decode the second predicted trajectory tensor to obtain the target predicted driving trajectory corresponding to each drivable trajectory in the set of future trajectories for surrounding vehicles.

[0064] In these embodiments, the target vehicle's future trajectory set, the historical trajectories of surrounding vehicles, and the target vehicle's current traffic environment information can be input into a trajectory prediction model (which can be simply referred to as a prediction model). The trajectory prediction model can then predict the target's predicted driving trajectory corresponding to each drivable trajectory in the future trajectory set for surrounding vehicles.

[0065] The trajectory prediction model can predict the target driving trajectory corresponding to each drivable trajectory in the future trajectory set of surrounding vehicles through target operations. The target operations may include the following steps:

[0066] Step 1: Model Encoding: Encode the input set of future trajectories of the target vehicle, the historical trajectories of surrounding vehicles, and the current traffic environment information of the target vehicle to obtain the drivable trajectory tensor T of the target vehicle corresponding to the set of future trajectories. f The historical trajectory tensor T of surrounding vehicles corresponding to the historical trajectory a And the traffic environment tensor T corresponding to the current traffic environment information r .

[0067] In practical implementation, the trajectory prediction model can design a first network to perform dimensionality transformation on the above three inputs, uniformly converting the parameter quantities of their feature dimensions into d. m The dimensions are respectively obtained as [N] a ,d m ]、[N r ,d m ] and [N f ,d m The three input tensors T a T rand T f , where N a N represents the number of surrounding vehicles. r This indicates the number of traffic information items in the current traffic environment. These traffic information items can be L, S, or V, as mentioned above; N f This represents the number of drivable trajectories in the future driving trajectory. The first network can be a multilayer perceptron (MLP) or a long short-term memory (LSTM) network, etc.

[0068] Step 2, Surrounding Vehicle Trajectory Prediction: The trajectory prediction model can be designed with a first cross-attention network, for the surrounding vehicle historical trajectory tensor T obtained in Step 1. a and traffic environment tensor T r By using a first cross-attention network to predict the trajectories of surrounding vehicles, a first predicted trajectory tensor T, which can represent the initial predicted driving trajectories of the surrounding vehicles, is obtained. m .

[0069] In practical implementation, the historical trajectory tensor T of surrounding vehicles can be used. a As the first query matrix Q1, with traffic environment tensor T r The first predicted trajectory tensor T is obtained by processing the first key matrix K1 and the first value matrix V1 through the first cross-attention network. m The embodiments of this application do not limit the specific structure of the first cross-attention network. In some embodiments, it can be an 8-head cross-attention network, but it is not limited to this.

[0070] Step 3, Trajectory Interaction Correction: The trajectory prediction model can design a second cross-attention network for the target vehicle's drivable trajectory tensor T obtained in Step 1. f and the first predicted trajectory tensor T obtained in step two m The prediction results can be corrected using a second cross-attention network to obtain a second prediction trajectory tensor T that can represent the target predicted driving trajectory corresponding to each drivable trajectory in the future trajectory set of surrounding vehicles. e .

[0071] In practical implementation, the first predicted trajectory tensor T can be used. m As the second query matrix Q2, with the target vehicle's drivable trajectory tensor T f The second key matrix K2 and the second value matrix V2 are used to calculate the second predicted trajectory tensor T through the second cross-attention network. e The embodiments of this application do not limit the specific structure of the second cross-attention network. In some embodiments, it can be an 8-head cross-attention network, but it is not limited to this.

[0072] Step 4, Model Decoding: A second network can be designed for the trajectory prediction model. This second network is used to process the second predicted trajectory tensor T obtained in Step 3. e Decoding is performed to obtain the target's predicted driving trajectory corresponding to each drivable trajectory in the set of future trajectories for surrounding vehicles; that is, the predicted driving trajectory of surrounding vehicles under the influence of different actions of the target vehicle. In this context, the superscript 'f' represents the drivable trajectory of the target vehicle, and the subscript 't' represents future time.

