Surrounding vehicle predicted trajectory optimization method and device, vehicle and storage medium

Abstract

The embodiment of the application discloses a kind of prediction trajectory optimization method, device, vehicle and storage medium of surrounding vehicle, it is related to vehicle control technical field, including: obtaining the initial prediction trajectory of the surrounding vehicle of current vehicle, determine the starting point lane corresponding to the starting point of initial prediction trajectory and the end lane corresponding to the end point;According to the position of starting point lane and the position of end lane, determine the optimization lane of end lane, and according to starting point lane and optimization lane, the direction optimization of initial prediction trajectory is carried out, and intermediate prediction trajectory is obtained;According to intermediate prediction trajectory, determine the front vehicle of surrounding vehicle;Based on intermediate prediction trajectory, determine the interaction trajectory point of surrounding vehicle and front vehicle, and move interaction trajectory point to obtain the optimization trajectory point of interaction trajectory point;Based on optimization trajectory point, the speed optimization of intermediate prediction trajectory is carried out, and the target prediction trajectory of surrounding vehicle is obtained, improve the rationality and accuracy of prediction trajectory, and improve the driving safety of automatic driving vehicle.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to a method, apparatus, vehicle, and storage medium for predicting and optimizing the trajectories of surrounding vehicles. Background Technology

[0002] When making decisions and plans, autonomous vehicles need to predict the movement trajectories of surrounding vehicles to ensure their safe operation.

[0003] Currently, neural network models are used to predict the movement trajectories of surrounding vehicles over a period of time. However, the prediction results based on neural network models rely on the training results of the neural network models on the dataset. This may not adequately consider lane lines, surrounding vehicles, and the rationality of vehicle movement. This may lead to unreasonable driving scenarios in the prediction results, such as changing driving trajectories between three lanes or colliding with surrounding vehicles. Consequently, the accuracy of predicting the movement trajectories of surrounding vehicles is low, which reduces the driving safety of autonomous vehicles. Summary of the Invention

[0004] This application provides a method, apparatus, vehicle, and storage medium for optimizing the predicted trajectories of surrounding vehicles. It implements a method for optimizing predicted trajectories, improves the accuracy of predicting the motion trajectories of surrounding vehicles, and solves the problem of low prediction accuracy of predicted trajectories determined by neural network models in the prior art.

[0005] In a first aspect, embodiments of this application provide a method for optimizing the predicted trajectories of surrounding vehicles, the method comprising:

[0006] Obtain the initial predicted trajectories of surrounding vehicles of the current vehicle, and determine the starting lane corresponding to the starting point of the initial predicted trajectory and the ending lane corresponding to the ending point of the trajectory.

[0007] The optimal lane for the endpoint lane is determined based on the positions of the starting lane and the endpoint lane. The direction of the initial predicted trajectory is then optimized based on the starting lane and the optimized lane to obtain the intermediate predicted trajectory.

[0008] The vehicle in front of the surrounding vehicles is determined based on the intermediate predicted trajectory;

[0009] Based on the intermediate predicted trajectory, the interaction trajectory points between the surrounding vehicles and the vehicle in front are determined, and the interaction trajectory points are moved to obtain the optimized trajectory points of the interaction trajectory points.

[0010] Based on the optimized trajectory points, the speed of the intermediate predicted trajectory is optimized to obtain the target predicted trajectory of the surrounding vehicles.

[0011] Secondly, embodiments of this application provide a device for optimizing the predicted trajectories of surrounding vehicles, the device comprising:

[0012] The lane determination module is used to obtain the initial predicted trajectory of the surrounding vehicles of the current vehicle, and determine the starting lane corresponding to the starting point of the initial predicted trajectory and the ending lane corresponding to the ending point of the trajectory.

[0013] The direction optimization module is used to determine the optimized lane of the destination lane based on the position of the starting lane and the position of the destination lane, and to optimize the direction of the initial predicted trajectory based on the starting lane and the optimized lane to obtain the intermediate predicted trajectory.

[0014] The preceding vehicle determination module is used to determine the preceding vehicle of surrounding vehicles based on the intermediate predicted trajectory;

[0015] The trajectory point optimization module is used to determine the interaction trajectory points between surrounding vehicles and the vehicle in front based on the intermediate predicted trajectory, and to move the interaction trajectory points to obtain the optimized trajectory points of the interaction trajectory points.

[0016] The speed optimization module is used to optimize the speed of the intermediate predicted trajectory based on the optimized trajectory points, so as to obtain the target predicted trajectory of the surrounding vehicles.

[0017] Thirdly, embodiments of this application provide a vehicle, the vehicle comprising:

[0018] At least one processor; and a memory communicatively connected to the at least one processor;

[0019] The memory stores a computer program that can be executed by at least one processor, which enables the at least one processor to perform the surrounding vehicle trajectory optimization method of any embodiment of the present application.

[0020] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for optimizing the predicted trajectories of surrounding vehicles as described in any embodiment of this application.

[0021] In this embodiment, the initial predicted trajectories of surrounding vehicles can be obtained, and the starting lane corresponding to the starting point of the initial predicted trajectory and the ending lane corresponding to the ending point of the trajectory can be determined. Then, based on the positions of the starting and ending lanes, an optimized lane for the ending lane is determined. The initial predicted trajectory is then optimized in direction based on the starting and optimized lanes to obtain an intermediate predicted trajectory. Next, the preceding vehicle of the surrounding vehicles is determined based on the intermediate predicted trajectory. Then, the interaction trajectory points between the surrounding vehicles and the preceding vehicle are determined based on the intermediate predicted trajectory, and these interaction trajectory points are moved to obtain optimized trajectory points. Finally, the intermediate predicted trajectory is optimized in speed based on the optimized trajectory points to obtain the target predicted trajectory of the surrounding vehicles, thus realizing the function of optimizing the predicted trajectory of surrounding vehicles. By determining the optimized lane based on the starting and ending lanes of the initial predicted trajectory and optimizing the direction based on the optimized lane, the intermediate predicted trajectory is more in line with actual traffic rules and driving habits, avoiding dangerous situations such as changing two or more lanes at once. This approach effectively avoids the problem in existing technologies where predictions fail to adequately consider the rationality of lane lines and vehicle movement, potentially leading to unreasonable driving scenarios. This improves the rationality and accuracy of the predicted trajectory. By incorporating the preceding vehicle and moving interaction trajectory points from surrounding vehicles to obtain optimized trajectory points, and then optimizing speed based on these optimized trajectory points, the predicted trajectory more closely resembles actual driving scenarios, preventing dangerous situations such as collisions between surrounding vehicles and the preceding vehicle. This effectively avoids the problem in existing technologies where predictions fail to adequately consider environmental vehicles (i.e., the preceding vehicle from surrounding areas), potentially leading to unreasonable driving scenarios. Furthermore, through multi-level optimization of the initial predicted trajectory, the vehicle can better cope with various uncertainties and changing factors, and can plan obstacle avoidance paths in advance, optimizing driving speed and route. This makes the autonomous driving system more reliable and stable, thereby improving the driving safety of autonomous vehicles and enhancing the user experience. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart illustrating a method for optimizing the predicted trajectories of surrounding vehicles provided in an embodiment of this application.