[0073] For ease of understanding, the specific implementation logic of the trajectory prediction model can be found in [link to documentation]. Figure 3 .

[0074] Through the above embodiments, the trajectory prediction model can use the historical trajectory tensor T of surrounding vehicles. a As the first query matrix Q1, with traffic environment tensor T r The first predicted trajectory tensor T is obtained by processing the first key matrix K1 and the first value matrix V1 through the first cross-attention network. m Then, using the first predicted trajectory tensor T... m As the second query matrix Q2, with the target vehicle's drivable trajectory tensor T f The second key matrix K2 and the second value matrix V2 are used to calculate the second predicted trajectory tensor T through the second cross-attention network. e Then, the target predicted driving trajectory is obtained by decoding the driving trajectory of the surrounding vehicles and the driving trajectory of each drivable trajectory in the future trajectory set. In this way, by inputting the driving trajectory of the target vehicle into the trajectory prediction model to predict the future driving trajectory of the surrounding vehicles, the impact of the target vehicle on the surrounding vehicles is fully considered, which can improve the accuracy of driving trajectory prediction.

[0075] In some other embodiments, step 202 may include:

[0076] Based on historical trajectory and current traffic environment information, an initial predicted driving trajectory is determined;

[0077] For each drivable trajectory in the future trajectory set, calculate the first correlation between the initial predicted drivable trajectory and the drivable trajectory;

[0078] The initial predicted driving trajectory is adjusted based on the first relevance to obtain the target predicted driving trajectory corresponding to the driving trajectory of surrounding vehicles.

[0079] In these embodiments, the initial predicted driving trajectory of the surrounding vehicles can be predicted based on the historical trajectories of the surrounding vehicles and the current traffic environment information of the target vehicle.

[0080] Next, considering the interaction between the target vehicle and surrounding vehicles, the initial predicted driving trajectories of the surrounding vehicles can be adjusted using each drivable trajectory in the future trajectory set, thus obtaining the target predicted driving trajectory of the surrounding vehicles corresponding to each drivable trajectory. In other words, the target predicted driving trajectory of a surrounding vehicle corresponding to a certain drivable trajectory can be obtained based on the interaction between that drivable trajectory and the initial predicted driving trajectory of the surrounding vehicles.

[0081] In specific implementation, for each drivable trajectory in the future trajectory set, the correlation between the drivable trajectory and the initial predicted drivable trajectory of the surrounding vehicles can be calculated first (denoted as the first correlation). The correlation in this application embodiment can be calculated, but is not limited to, by calculation methods such as dot product, cosine or Euclidean algorithm.

[0082] Subsequently, the initial predicted driving trajectory is adjusted based on the first relevance to obtain the target predicted driving trajectory of surrounding vehicles corresponding to the drivable trajectory. In this embodiment, the adjustment based on relevance can be implemented, but is not limited to, through weighted summation or attention mechanisms.

[0083] To facilitate understanding of the correlation-based adjustment method, the following example illustrates the adjustment of the initial predicted driving trajectory of the target vehicle based on the first correlation.

[0084] For the weighted summation method, the first weight of the initial predicted driving trajectory can be determined based on the first relevance, and the first relevance is positively correlated with the first weight; (1-first weight) is used as the second weight of the drivable trajectory; then, the first weight and the second weight are used to perform a weighted summation of the initial predicted driving trajectory and the drivable trajectory to obtain the target predicted driving trajectory corresponding to the drivable trajectory.

[0085] For the attention mechanism approach, the attention weight of the initial predicted driving trajectory can be determined based on the first relevance, and the first relevance and the attention weight can be positively correlated. Then, the product of the attention weight and the initial predicted driving trajectory is calculated, and then the product is added to the initial predicted driving trajectory to obtain the target predicted driving trajectory.

[0086] Through the above embodiments, after obtaining the initial predicted driving trajectories of surrounding vehicles, the correlation between each drivable trajectory of the target vehicle and the initial predicted driving trajectory can be calculated. Then, the initial predicted driving trajectory is adjusted based on the correlation to obtain the target predicted driving trajectory of the surrounding vehicles corresponding to the drivable trajectories. In this way, the target predicted driving trajectory of the surrounding vehicles corresponding to the drivable trajectories can reflect the interaction between the target vehicle and its surrounding vehicles, thereby improving the accuracy of trajectory prediction.