[0024] Figure 2 This is another flowchart illustrating the method for optimizing the predicted trajectory of surrounding vehicles provided in this application embodiment;

[0025] Figure 3 This is an example diagram of a lane network provided in an embodiment of this application;

[0026] Figure 4 This is an example diagram of the orientation-optimized initial predicted trajectory provided in an embodiment of this application;

[0027] Figure 5 This is another example diagram of the orientation-optimized initial predicted trajectory provided in the embodiments of this application;

[0028] Figure 6 This is another flowchart illustrating the method for optimizing the predicted trajectory of surrounding vehicles provided in the embodiments of this application;

[0029] Figure 7 This is an example diagram of the velocity optimization intermediate prediction trajectory provided in the embodiments of this application;

[0030] Figure 8 This is a schematic diagram of a predicted trajectory optimization device for surrounding vehicles provided in an embodiment of this application;

[0031] Figure 9 This is a structural schematic diagram of a vehicle provided in an embodiment of this application. Detailed Implementation

[0032] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0033] It should be noted that the terms "first," "second," "target," and "original," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in sequences other than those illustrated or described herein. Furthermore, the terms "comprising," "having," and any variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0034] Figure 1This is a flowchart illustrating a method for optimizing the predicted trajectories of surrounding vehicles provided in this application embodiment. This embodiment can be applied to scenarios requiring optimization of the predicted trajectories of surrounding vehicles of the current vehicle. The method for optimizing the predicted trajectories of surrounding vehicles provided in this embodiment can be executed by a device for optimizing the predicted trajectories of surrounding vehicles provided in this application embodiment. This device can be implemented through software and / or hardware. In a specific embodiment, the device for optimizing the predicted trajectories of surrounding vehicles can be integrated into a vehicle, for example, the vehicle can be an autonomous vehicle, and the vehicle can include a vehicle controller. The executing entity of this method can be the vehicle controller (i.e., the current vehicle's vehicle controller), see [link to relevant documentation]. Figure 1 The method for optimizing the predicted trajectories of surrounding vehicles in this embodiment includes, but is not limited to, the following steps:

[0035] S110. Obtain the initial predicted trajectory of the surrounding vehicles of the current vehicle, and determine the starting lane corresponding to the starting point of the initial predicted trajectory and the ending lane corresponding to the ending point of the trajectory.

[0036] The current vehicle refers to the vehicle currently performing an autonomous driving task. It can plan its own driving path based on the movement trajectories of surrounding vehicles and control its own driving. Surrounding vehicles refer to other vehicles near the current vehicle, which may affect the current vehicle's driving.

[0037] The initial predicted trajectory is based on data about surrounding vehicles collected by the vehicle's sensors (such as cameras, lidar, and millimeter-wave radar), and is a preliminary prediction of the possible driving paths of surrounding vehicles over a future period using a neural network model. The neural network model is used to predict the vehicle's driving trajectory.

[0038] Optionally, the initial predicted trajectory may include multiple trajectory points and state data for each trajectory point. The state data for each trajectory point may include its position, distance, time, speed, steering angle, and direction of travel. The distance is the distance between the trajectory point and the trajectory starting point. The time is the time required for surrounding vehicles to travel from the trajectory starting point to the trajectory point. The speed is the speed of surrounding vehicles when they reach the trajectory point. The steering angle is the angle between the centerline and the lane line of the surrounding vehicles when they reach the trajectory point. The direction of travel is the direction of travel of surrounding vehicles at the trajectory point, such as north, south, east, or west.

[0039] The trajectory start point is the initial position of the predicted trajectory, that is, the location of surrounding vehicles at the current moment; the trajectory start point is determined in real time based on the current vehicle's sensors. The starting lane is the lane where the trajectory start point is located.

[0040] The trajectory endpoint is the end position of the initial predicted trajectory, that is, the position where surrounding vehicles are expected to arrive at the end of the prediction period. The endpoint lane is the lane where the trajectory endpoint is located.

[0041] Specifically, when it is necessary to optimize the predicted trajectories of surrounding vehicles, the initial predicted trajectories of these vehicles can be obtained. This can be achieved by using the vehicle's sensors (such as cameras, lidar, and millimeter-wave radar) to collect real-time state data of surrounding vehicles, including their position, speed, and acceleration, as well as environmental information such as road structure and traffic signs. Based on this collected data, a pre-trained neural network model is used to predict the future trajectories of the surrounding vehicles, resulting in the predicted trajectories, which are then used as the initial predicted trajectories. The neural network model can be a recurrent neural network (RNN) or a long short-term memory (LSTM) network, among others.

[0042] Next, the trajectory start point and trajectory end point can be extracted from the initial predicted trajectory. Then, based on the location of the trajectory start point and high-precision map information, the lane line detection algorithm is used to determine the lane corresponding to the trajectory start point to obtain the starting lane. And based on the location of the trajectory end point and high-precision map information, the lane line detection algorithm is used to determine the lane corresponding to the trajectory end point to obtain the ending lane.

[0043] S120. Determine the optimal lane for the endpoint lane based on the position of the starting lane and the position of the endpoint lane, and optimize the direction of the initial predicted trajectory based on the starting lane and the optimal lane to obtain the intermediate predicted trajectory.

[0044] Among them, the optimized lane is the best destination lane selected according to traffic rules (such as lane changing rules), which can provide better driving conditions and lower potential risks.

[0045] The intermediate predicted trajectory is the trajectory obtained after directional optimization of the initial predicted trajectory. It provides a smooth driving path that meets traffic rules between the starting lane and the optimized lane. Optionally, the intermediate predicted trajectory may include multiple trajectory points and the state data of each trajectory point. The state data of a trajectory point may include the position, distance, time, speed, steering angle, and direction of travel of the trajectory point. Furthermore, the directional optimization does not change the time or speed of the trajectory point.

[0046] Specifically, after obtaining the starting lane and the ending lane, the optimal lane for the ending lane can be determined based on their positions. For example, based on the positions of the starting lane and the ending lane, the vehicle's sensors can be used to collect attribute information of the starting lane and the ending lane, such as lane width, lane markings, traffic flow, and road curvature. Then, based on the collected attribute information, the traffic conditions and traffic rule restrictions of the ending lane (such as no-lane-changing zones, one-way zones, and continuous lane-changing rules) can be determined. Finally, based on the traffic conditions and traffic rule restrictions of the ending lane, an optimal lane can be selected as the optimal lane for the ending lane. This optimal lane can minimize conflicts with other vehicles and improve driving safety and efficiency.

[0047] Then, the initial predicted trajectory can be optimized in direction based on the starting lane and the optimized lane to obtain the intermediate predicted trajectory. For example, based on the positional relationship between the starting lane and the optimized lane, the steering angle that needs to be adjusted for each trajectory point in the initial predicted trajectory can be calculated. Then, while ensuring the safety of the predicted trajectory and meeting traffic rule restrictions, the direction of each trajectory point in the initial predicted trajectory can be adjusted to generate the intermediate predicted trajectory. At this time, the intermediate predicted trajectory can smoothly connect the starting lane and the optimized lane, and the time and speed corresponding to each trajectory point in the intermediate predicted trajectory have not changed and are still the same as the time and speed of the corresponding trajectory points in the initial predicted trajectory.

[0048] S130. Determine the preceding vehicle of the surrounding vehicles based on the intermediate predicted trajectory.

[0049] The "front vehicle" refers to the vehicle located to the left, right, or in front of the surrounding vehicles. For example, when the surrounding vehicles are changing lanes to the left, the vehicle located to the left and left front of the surrounding vehicles is identified as the front vehicle; when the surrounding vehicles are changing lanes to the right, the vehicle located to the right and right front of the surrounding vehicles is identified as the front vehicle; when the surrounding vehicles are in a lane-keeping state (i.e., not changing lanes), the vehicle located directly in front of the surrounding vehicles is identified as the front vehicle.

[0050] Specifically, after obtaining the intermediate predicted trajectory, the vehicle in front of the surrounding vehicles can be determined based on the intermediate predicted trajectory. That is, the lateral intentions of the surrounding vehicles, such as changing lanes to the left, changing lanes to the right, and keeping lanes, can be determined based on the lateral intentions.

[0051] Specifically, when the starting lane and the lane corresponding to the end point in the intermediate predicted trajectory are the same lane, it can be determined that the lateral intention of the surrounding vehicles is to keep their lane, and the vehicle directly in front of the surrounding vehicles is identified as the leading vehicle; when the lane corresponding to the end point in the intermediate predicted trajectory is to the left of the starting lane, it can be determined that the lateral intention of the surrounding vehicles is to change lanes to the left, and the vehicles to the left and left front of the surrounding vehicles are identified as the leading vehicles; when the lane corresponding to the end point in the intermediate predicted trajectory is to the right of the starting lane, it can be determined that the lateral intention of the surrounding vehicles is to change lanes to the right, and the vehicles to the right and right front of the surrounding vehicles are identified as the leading vehicles.