[0087] This application does not limit the method for obtaining the initial predicted driving trajectory of surrounding vehicles. In some embodiments, the initial predicted driving trajectory of surrounding vehicles can be predicted by inputting the historical trajectories of surrounding vehicles and the current traffic environment information of the target vehicle into a pre-trained network model. In other embodiments, determining the initial predicted driving trajectory based on historical trajectories and current traffic environment information may include:

[0088] Calculate the second correlation between historical trajectories and current traffic environment information;

[0089] The historical trajectory is adjusted based on the second correlation to obtain the initial predicted driving trajectory.

[0090] In these embodiments, the initial predicted driving trajectory of surrounding vehicles can be obtained based on the interaction between the historical trajectories of surrounding vehicles and the current traffic environment information of the target vehicle. Specifically, the correlation between the historical trajectory and the current environment information (denoted as the second correlation) can be calculated first, and then the historical trajectory can be adjusted based on the second correlation to obtain the initial predicted driving trajectory. The calculation of the second similarity and the method of adjusting the historical trajectory based on the second similarity can be found in the aforementioned content on the calculation of similarity and the adjustment based on similarity. To avoid repetition, it will not be repeated here.

[0091] Through the above embodiments, the acquisition of the initial predicted driving trajectory of the target vehicle's surrounding vehicles takes into account the interaction between the surrounding vehicles and the traffic environment. In this way, the accuracy of acquiring the initial predicted driving trajectory of the target vehicle's surrounding vehicles can be improved, thereby improving the accuracy of vehicle trajectory planning.

[0092] In some embodiments of the aforementioned scheme that obtains the set of future trajectories of a target vehicle by performing behavior planning on the target vehicle, the current traffic environment information includes lane line information and traffic light information.

[0093] Obtain the set of future trajectories of the target vehicle, including:

[0094] Based on lane markings and traffic light information, determine the permissible direction of travel for the target vehicle;

[0095] Based on the drivable direction, an interpolation method is used to generate a set of future trajectories.

[0096] In these embodiments, the permissible driving direction of the target vehicle can be determined by combining lane line information and traffic light information in the current traffic environment, such as changing lanes to the left, continuing straight, or changing lanes to the right. Specifically, if the target vehicle's current driving lane has a left-adjacent lane and the traffic light includes a left-turn signal, then the permissible driving direction of the target vehicle can be determined to include changing lanes to the left; if the target vehicle's current driving lane has a right-adjacent lane and the traffic light includes a right-turn signal, then the permissible driving direction of the target vehicle can be determined to include changing lanes to the right; if the traffic light includes a straight-ahead signal, then the permissible driving direction of the target vehicle can be determined to include continuing straight.

[0097] Then, based on the drivable direction, the current position of the target vehicle, and the lane lines corresponding to the drivable direction, an interpolation method can be used to generate the driving trajectory corresponding to each drivable direction, thus obtaining each drivable trajectory. This application does not limit the specific form of the interpolation method; in some embodiments, the interpolation method can be a spline curve interpolation method, but it is not limited to this.

[0098] In the above embodiments, the possible driving direction of the target vehicle is determined by the lane line information and traffic light information in the current traffic environment of the target vehicle, and then a set of future trajectories is generated. In this way, multiple behaviors of the vehicle can be considered as much as possible, thereby improving the success rate of target vehicle planning.

[0099] For the aforementioned scheme that scores drivable trajectories using a preset algorithm, in some embodiments, for each drivable trajectory in the future trajectory set, a target score for the drivable trajectory is determined based on the drivable trajectory and the target predicted trajectories of surrounding vehicles corresponding to the drivable trajectory, including:

[0100] Based on the drivable trajectory and the target predicted trajectories of surrounding vehicles corresponding to the drivable trajectory, the safety score corresponding to the drivable trajectory is determined.