[0052] S140. Based on the intermediate predicted trajectory, determine the interaction trajectory points between the surrounding vehicles and the vehicle in front, and move the interaction trajectory points to obtain the optimized trajectory points of the interaction trajectory points.

[0053] Among them, the interaction trajectory points are the trajectory points in the intermediate predicted trajectory where the surrounding vehicles may interact with the vehicle in front.

[0054] Optimized trajectory points are more reasonable and safer predicted locations obtained by fine-tuning or moving interactive trajectory points. They take into account factors such as traffic rules, road conditions, vehicle dynamics, and safety, aiming to reduce the risk of collisions between vehicles.

[0055] Specifically, after identifying the vehicle in front of the surrounding vehicles, the interaction trajectory points between the surrounding vehicles and the vehicle in front can be determined based on the intermediate predicted trajectory. That is, the surrounding environment information, such as the position and speed of the vehicle in front, can be obtained using the sensors of the current vehicle. Then, based on the surrounding environment information and the intermediate predicted trajectory, the trajectory points where the surrounding vehicles and the vehicle in front may interact can be identified from the multiple trajectory points included in the intermediate predicted trajectory, and these trajectory points are determined as the interaction trajectory points.

[0056] Next, the optimized trajectory point of the interaction trajectory point can be obtained by moving the interaction trajectory point. That is, the position corresponding to the interaction trajectory point can be obtained from the intermediate predicted trajectory, then the movement strategy of the interaction trajectory point can be determined, and the position corresponding to the interaction trajectory point can be moved according to the movement strategy. For example, the position corresponding to the interaction trajectory point can be moved a random distance towards the trajectory endpoint to avoid collisions between surrounding vehicles and the vehicle in front at the interaction trajectory point. The random distance can be randomly set according to the actual situation while ensuring that surrounding vehicles do not collide with the vehicle in front.

[0057] S150. Based on the optimized trajectory points, the speed of the intermediate predicted trajectory is optimized to obtain the target predicted trajectory of the surrounding vehicles.

[0058] The target predicted trajectory is the final predicted trajectory obtained by optimizing the speed of each trajectory point in the intermediate predicted trajectory based on the optimized interactive trajectory points. Optionally, the target predicted trajectory may include multiple trajectory points and the state data of each trajectory point; the state data of the trajectory point may include the position, distance, time, speed, steering angle, and direction of travel of the trajectory point; speed optimization does not change the time and direction of travel of the trajectory point.

[0059] Specifically, after obtaining the optimized trajectory points, the speed of the intermediate predicted trajectory can be optimized based on these points. For example, the position of each trajectory point can be moved based on the moving distance (i.e., the distance between the interactive trajectory point and the optimized trajectory point). For instance, the position corresponding to each trajectory point can be moved by that distance towards the trajectory endpoint to obtain the target distance (i.e., the distance between the trajectory point and the trajectory start point). At this point, it is not necessary to move the position corresponding to the trajectory start point. Then, the ratio between the target distance corresponding to each trajectory point and the time corresponding to each trajectory point is calculated to obtain the target speed of surrounding vehicles at each trajectory point. Next, the target speed corresponding to each trajectory point is smoothed to ensure that the speed change is within a reasonable range, avoiding the impact of sudden acceleration or deceleration on passenger comfort and safety. Then, the smoothed target speed is combined with the target distance corresponding to each trajectory point to reconstruct the target predicted trajectory of surrounding vehicles. This considers both the interaction between vehicles and ensures the smoothness and safety of driving. Afterward, the generated target predicted trajectory can be verified to ensure that it meets the requirements of traffic rules, road conditions, and vehicle dynamics characteristics.

[0060] Optionally, after obtaining the target predicted trajectory, the vehicle controller of the current vehicle can determine the control strategy of the current vehicle (i.e., the control operation of the current vehicle in the future period) based on the target predicted trajectory, such as adjusting the vehicle speed and lane changing, so as to make decisions and plans for the vehicle. This allows the current vehicle to plan obstacle avoidance paths in advance, optimize driving speed and route, and effectively deal with emergencies, reduce traffic accidents, and thus ensure the safety and efficiency of the current vehicle during driving, thereby improving the driving safety of autonomous vehicles.

[0061] The technical solution of this application determines the optimized lane by using the starting and ending lanes of the initial predicted trajectory, and optimizes the direction based on the optimized lane. This makes the intermediate predicted trajectory more in line with actual traffic rules and driving habits, avoiding dangerous situations such as changing two or more lanes at once. It effectively avoids the problem of unreasonable driving scenarios that may occur due to insufficient consideration of the rationality of lane lines and vehicle driving in the prediction results of the prior art, thereby improving the rationality and accuracy of the target predicted trajectory. By introducing the preceding vehicle of surrounding vehicles and the movement interaction trajectory points to obtain the optimized trajectory points, and optimizing the speed based on the optimized trajectory points, the target predicted trajectory is closer to the actual driving scenario, avoiding dangerous situations such as collisions between surrounding vehicles and the preceding vehicle. This effectively avoids the problem of unreasonable driving scenarios that may occur due to insufficient consideration of environmental vehicles (i.e., the preceding vehicle of surrounding vehicles) in the prediction results of the prior art, thereby improving the rationality and accuracy of the target predicted trajectory. By optimizing the initial predicted trajectory at multiple levels, the current vehicle can better cope with various uncertainties and changing factors, and can plan obstacle avoidance paths in advance, optimize driving speed and route, making the autonomous driving system more reliable and stable, thereby improving the driving safety of autonomous vehicles and enhancing the user experience.

[0062] The following further describes a method for optimizing the predicted trajectories of surrounding vehicles provided by embodiments of this application. Figure 2 This is another flowchart illustrating the method for optimizing the predicted trajectory of surrounding vehicles provided in this application. This application embodiment is a detailed refinement of the process of "determining the optimized lane for the endpoint lane based on the positions of the starting lane and the endpoint lane, and optimizing the direction of the initial predicted trajectory based on the starting lane and the optimized lane to obtain the intermediate predicted trajectory." See also... Figure 2 The method in this embodiment includes, but is not limited to, the following steps:

[0063] S201. Determine lane change conditions based on the positions of the starting lane and the ending lane.

[0064] Lane changing refers to situations where a vehicle needs to change from its current lane to another lane due to factors such as road conditions, traffic rules, or driving needs. Lane changing situations can include single lane changes, continuous lane changes, and no lane changes.

[0065] Specifically, the positional relationship between the starting lane and the ending lane can be determined based on their positions, and lane changing situations can be determined based on this relationship.

[0066] Specifically, if the starting lane and the ending lane are the same lane, it indicates that the surrounding vehicles are in a lane-keeping state, and the lane change situation can be determined as no lane change; if the starting lane and the ending lane are not the same lane, and the ending lane is adjacent to the starting lane, it indicates that the surrounding vehicles are in a single lane change state, and the lane change situation can be determined as a single lane change; if the starting lane and the ending lane are not the same lane, and the ending lane is not adjacent to the starting lane, it indicates that the surrounding vehicles are in a continuous lane change state, and the lane change situation can be determined as a continuous lane change.

[0067] For example, such as Figure 3 The diagram shown is an example of a lane network provided in an embodiment of this application. Figure 3 The location of the surrounding vehicles is the starting point of the initial predicted trajectory. At this time, the starting lane corresponding to the starting point of the trajectory is lane 2. If the ending point of the initial predicted trajectory is in lane 4, it means that the ending lane is lane 4 and the lane change is continuous. If the ending point of the initial predicted trajectory is in lane 3, it means that the ending lane is lane 3 and the lane change is single. If the ending point of the initial predicted trajectory is in lane 2, it means that the ending lane is lane 2 and the lane change is no lane change.

[0068] S202. Determine whether the lane change situation is "no lane change".

[0069] Specifically, after obtaining the lane change information, it can be determined whether the lane change is not a lane change. If the lane change is not a lane change, it indicates that the initial predicted trajectory meets the lane change rules, and S203 can be executed at this time; if the lane change is not a lane change, S207 can be executed to continue to determine whether the initial predicted trajectory meets the lane change rules.

[0070] S203. When the lane change situation is no lane change, determine the lane corresponding to the midpoint of the initial predicted trajectory.

[0071] The middle point lane is the lane where the midpoint of the trajectory is located in the initial predicted trajectory; the midpoint of the trajectory does not include the trajectory start point and trajectory end point.

[0072] Specifically, when the lane change situation is "no lane change", it indicates that the surrounding vehicles are in the lane-keeping state. At this time, the middle point lane corresponding to the middle point of the initial predicted trajectory can be determined. That is, each middle point of the initial predicted trajectory can be traversed, and based on the position of each middle point and the high-precision map information, the lane line detection algorithm can be used to determine the middle point lane corresponding to each middle point.

[0073] S204. Determine whether the intermediate point lane and the starting point lane are the same lane.

[0074] Specifically, after determining the intermediate lane corresponding to each intermediate point of the trajectory, it can be determined whether the intermediate lane is the same lane as the starting lane. If each intermediate lane is the same lane as the starting lane, S206 can be executed; if there is an intermediate lane that is not the same lane as the starting lane, S205 can be executed.

[0075] S205. When the intermediate point lane and the starting lane are not the same lane, the direction of the initial predicted trajectory is optimized based on the starting lane and the ending lane to obtain the intermediate predicted trajectory.

[0076] In this case, the lanes corresponding to each trajectory point in the intermediate predicted trajectory are the same as the starting lane.

[0077] Specifically, when the intermediate point lane is not the same as the starting lane, the direction of the initial predicted trajectory can be optimized based on the starting and ending lanes to obtain the intermediate predicted trajectory. That is, based on the starting and ending lanes, the turning angle that needs to be adjusted for each intermediate point in the initial predicted trajectory can be calculated. Then, while ensuring the safety of the predicted trajectory and meeting traffic rule restrictions, the direction of each intermediate point in the initial predicted trajectory is adjusted to generate the intermediate predicted trajectory. The lanes corresponding to each trajectory point in the intermediate predicted trajectory are the same as the starting lane. At this time, the intermediate predicted trajectory can smoothly connect the starting and ending lanes, and the time and speed corresponding to each intermediate point in the intermediate predicted trajectory have not changed and are still the same as the time and speed of the corresponding intermediate point in the initial predicted trajectory.

[0078] For example, such as Figure 4 The image shown is an example diagram of a direction-optimized initial predicted trajectory provided in an embodiment of this application. Figure 4 In section 'a', the orange curve represents the initial predicted trajectory. The starting lane of the initial predicted trajectory corresponds to lane 2, and the ending lane corresponds to lane 2. At this point, the initial predicted trajectory shows no lane change. Furthermore, based on the starting and ending lanes, the initial predicted trajectory is optimized for direction, resulting in the intermediate predicted trajectory. Figure 4 The orange straight line in b represents lane 2, which corresponds to each trajectory point in the intermediate predicted trajectory.

[0079] S206. When the intermediate point lane and the starting point lane are the same lane, the initial predicted trajectory is determined as the intermediate predicted trajectory.

[0080] Specifically, when each intermediate point lane is the same lane as the starting lane, it indicates that there is no need to optimize the direction of the initial predicted trajectory. In this case, the initial predicted trajectory can be directly determined as the intermediate predicted trajectory.

[0081] S207. When the lane change situation is not a non-lane change, determine whether the lane change situation is a continuous lane change.

[0082] Specifically, when the lane change situation is not a non-lane change, it can be determined whether the lane change situation is a continuous lane change. If the lane change situation is a continuous lane change, it indicates that the initial predicted trajectory does not meet the lane change rules (i.e., it is not allowed to change two or more lanes at once), and S208 can be executed at this time; if the lane change situation is a single lane change, it indicates that the lane change situation is not a continuous lane change, that is, the initial predicted trajectory meets the lane change rules, and S211 can be executed at this time.

[0083] S208. When changing lanes continuously, the direction of lane change shall be determined based on the position of the starting lane and the position of the ending lane.

[0084] The lane change direction refers to the direction chosen by surrounding vehicles when changing lanes; the lane change direction can include changing lanes to the left and changing lanes to the right.

[0085] Specifically, when the lane change is a continuous lane change, the direction of the lane change can be determined based on the position of the starting lane and the ending lane. That is, if the ending lane is to the left of the starting lane, the direction of the lane change can be determined as a left lane change; if the ending lane is to the right of the starting lane, the direction of the lane change can be determined as a right lane change.

[0086] For example, such as Figure 3 As shown, the starting lane corresponding to the starting point of the trajectory is lane 2; if the ending lane is lane 4, then the lane change direction is left lane change.

[0087] S209. Determine the adjacent lanes of the starting lane based on the lane change direction, and identify the adjacent lanes as the optimized lanes.

[0088] The adjacent lane is the lane that is adjacent to the starting lane in the direction of the lane change.

[0089] Specifically, after determining the lane-changing direction, the adjacent lanes of the starting lane in the lane-changing direction can be identified as optimized lanes. For example, such as... Figure 3 As shown, if the starting lane corresponding to the trajectory start point is lane 2 and the ending lane corresponding to the trajectory end point is lane 4, then the lane change direction is left lane change. At this time, it can be determined that lane 3 is the adjacent lane of lane 2 on the left lane change, and lane 3 is determined as the optimized lane.

[0090] S210. Optimize the direction of the initial predicted trajectory based on the starting lane and the optimized lane to obtain the intermediate predicted trajectory.

[0091] Among them, the lane corresponding to the endpoint in the intermediate predicted trajectory is the optimized lane.

[0092] Specifically, after obtaining the optimized lane, the initial predicted trajectory can be optimized in direction based on the starting lane and the optimized lane to obtain the intermediate predicted trajectory. For example, based on the positional relationship between the starting lane and the optimized lane, the steering angle that needs to be adjusted for each trajectory point in the initial predicted trajectory can be calculated. Then, while ensuring the safety of the predicted trajectory and meeting traffic rule restrictions, the direction of each trajectory point in the initial predicted trajectory is adjusted to generate the intermediate predicted trajectory. The lane corresponding to the end point in the intermediate predicted trajectory is the optimized lane. At this time, the intermediate predicted trajectory can smoothly connect the starting lane and the optimized lane, and the time and speed corresponding to each trajectory point in the intermediate predicted trajectory have not changed and are still the same as the time and speed of the corresponding trajectory points in the initial predicted trajectory.

[0093] For example, such as Figure 5 The figure shown is another example diagram of the orientation-optimized initial predicted trajectory provided in the embodiments of this application. Figure 5 In equation c, the orange curve represents the initial predicted trajectory. The starting lane of the initial predicted trajectory is lane 2, and the ending lane is lane 4. At this point, the initial predicted trajectory involves continuous lane changes, with the lane change direction being left. Based on the lane change direction, the optimized lane is lane 3. Furthermore, the initial predicted trajectory is optimized in direction based on the starting lane and the optimized lane, resulting in the intermediate predicted trajectory. Figure 5 The orange curve in d represents the starting lane of the intermediate predicted trajectory, which is lane 2, and the ending lane is lane 3 (i.e., the lane corresponding to the ending lane in the intermediate predicted trajectory is the optimized lane).

[0094] S211. When the lane change is a single lane change, the initial predicted trajectory is determined as the intermediate predicted trajectory.

[0095] Specifically, when the lane change is a single lane change, it indicates that the initial predicted trajectory meets the lane change rules, and there is no need to optimize the direction of the initial predicted trajectory. In this case, the initial predicted trajectory can be directly determined as the intermediate predicted trajectory.