[0101] Based on the coordinates of each driving point in the drivable trajectory, determine the vehicle speed score and stability score of the drivable trajectory;

[0102] The target score for the drivable trajectory is determined based on the safety score, speed score, and stability score.

[0103] In these embodiments, the target vehicle and its surrounding vehicles can be predicted based on their respective drivable trajectories and their corresponding predicted trajectories, thereby predicting the probability of trajectory conflict and / or traffic efficiency, and thus obtaining a safety score corresponding to each drivable trajectory. The probability of trajectory conflict is negatively correlated with the safety score.

[0104] In addition, the driving speed and driving stability of the driving trajectory can be analyzed based on the coordinates of each driving point in the driving trajectory to obtain a speed score and a stability score. The driving stability of the driving trajectory is positively correlated with the stability score. For the speed score, a speed threshold can be preset, and then the speed score can be determined based on the difference between the speed threshold and the driving speed of the driving trajectory.

[0105] Then, a weighted average can be calculated on the safety score, speed score, and stability score of the drivable trajectory to obtain the target score of the drivable trajectory.

[0106] In some implementations, the target score of a drivable trajectory can be obtained through an evaluation function that considers indicators such as safety, traffic efficiency, and driving smoothness, but it is not limited to this.

[0107] In this way, the target score of the drivable trajectory can reflect information such as the safety and stability of the drivable trajectory. As a result, the drivable trajectory with the highest score selected based on the target score of the drivable trajectory can be the best drivable trajectory with the highest overall evaluation. This can further improve the reliability of the target vehicle's driving trajectory planning.

[0108] It should be noted that the various embodiments described in this application can be combined with each other or implemented individually without conflict, and this application does not limit this.

[0109] For ease of understanding, a specific embodiment will be used as an example:

[0110] In the following specific embodiment, the target vehicle is referred to as the autonomous vehicle, and the target predicted driving trajectories of surrounding vehicles are realized through a model. To prevent the autonomous vehicle's drivable space from being occupied by surrounding vehicles, this specific embodiment may include the following: First, for each possible action of the autonomous vehicle (e.g., maintaining a straight path, changing lanes to the left, or changing lanes to the right), trajectory planning is performed using spline curve generation. Second, the autonomous vehicle's various action trajectories are fed into a deep learning-based prediction model to calculate the prediction results for surrounding vehicles, i.e., the target predicted driving trajectories of surrounding vehicles. Third, using an evaluation function that considers indicators such as safety, traffic efficiency, and driving smoothness, combined with the prediction results of surrounding vehicles, the optimal autonomous vehicle behavior, i.e., the drivable trajectory with the highest score, is selected. Finally, the selected drivable trajectory is output to the vehicle control module to realize autonomous vehicle control.

[0111] Compared with related technologies, the above specific embodiments can fully consider the impact of the vehicle's behavior on surrounding vehicles, improve the flexibility and efficiency of the vehicle's movement; can bring the future trajectory planned by the vehicle into the prediction model, improve the accuracy of the prediction; and can perform calculations on as many different vehicle behaviors as possible, thereby improving the success rate of vehicle planning.

[0112] To facilitate understanding, further integration Figure 4 The implementation of the above specific embodiments will be described, such as... Figure 4 As shown, the following steps may be included:

[0113] Step 1: Obtain the historical trajectory of surrounding vehicles over the past 2 seconds and store it at 0.1-second intervals. The historical trajectory information includes the horizontal coordinate value. ordinate value The angle of the front of the surrounding vehicles t1,t2,…t end It is a timestamp, the total duration of the historical trajectory, with a total of 21 time points.

[0114] Step 2: Obtain the current time t end The vehicle's surrounding traffic environment information (i.e., current traffic environment information) includes lane line point set L, traffic light information S, road speed limit information V, etc.