[0096] It should be noted that the execution of S203 to S206 and S207 to S211 has no obvious order and can be determined according to the actual situation. This embodiment does not make a specific limitation on this. The execution of S205 and S206 has no obvious order and can be determined according to the actual situation. This embodiment does not make a specific limitation on this. The execution of S208 to S210 and S211 has no obvious order and can be determined according to the actual situation. This embodiment does not make a specific limitation on this.

[0097] The technical solution of this application embodiment can determine the lane change situation based on the position of the starting lane and the ending lane, i.e., single lane change, continuous lane change, and no lane change. When the lane change situation is no lane change, the intermediate point lane corresponding to the intermediate point of the initial predicted trajectory is determined. Then, when the intermediate point lane is not the same lane as the starting lane, the direction of the initial predicted trajectory is optimized based on the starting lane and the ending lane to obtain the intermediate predicted trajectory. At this time, the lanes corresponding to each trajectory point in the intermediate predicted trajectory are the same as the starting lane, which can maintain the stable driving of the vehicle in the current lane, avoid unnecessary lane changes, and reduce the safety hazards caused by lane changes. This effectively improves the rationality of the intermediate predicted trajectory when there is no lane change, thereby improving the accuracy of the determination of the intermediate predicted trajectory. This provides data support for subsequently determining the target prediction trajectory. In the case of continuous lane changes, the lane change direction is determined based on the positions of the starting and ending lanes. Then, the adjacent lanes of the starting lane are determined based on the lane change direction, and these adjacent lanes are designated as optimized lanes. The initial prediction trajectory is then optimized based on the starting lane and the optimized lanes to obtain the intermediate prediction trajectory. By determining the lane change direction and the optimized lanes, the rationality of the intermediate prediction trajectory in lane change situations can be improved, effectively avoiding the occurrence of continuous lane changes. This improves the accuracy of determining the intermediate prediction trajectory, provides data support for subsequently determining the target prediction trajectory, and provides strong protection for the driving safety and traffic efficiency of autonomous vehicles, thereby improving the driving safety of autonomous vehicles.

[0098] The following further describes a method for optimizing the predicted trajectories of surrounding vehicles provided by embodiments of this application. Figure 6 This is another flowchart illustrating the method for optimizing the predicted trajectory of surrounding vehicles provided in this application. This application embodiment is a detailed refinement of the process of "determining the interaction trajectory points between surrounding vehicles and the vehicle in front based on the intermediate predicted trajectory, and moving the interaction trajectory points to obtain optimized trajectory points; optimizing the speed of the intermediate predicted trajectory based on the optimized trajectory points to obtain the target predicted trajectory of the surrounding vehicles," and a detailed explanation of determining the longitudinal intent of the surrounding vehicles after optimizing the speed of the intermediate predicted trajectory based on the optimized trajectory points to obtain the target predicted trajectory of the surrounding vehicles. See also... Figure 6 The method in this embodiment includes, but is not limited to, the following steps:

[0099] S601. Determine the interaction trajectory points between surrounding vehicles and the vehicle in front based on the intermediate predicted trajectory.

[0100] S602. Obtain the first speed of surrounding vehicles at the interaction trajectory point, and obtain the second speed of the vehicle in front at the interaction trajectory point.

[0101] The first speed is the speed of surrounding vehicles when they reach the interaction trajectory point. The second speed is the speed of the vehicle in front when it reaches the interaction trajectory point.

[0102] Specifically, after obtaining the interaction trajectory points, the speed corresponding to the interaction trajectory points can be obtained from the intermediate predicted trajectory and determined as the first speed. Then, using the current vehicle's sensors (such as cameras, lidar, and millimeter-wave radar), the speed of the preceding vehicle at the interaction trajectory points can be obtained and determined as the second speed.

[0103] S603. Determine whether the first speed is greater than the second speed.

[0104] Specifically, after obtaining the first speed and the second speed, it can be determined whether the first speed is greater than the second speed; if the first speed is greater than the second speed, it indicates that there is a collision risk between the surrounding vehicles and the vehicle in front, and S604 can be executed at this time; if the first speed is not greater than the second speed, it indicates that there is no collision risk between the surrounding vehicles and the vehicle in front, and S609 can be executed at this time.

[0105] S604. When the first speed is greater than the second speed, the interactive trajectory point is moved a preset distance towards the trajectory starting point to obtain the optimized trajectory point.

[0106] The preset distance is a pre-set value used to represent the movement distance of the interactive trajectory point. Users can adjust and set the preset distance according to actual usage needs. This application embodiment does not specifically limit this.

[0107] For example, such as Figure 7 The image shown is an example diagram of a velocity optimization intermediate prediction trajectory provided in an embodiment of this application. Figure 7 The orange curve in 'e' represents the intermediate predicted trajectory, and based on this intermediate predicted trajectory, the interaction trajectory point between the surrounding vehicles and the vehicle in front is determined as 's_pre'. When the first speed of the surrounding vehicles at the interaction trajectory point is 60 km / h, and the second speed of the vehicle in front at the interaction trajectory point is 55 km / h, with a preset distance of 2m, the first speed is greater than the second speed, indicating a collision risk between the surrounding vehicles and the vehicle in front. In this case, the interaction trajectory point can be moved 2m towards the trajectory starting point to obtain the optimized trajectory point. Figure 7 s_new in f.

[0108] S605. Determine the trajectory shrinkage ratio based on the interactive trajectory points and the optimized trajectory points.

[0109] The trajectory shrinkage ratio is a parameter that describes the relationship between the intermediate predicted trajectory and the target predicted trajectory, reflecting the degree to which the intermediate predicted trajectory needs to be shrunk.

[0110] Specifically, after obtaining the optimized trajectory points, the position and distance corresponding to the interactive trajectory points can be extracted from the intermediate predicted trajectory. Then, the position corresponding to the optimized trajectory points is determined based on the preset distance and the position corresponding to the interactive trajectory points. Then, the target distance between the optimized trajectory points and the trajectory starting point is determined based on the position corresponding to the optimized trajectory points and the position corresponding to the trajectory starting point. Finally, the ratio between the target distance and the distance corresponding to the interactive trajectory points is calculated to obtain the trajectory shrinkage ratio.

[0111] Optionally, the speed of each trajectory point in the intermediate predicted trajectory is optimized based on the trajectory contraction ratio to obtain the target predicted trajectory of the surrounding vehicles. Each trajectory point excludes the trajectory start point; that is, speed optimization is not performed on the trajectory start point in the intermediate predicted trajectory. In this embodiment, optimizing the speed of the intermediate predicted trajectory based on the trajectory contraction ratio can effectively avoid collisions between surrounding vehicles and the vehicle in front, thereby improving the accuracy and rationality of the target predicted trajectory and thus enhancing the driving safety of the current vehicle.

[0112] S606. Based on the trajectory shrinkage ratio, the distance corresponding to each trajectory point is shrunk proportionally to obtain the corrected distance corresponding to each trajectory point.

[0113] The corrected distance is the new distance between the trajectory point and the trajectory starting point after the trajectory points in the intermediate predicted trajectory are proportionally shrunk.

[0114] Specifically, after obtaining the trajectory contraction ratio, any trajectory point can be selected from multiple trajectory points in the intermediate predicted trajectory as the current trajectory point. Then, the product of the distance corresponding to the current trajectory point and the trajectory contraction ratio is calculated, and this product is determined as the correction distance corresponding to the current trajectory point. Afterward, other trajectory points can be selected as the current trajectory point, and the above process is repeated to obtain the correction distance corresponding to each trajectory point. It should be noted that the trajectory point selected from the multiple trajectory points in the intermediate predicted trajectory does not include the trajectory starting point.

[0115] S607. Optimize the velocity corresponding to each trajectory point to obtain the corrected velocity for each trajectory point.

[0116] The corrected speed is the new speed of the trajectory point after speed optimization of the trajectory point in the intermediate predicted trajectory.

[0117] Specifically, the velocity corresponding to each trajectory point is optimized to obtain the corrected velocity for each trajectory point, including Sa1-Sa3:

[0118] Sa1. For each trajectory point, determine whether the distance corresponding to the current trajectory point is less than the distance corresponding to the interactive trajectory point.

[0119] Specifically, for each trajectory point in the intermediate predicted trajectory, any trajectory point other than the trajectory starting point can be selected as the current trajectory point, and it is determined whether the distance corresponding to the current trajectory point is less than the distance corresponding to the interaction trajectory point. If the distance corresponding to the current trajectory point is less than the distance corresponding to the interaction trajectory point, it indicates that the current trajectory point is the trajectory point before the surrounding vehicles enter the interaction area, and Sa2 can be executed at this time; if the distance corresponding to the current trajectory point is not less than the distance corresponding to the interaction trajectory point, it indicates that the current trajectory point is the trajectory point after the surrounding vehicles enter the interaction area, and Sa3 can be executed at this time.

[0120] Sa2. When the distance to the current trajectory point is less than the distance to the interactive trajectory point, determine the correction speed corresponding to the current trajectory point based on the correction distance corresponding to each trajectory point.

[0121] Specifically, in one implementation, when the distance corresponding to the current trajectory point is less than the distance corresponding to the interaction trajectory point, deceleration prediction of surrounding vehicles can be performed before the interaction occurs. That is, the time corresponding to the current trajectory point can be obtained from the intermediate predicted trajectory, and then the corrected speed corresponding to the current trajectory point can be determined based on the corrected distance and the time corresponding to the current trajectory point. That is, the ratio between the corrected distance and the time corresponding to the current trajectory point is calculated, and this ratio is determined as the corrected speed corresponding to the current trajectory point. At this time, the corrected distance is less than the distance corresponding to the current trajectory point, so the corrected speed is less than the speed.

[0122] Specifically, in another implementation, the correction velocity corresponding to the current trajectory point is determined based on the correction distance corresponding to each trajectory point, including Sb1-Sb3:

[0123] Sb1. Select a trajectory point corresponding to a first preset distance from the current trajectory point toward the trajectory starting point to obtain the first trajectory point.

[0124] The first preset distance is a pre-set value used to determine the distance that needs to be reached when searching from the current trajectory point to the trajectory starting point. Users can adjust and set it according to actual usage. This application embodiment does not make specific limitations on this.

[0125] The first trajectory point is the trajectory point reached after moving a first preset distance from the position corresponding to the current trajectory point towards the trajectory starting point.

[0126] Specifically, starting from the position corresponding to the current trajectory point, the trajectory points can be traversed in the direction of the trajectory starting point. For each traversed trajectory point, the distance between it and the current trajectory point is calculated. When the first trajectory point with a distance greater than or equal to the first preset distance is found, the search is stopped and the trajectory point is determined as the first trajectory point.

[0127] Sb2. Select a trajectory point corresponding to the second preset distance from the current trajectory point towards the trajectory endpoint to obtain the second trajectory point.

[0128] The second preset distance is a pre-set value used to determine the distance required to search from the current trajectory point towards the trajectory endpoint. Users can adjust and set this distance according to actual usage; this embodiment does not impose specific limitations on it. It should be noted that the first and second preset distances can be equal or unequal.

[0129] The second trajectory point is the trajectory point reached after moving a second preset distance from the position corresponding to the current trajectory point towards the trajectory endpoint.

[0130] Specifically, starting from the position corresponding to the current trajectory point, the trajectory points can be traversed towards the trajectory endpoint. For each traversed trajectory point, the distance between it and the current trajectory point is calculated. When the first trajectory point with a distance greater than or equal to the second preset distance is found, the search is stopped, and the trajectory point is determined as the second trajectory point.

[0131] Sb3. Determine the correction speed corresponding to the current trajectory point based on the correction distance corresponding to the first trajectory point, the time corresponding to the first trajectory point, the correction distance corresponding to the second trajectory point, and the time corresponding to the second trajectory point.

[0132] The time corresponding to the first trajectory point is the time required for surrounding vehicles to travel from the trajectory start point to the first trajectory point, which is the time corresponding to the first trajectory point in the intermediate predicted trajectory. The time corresponding to the second trajectory point is the time required for surrounding vehicles to travel from the trajectory start point to the second trajectory point, which is the time corresponding to the second trajectory point in the intermediate predicted trajectory.

[0133] Specifically, after obtaining the first trajectory point and the second trajectory point, the correction distance corresponding to the first trajectory point, the time corresponding to the first trajectory point, the correction distance corresponding to the second trajectory point, and the time corresponding to the second trajectory point can be obtained. Then, the difference between the correction distance corresponding to the second trajectory point and the correction distance corresponding to the first trajectory point (denoted as the distance difference) is calculated, and the difference between the time corresponding to the second trajectory point and the time corresponding to the first trajectory point (denoted as the time difference) is calculated. After that, the ratio between the distance difference and the time difference is calculated, and this ratio is determined as the correction speed corresponding to the current trajectory point.

[0134] In this embodiment, determining the correction speed based on the information of the first trajectory point and the second trajectory point can maintain the smoothness of the correction speed, avoid the discomfort caused by sudden speed changes, and thus improve the rationality of the target prediction trajectory; furthermore, it improves the accuracy of the correction speed determination, provides data support for the subsequent determination of the target prediction trajectory, and thus improves the accuracy of the target prediction trajectory.

[0135] Sa3. When the distance to the current trajectory point is not less than the distance to the interaction trajectory point, determine the corrected speed corresponding to the current trajectory point based on the second speed of the preceding vehicle at the interaction trajectory point.

[0136] Specifically, when the distance corresponding to the current trajectory point is not less than the distance corresponding to the interaction trajectory point, it indicates that the current trajectory point is the trajectory point after the surrounding vehicles enter the interaction area, and the deceleration prediction of the surrounding vehicles has been performed before entering the interaction area. Therefore, the surrounding vehicles have already maintained a safe distance from the vehicle in front when they reach the interaction trajectory point, and there is no need to continue to decelerate. Thus, the second speed of the vehicle in front at the interaction trajectory point can be directly determined as the corrected speed corresponding to the current trajectory point.

[0137] Then, other trajectory points can be selected from the trajectory points other than the trajectory starting point as the current trajectory point, and Sa1-Sa3 can be executed repeatedly to obtain the corrected speed corresponding to each trajectory point.

[0138] For example, the intermediate predicted trajectory is {trajectory start point, intermediate point 1, intermediate point 2, intermediate point 3, trajectory end point}, the distance corresponding to each trajectory point in the intermediate predicted trajectory is {0, 2, 4, 6, 8}, and the unit of distance is meters (m). The correction distance corresponding to each trajectory point in the intermediate predicted trajectory is {0, 1, 2, 3, 4}, and the time corresponding to each trajectory point in the intermediate predicted trajectory is {0, 0.1, 0.2, 0.3, 0.4}, and the unit of time is seconds (s). If the interaction trajectory point is intermediate point 3, and the second speed of the preceding vehicle at the interaction trajectory point is 20 m / s, then the distance corresponding to intermediate point 1 (i.e., 2 m) and the distance corresponding to intermediate point 2 (i.e., 4 m) are less than the distance corresponding to the interaction trajectory point (i.e., 6 m), and the distance corresponding to intermediate point 3 (i.e., 6 m) and the distance corresponding to the trajectory end point (i.e., 8 m) are not less than the distance corresponding to the interaction trajectory point (i.e., 6 m).

[0139] When the first preset distance is 2m and the second preset distance is 2m, the process for determining the corrected speed corresponding to the intermediate point 1 can be as follows: the first trajectory point can be determined as the trajectory start point, the second trajectory point as the intermediate point 2, then the distance difference can be determined as 4m (i.e., 4-0), the time difference as 0.2s (i.e., 0.2-0), and then the corrected speed corresponding to the intermediate point 1 can be determined as 20m / s; the process for determining the corrected speed corresponding to the intermediate point 2 can be as follows: the first trajectory point can be determined as the intermediate point 1, the second trajectory point as the intermediate point 3, then the distance difference can be determined as 4m (i.e., 6-2), the time difference as 0.2s (i.e., 0.3-0.1), and then the corrected speed corresponding to the intermediate point 2 can be determined as 20m / s; the corrected speed corresponding to the intermediate point 3 is the second speed of the preceding vehicle at the interaction trajectory point, i.e., 20m / s; the corrected speed corresponding to the trajectory end point is the second speed of the preceding vehicle at the interaction trajectory point, i.e., 20m / s.