[0115] Step 3: Based on the traffic environment information L and S, determine the possible directions the vehicle can travel, and use spline curve interpolation to generate the future 8-second trajectory (i.e., the possible trajectory of the target vehicle) in each possible direction, denoted as f; Figure 5 For example, if a car is in a 3-lane scenario, there are 3 possible directions to travel: change lanes to the left, stay straight, or change lanes to the right. Then, the set of future trajectories is f = {f1, f2, f3}.

[0116] Step 4: Model Encoding: Encode the historical trajectories of surrounding vehicles (X, Y, Ω), traffic environment information (L, S, V), and the drivable trajectory F of the vehicle. Design three MLP networks to perform dimensionality transformation on the above input data, unifying the parameter count of its feature dimensions into d. m The dimensions are respectively obtained as [N] a ,d m ]、[N r ,d m ] and [N f ,d m The three input tensors T a T r and T f , where N a Indicates the number of surrounding vehicles, N r N represents the number of traffic information items in the current traffic environment. f This indicates the number of possible trajectories for the vehicle.

[0117] Step 5: Surrounding Vehicle Trajectory Prediction: Using the surrounding vehicle historical trajectory tensor and traffic environment tensor encoded in Step 4, a cross-attention network is designed to calculate the trajectory prediction. In this step, the surrounding vehicle historical trajectory tensor T... a To query matrix Q1, use the traffic environment tensor T r Given a key matrix K1 and a value matrix V1, an 8-head cross-attention network is used to calculate the predicted trajectory tensor T of surrounding vehicles over the next 8 seconds. m That is, the first predicted trajectory tensor, whose dimension is also [N]. a ,d m ].

[0118] Step 6: Trajectory Interaction Correction: Cross-attention is applied to the tensor of the result from Step 5 and the vehicle's drivable trajectory, so that the target prediction structure is affected by different behaviors of the vehicle, thus correcting the prediction result. In this step, the prediction result tensor T from Step 5 is used... m To query matrix Q2, use the vehicle's drivable trajectory tensor T. f Given the key matrix K2 and value matrix V2, an 8-head cross-attention network is used to calculate the prediction results of surrounding vehicles under the influence of different actions of the vehicle, denoted as T. e That is, the second predicted trajectory tensor.

[0119] Step 7: Model Decoding: Use an MLP network to process the result T from Step 6. e Decoding is performed to obtain the predicted output trajectory under the influence of different vehicle actions. This refers to the predicted driving trajectory of surrounding vehicles. The superscript f∈{f1,f2,f3} represents the vehicle's action, and the subscript t=0.1,0.2,…8.0 represents the time in the next 8 seconds, with a time interval of 0.1s.

[0120] Step 8: Using a weighted evaluation function g(f), based on the trajectory planned by the autonomous vehicle and the corresponding prediction results of surrounding vehicles, and taking into account vehicle safety, autonomous vehicle evaluation speed, and autonomous vehicle driving smoothness indicators, the results of Step 3 are scored to obtain the target scores for each drivable trajectory of the target vehicle.

[0121] Step 9: Output the driving trajectory of the vehicle with the highest score, and end the process.

[0122] It should be noted that, Figure 5 The selection of information such as time, time interval, interpolation method and attention network in the corresponding vehicle trajectory planning method is only an example and does not limit the form of the above information. It can be selected according to actual needs, and this application embodiment does not limit it.

[0123] Based on the vehicle trajectory planning method provided in the above embodiments, this application also provides specific implementation methods of the vehicle trajectory planning device. Please refer to the following embodiments.

[0124] See Figure 6 The vehicle trajectory planning device provided in this application embodiment may include:

[0125] Module 601 is used to acquire the set of future trajectories of the target vehicle;

[0126] The determination module 602 is used to determine the target predicted driving trajectory of the surrounding vehicles corresponding to each drivable trajectory in the future trajectory set when the number of drivable trajectories included in the future trajectory set is greater than 1, based on the future trajectory set, the historical trajectories of the surrounding vehicles of the target vehicle, and the current traffic environment information of the target vehicle; wherein, the target predicted driving trajectory of the surrounding vehicles corresponding to each drivable trajectory is obtained by adjusting the initial predicted driving trajectory of the surrounding vehicles based on the drivable trajectories; the initial predicted driving trajectory is obtained based on the historical trajectory and the current traffic environment information;

[0127] The output module 603 is used to determine the target score of each drivable trajectory in the future trajectory set based on the drivable trajectory and the target prediction trajectories of surrounding vehicles corresponding to the drivable trajectory, and output the drivable trajectory with the highest target score in the future trajectory set.

[0128] The vehicle trajectory planning device provided in this application embodiment can realize the various processes in the method embodiment, and will not be described again here to avoid repetition.

[0129] Figure 7 A schematic diagram of the hardware structure for vehicle trajectory planning provided in an embodiment of this application is shown.

[0130] The vehicle trajectory planning device may include a processor 701 and a memory 702 storing computer program instructions.

[0131] Specifically, the processor 701 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0132] Memory 702 may include mass storage for data or instructions. For example, and not limitingly, memory 702 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 702 may include removable or non-removable (or fixed) media. Where appropriate, memory 702 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 702 is non-volatile solid-state memory.

[0133] Memory may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, and electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of this disclosure.

[0134] The processor 701 reads and executes computer program instructions stored in the memory 702 to implement any of the vehicle trajectory planning methods in the above embodiments.

[0135] In one example, the vehicle trajectory planning device may also include a communication interface 707 and a bus 710. For example, Figure 7 As shown, the processor 701, memory 702, and communication interface 707 are connected through bus 710 and complete communication with each other.

[0136] The communication interface 707 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0137] Bus 710 includes hardware, software, or both, that couples the components of the vehicle trajectory planning device together. This is an example, not a limitation.

[0138] The bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 710 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, this application contemplates any suitable bus or interconnect.

[0139] Furthermore, in conjunction with the insulation resistance detection methods in the above embodiments, this application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the insulation resistance detection methods in the above embodiments.

[0140] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0141] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. The programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM, floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0142] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0143] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0144] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method for planning vehicle driving trajectory, characterized in that, include: Obtain the set of future trajectories of the target vehicle; If the number of drivable trajectories included in the future trajectory set is greater than 1, the target predicted driving trajectory of the surrounding vehicles corresponding to each drivable trajectory in the future trajectory set is determined based on the future trajectory set, the historical trajectories of the surrounding vehicles, and the current traffic environment information of the target vehicle; wherein, the target predicted driving trajectory of the surrounding vehicles corresponding to each drivable trajectory is obtained by adjusting the initial predicted driving trajectory of the surrounding vehicles based on the drivable trajectories; the initial predicted driving trajectory is obtained based on the historical trajectories and the current traffic environment information; For each drivable trajectory in the future trajectory set, based on the drivable trajectory and the target predicted drivable trajectories of the surrounding vehicles corresponding to the drivable trajectory, the target score of the drivable trajectory is determined, and the drivable trajectory with the highest target score in the future trajectory set is output. The step of determining the target predicted driving trajectory of the surrounding vehicles corresponding to each drivable trajectory in the future trajectory set based on the future trajectory set, the historical trajectories of the surrounding vehicles of the target vehicle, and the current traffic environment information of the target vehicle includes: determining the initial predicted driving trajectory based on the historical trajectory and the current traffic environment information; calculating a first correlation between the initial predicted driving trajectory and each drivable trajectory in the future trajectory set; and adjusting the initial predicted driving trajectory based on the first correlation to obtain the target predicted driving trajectory of the surrounding vehicles corresponding to the drivable trajectories.