[0140] In this embodiment, when the distance to the current trajectory point is less than the distance to the interactive trajectory point, the correction speed is determined based on the correction distance. This can appropriately reduce the speed of the trajectory point before entering the interactive area, maintaining a safe distance between surrounding vehicles and the vehicle in front, thereby effectively avoiding collisions. When the distance to the current trajectory point is not less than the distance to the interactive trajectory point, the correction speed is determined based on the second speed. This allows the speed of the trajectory point after entering the interactive area to be closer to the actual traffic flow speed. By reasonably adjusting the correction speed under different distance conditions, the accuracy of the correction speed determination is improved, thereby improving the rationality and accuracy of the target predicted trajectory.

[0141] S608. Determine the target predicted trajectory based on the correction distance and correction velocity corresponding to each trajectory point.

[0142] Specifically, after obtaining the corrected velocity corresponding to each trajectory point, the corrected distance and corrected velocity corresponding to each trajectory point can be combined with the time and driving direction corresponding to each trajectory point in the intermediate predicted trajectory to reconstruct the target predicted trajectory of the surrounding vehicles. Then, S610 can be executed.

[0143] For example, such as Figure 7 As shown, Figure 7 The orange curve in f represents the target predicted trajectory obtained after speed optimization of the intermediate predicted trajectory. When surrounding vehicles are traveling along the target predicted trajectory, there are no interaction trajectory points between the surrounding vehicles and the vehicle in front.

[0144] S609. When the first speed is not greater than the second speed, the intermediate predicted trajectory is determined as the target predicted trajectory.

[0145] Specifically, when the first speed is no greater than the second speed, it indicates that there is no risk of collision between the surrounding vehicles and the vehicle in front, and there is no need to optimize the speed of the intermediate predicted trajectory. At this time, the intermediate predicted trajectory can be directly determined as the target predicted trajectory. Then, S610 can be executed.

[0146] S610. Obtain the starting speed of surrounding vehicles at the starting point of the trajectory, and determine the target distance and target time of the target trajectory point in the target predicted trajectory.

[0147] The starting speed is the speed of the surrounding vehicles at the current moment, that is, the speed of the surrounding vehicles at the starting point of the trajectory.

[0148] The target trajectory point is a trajectory point randomly selected from multiple trajectory points in the target predicted trajectory, and the target trajectory point is not the starting point of the target predicted trajectory; the target distance is the corrected distance corresponding to the target trajectory point, that is, the distance between the target trajectory point and the trajectory starting point; the target time is the time required for surrounding vehicles to travel from the trajectory starting point to the target trajectory point, that is, the time corresponding to the target trajectory point in the target predicted trajectory.

[0149] Specifically, after obtaining the target predicted trajectory, the current speed of surrounding vehicles can be collected in real time using the current vehicle's sensors (such as cameras, lidar, and millimeter-wave radar) to obtain the starting speed of surrounding vehicles at the trajectory start point. Then, from the multiple trajectory points of the target predicted trajectory, a trajectory point other than the trajectory start point can be randomly selected as the target trajectory point. After that, the distance (i.e., the corrected distance) and the time corresponding to the target trajectory point are obtained from the target predicted trajectory. The distance corresponding to the target trajectory point is determined as the target distance, and the time corresponding to the target trajectory point is determined as the target time.

[0150] S611. Calculate the distance traveled by surrounding vehicles from the starting point of the trajectory at the starting speed to the target distance in the specified time, and obtain the predetermined distance.

[0151] The predetermined distance is the distance that surrounding vehicles would travel in the target time while maintaining a constant speed from the starting point.

[0152] Specifically, after obtaining the starting speed, target distance, and target time, the product of the starting speed and target time can be calculated, and this product can be determined as the predetermined distance.

[0153] S612. Determine the longitudinal intentions of surrounding vehicles based on the target distance and the predetermined distance.

[0154] Among them, longitudinal intention refers to the driving intention of surrounding vehicles in the longitudinal direction (i.e., the direction of travel).

[0155] Specifically, after obtaining the predetermined distance, the relationship between the target distance and the predetermined distance can be determined, and the longitudinal intention of surrounding vehicles can be determined based on this relationship. That is, when the target distance is greater than the sum of the predetermined distance and the set threshold, the longitudinal intention of surrounding vehicles is determined to be acceleration; when the target distance is less than the sum of the predetermined distance and the set threshold, the longitudinal intention of surrounding vehicles is determined to be deceleration; and when the target distance is equal to the sum of the predetermined distance and the set threshold, the longitudinal intention of surrounding vehicles is determined to be constant speed. The set threshold is a pre-set value used to characterize a safety distance or buffer distance, providing additional considerations when judging the longitudinal intention of surrounding vehicles. Users can adjust and set it according to actual usage, and this application embodiment does not specifically limit this. In this application embodiment, the set threshold provides a fault-tolerant mechanism, enabling relatively accurate judgments even when faced with small changes in vehicle speed, measurement errors, or changes in road conditions, thereby ensuring the accuracy and reliability of the longitudinal intention. By adjusting the size of the set threshold, the sensitivity and robustness of the judgment can be balanced to adapt to different application scenarios and needs.

[0156] Optionally, after determining the longitudinal intent, the current vehicle's controller can determine the current vehicle's control strategy based on the longitudinal intent of surrounding vehicles, thereby making decisions and plans for the vehicle.

[0157] In the technical solution provided in this application embodiment, the interaction trajectory points between surrounding vehicles and the vehicle in front can be determined based on the intermediate predicted trajectory. Next, the first speed of the surrounding vehicles at the interaction trajectory points and the second speed of the vehicle in front at the interaction trajectory points are obtained. Then, when the first speed is greater than the second speed, the interaction trajectory points are moved a preset distance towards the trajectory starting point to obtain optimized trajectory points. This ensures that a sufficient safe distance is maintained between the surrounding vehicles and the vehicle in front, effectively avoiding collisions between them. This provides data support for determining the trajectory contraction ratio, thereby improving the rationality and accuracy of speed optimization. Then, the trajectory contraction ratio can be determined based on the interaction trajectory points and optimized trajectory points. Based on the trajectory contraction ratio, the distance corresponding to each trajectory point is proportionally contracted to obtain the corrected distance for each trajectory point. Then, the speed corresponding to each trajectory point is optimized to obtain the corrected speed for each trajectory point. Finally, the target predicted trajectory is determined based on the corrected distance and corrected speed for each trajectory point. By optimizing the distance and speed corresponding to each trajectory point, the target predicted trajectory becomes closer to the actual driving situation, thereby improving the accuracy and rationality of the target predicted trajectory and thus enhancing the driving safety of autonomous vehicles.

[0158] Next, the starting speeds of surrounding vehicles at the trajectory start point are obtained, and the target distance and target time of the target trajectory point in the target predicted trajectory are determined. Then, the distance traveled by surrounding vehicles from the trajectory start point at the starting speed within the target time is calculated to obtain the predetermined distance. Based on the target distance and the predetermined distance, the longitudinal intention of surrounding vehicles is determined, thus realizing the function of determining longitudinal intention. By observing the relationship between the target distance and the predetermined distance, the driving intention of surrounding vehicles in the driving direction can be accurately determined, thereby improving the accuracy and efficiency of determining longitudinal intention. Furthermore, autonomous vehicles can adjust their driving strategies according to longitudinal intention, making safe driving decisions such as avoidance and deceleration in advance, thereby reducing the risk of traffic accidents and improving the driving safety of autonomous vehicles.