2. The method according to claim 1, characterized in that, The step of determining the target predicted driving trajectory of the surrounding vehicles corresponding to each drivable trajectory in the future trajectory set based on the future trajectory set, the historical trajectories of the surrounding vehicles of the target vehicle, and the current traffic environment information of the target vehicle includes: The future trajectory set, the historical trajectories of surrounding vehicles of the target vehicle, and the current traffic environment information of the target vehicle are input into the trajectory prediction model. The target operation is then performed through the trajectory prediction model to obtain the target predicted driving trajectory. The target operation includes: The future trajectory set, the historical trajectories of surrounding vehicles of the target vehicle, and the current traffic environment information of the target vehicle are encoded to obtain the target vehicle drivable trajectory tensor corresponding to the future trajectory set, the surrounding vehicle historical trajectory tensor corresponding to the historical trajectory, and the traffic environment tensor corresponding to the current traffic environment information. The surrounding vehicle historical trajectory tensor is used as the first query matrix, and the traffic environment tensor is used as the first key matrix and the first value matrix. A first predicted trajectory tensor is generated using a first cross-attention network based on the first query matrix, the first key matrix, and the first value matrix; the first predicted trajectory tensor includes the initial predicted driving trajectory. Use the first predicted trajectory tensor as the second query matrix, and use the target vehicle drivable trajectory tensor as the second key matrix and the second value matrix. A second predicted trajectory tensor is generated using a second cross-attention network based on the second query matrix, the second key matrix, and the second value matrix. Decode the second predicted trajectory tensor to obtain the target predicted driving trajectory of the surrounding vehicles corresponding to each drivable trajectory in the future trajectory set.

3. The method according to claim 1, characterized in that, The step of determining the initial predicted driving trajectory based on the historical trajectory and the current traffic environment information includes: Calculate the second correlation between the historical trajectory and the current traffic environment information; The historical trajectory is adjusted based on the second correlation to obtain the initial predicted driving trajectory.

4. The method according to claim 1, characterized in that, The current traffic environment information includes lane line information and traffic light information; The acquisition of the future trajectory set of the target vehicle includes: Based on the lane line information and the traffic light information, the permissible driving direction of the target vehicle is determined; Based on the drivable direction, the set of future trajectories is generated using an interpolation method.

5. The method according to claim 1, characterized in that, For each drivable trajectory in the set of future trajectories, a score is determined based on the drivable trajectory and the target predicted trajectories of surrounding vehicles corresponding to the drivable trajectory, including: Based on the drivable trajectory and the target predicted trajectories of surrounding vehicles corresponding to the drivable trajectory, a safety score corresponding to the drivable trajectory is determined; Based on the coordinates of each driving point in the drivable trajectory, determine the vehicle speed score and stability score of the drivable trajectory; The target score for the drivable trajectory is determined based on the safety score, the vehicle speed score, and the stability score.

6. A vehicle trajectory planning device, characterized in that, The device includes: The acquisition module is used to acquire the set of future trajectories of the target vehicle; A determination module is configured to, when the number of drivable trajectories included in the future trajectory set is greater than 1, determine the target predicted driving trajectory of the surrounding vehicles corresponding to each drivable trajectory in the future trajectory set, based on the future trajectory set, the historical trajectories of the surrounding vehicles of the target vehicle, and the current traffic environment information of the target vehicle; wherein, the target predicted driving trajectory of the surrounding vehicles corresponding to each drivable trajectory is obtained by adjusting the initial predicted driving trajectory of the surrounding vehicles based on the drivable trajectories; the initial predicted driving trajectory is obtained based on the historical trajectories and the current traffic environment information; The output module is used to determine the target score of each drivable trajectory in the future trajectory set based on the drivable trajectory and the target predicted driving trajectory of the surrounding vehicles corresponding to the drivable trajectory, and output the drivable trajectory with the highest target score in the future trajectory set. The determining module is specifically used for: determining the initial predicted driving trajectory based on the historical trajectory and the current traffic environment information; calculating a first correlation between the initial predicted driving trajectory and the drivable trajectory for each drivable trajectory in the future trajectory set; adjusting the initial predicted driving trajectory based on the first correlation to obtain the target predicted driving trajectory of the surrounding vehicles corresponding to the drivable trajectory.

7. A vehicle trajectory planning device, characterized in that, The device includes: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, it implements the vehicle trajectory planning method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the vehicle trajectory planning method as described in any one of claims 1 to 5.

9. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device performs the vehicle trajectory planning method as described in any one of claims 1 to 5.

Images