[0159] Figure 8 This is a schematic diagram of a device for optimizing the predicted trajectory of surrounding vehicles provided in an embodiment of this application. (Refer to...) Figure 8 The device for optimizing the predicted trajectories of surrounding vehicles may include:

[0160] The lane determination module 810 is used to obtain the initial predicted trajectory of the surrounding vehicles of the current vehicle and determine the starting lane corresponding to the starting point of the initial predicted trajectory and the ending lane corresponding to the ending point of the trajectory.

[0161] The direction optimization module 820 is used to determine the optimized lane of the end lane based on the position of the starting lane and the position of the end lane, and to optimize the direction of the initial predicted trajectory based on the starting lane and the optimized lane to obtain the intermediate predicted trajectory.

[0162] The preceding vehicle determination module 830 is used to determine the preceding vehicle of surrounding vehicles based on the intermediate predicted trajectory.

[0163] The trajectory point optimization module 840 is used to determine the interaction trajectory points between the surrounding vehicles and the vehicle in front based on the intermediate predicted trajectory, and to move the interaction trajectory points to obtain the optimized trajectory points of the interaction trajectory points.

[0164] The speed optimization module 850 is used to optimize the speed of the intermediate predicted trajectory based on the optimized trajectory points, so as to obtain the target predicted trajectory of the surrounding vehicles.

[0165] In one embodiment, the surrounding vehicle trajectory optimization device further includes a continuous lane change optimization module, which is specifically used to: determine the lane change situation based on the position of the starting lane and the position of the ending lane before determining the optimized lane of the ending lane based on the position of the starting lane and the position of the ending lane; and when the lane change situation is continuous lane change, trigger the execution of determining the optimized lane of the ending lane based on the position of the starting lane and the position of the ending lane.

[0166] In one embodiment, the surrounding vehicle trajectory optimization device further includes a lane-change optimization module, which is specifically used to: after determining the lane-change situation based on the position of the starting lane and the position of the ending lane, when the lane-change situation is no lane change, determine the intermediate lane corresponding to the intermediate point of the initial predicted trajectory; when the intermediate lane is not the same lane as the starting lane, optimize the direction of the initial predicted trajectory based on the starting lane and the ending lane to obtain the intermediate predicted trajectory; the lanes corresponding to each trajectory point in the intermediate predicted trajectory are the same as the starting lane.

[0167] In one embodiment, the direction optimization module 820 determines the optimized lane of the endpoint lane based on the position of the starting lane and the position of the endpoint lane, including: determining the lane change direction based on the position of the starting lane and the position of the endpoint lane; determining the adjacent lane of the starting lane based on the lane change direction, and determining the adjacent lane as the optimized lane; correspondingly, the lane corresponding to the endpoint in the intermediate predicted trajectory is the optimized lane.

[0168] In one embodiment, the surrounding vehicle trajectory optimization device further includes a collision optimization module, which is specifically used to: obtain the first speed of the surrounding vehicles at the interaction trajectory point and the second speed of the preceding vehicle at the interaction trajectory point before moving the interaction trajectory point to obtain the optimized trajectory point; and trigger the execution of moving the interaction trajectory point to obtain the optimized trajectory point when the first speed is greater than the second speed.

[0169] In one embodiment, the trajectory point optimization module 840 moves the interactive trajectory point to obtain an optimized trajectory point, including: moving the interactive trajectory point a preset distance towards the trajectory starting point to obtain the optimized trajectory point.

[0170] In one embodiment, the speed optimization module 850 optimizes the speed of the intermediate predicted trajectory based on the optimized trajectory points to obtain the target predicted trajectory of the surrounding vehicles, including: determining the trajectory contraction ratio based on the interaction trajectory points and the optimized trajectory points; optimizing the speed of each trajectory point in the intermediate predicted trajectory based on the trajectory contraction ratio to obtain the target predicted trajectory of the surrounding vehicles, wherein each trajectory point does not include the trajectory starting point.

[0171] In one embodiment, the speed optimization module 850 optimizes the speed of each trajectory point in the intermediate predicted trajectory based on the trajectory contraction ratio to obtain the target predicted trajectory of the surrounding vehicles. This includes: proportionally contracting the distance corresponding to each trajectory point based on the trajectory contraction ratio to obtain the corrected distance corresponding to each trajectory point, wherein the distance corresponding to each trajectory point is the distance between each trajectory point and the trajectory starting point; optimizing the speed corresponding to each trajectory point to obtain the corrected speed corresponding to each trajectory point; and determining the target predicted trajectory based on the corrected distance and the corrected speed corresponding to each trajectory point.

[0172] In one embodiment, the speed optimization module 850 optimizes the speed corresponding to each trajectory point to obtain the corrected speed corresponding to each trajectory point, including: for each trajectory point, when the distance corresponding to the current trajectory point is less than the distance corresponding to the interactive trajectory point, determining the corrected speed corresponding to the current trajectory point based on the corrected distance corresponding to each trajectory point; when the distance corresponding to the current trajectory point is not less than the distance corresponding to the interactive trajectory point, determining the corrected speed corresponding to the current trajectory point based on the second speed of the preceding vehicle at the interactive trajectory point.

[0173] In one embodiment, the speed optimization module 850 determines the corrected speed corresponding to the current trajectory point based on the corrected distance corresponding to each trajectory point, including: selecting a trajectory point corresponding to a first preset distance from the current trajectory point towards the trajectory start point to obtain a first trajectory point; selecting a trajectory point corresponding to a second preset distance from the current trajectory point towards the trajectory end point to obtain a second trajectory point; and determining the corrected speed corresponding to the current trajectory point based on the corrected distance corresponding to the first trajectory point, the time corresponding to the first trajectory point, the corrected distance corresponding to the second trajectory point, and the time corresponding to the second trajectory point, wherein the time corresponding to the first trajectory point is the time required for surrounding vehicles to travel from the trajectory start point to the first trajectory point, and the time corresponding to the second trajectory point is the time required for surrounding vehicles to travel from the trajectory start point to the second trajectory point.

[0174] In one embodiment, the surrounding vehicle trajectory optimization device further includes an intent determination module, which is specifically used to: obtain the starting speed of the surrounding vehicles at the trajectory starting point, and determine the target distance and target time of the target trajectory point in the target predicted trajectory, wherein the target distance is the correction distance corresponding to the target trajectory point, and the target time is the time required for the surrounding vehicles to travel from the trajectory starting point to the target trajectory point; calculate the distance traveled by the surrounding vehicles at the starting speed from the trajectory starting point in the target time to obtain a predetermined distance; and determine the longitudinal intent of the surrounding vehicles based on the target distance and the predetermined distance.

[0175] In one embodiment, the intent determination module determines the longitudinal intent of surrounding vehicles based on a target distance and a predetermined distance, including: determining that the longitudinal intent of surrounding vehicles is acceleration when the target distance is greater than the sum of the predetermined distance and a set threshold; determining that the longitudinal intent of surrounding vehicles is deceleration when the target distance is less than the sum of the predetermined distance and the set threshold; and determining that the longitudinal intent of surrounding vehicles is constant speed when the target distance is equal to the sum of the predetermined distance and the set threshold.

[0176] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is merely an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the functional modules described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0177] The surrounding vehicle trajectory prediction optimization device provided in this embodiment can be applied to the surrounding vehicle trajectory prediction optimization method provided in any of the above embodiments, and has corresponding functions and beneficial effects.

[0178] Figure 9 This is a structural schematic diagram of a vehicle provided in an embodiment of this application. Figure 9 A block diagram of an exemplary vehicle 11 suitable for implementing embodiments of this application is shown. Figure 9 The vehicle 11 shown is merely an example and should not impose any limitations on the functionality and scope of use of this embodiment.

[0179] like Figure 9 As shown, vehicle 11 is represented in the form of a general-purpose computing electronic device. Components of vehicle 11 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and a bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0180] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0181] Vehicle 11 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by vehicle 11, including volatile and non-volatile media, removable and non-removable media.

[0182] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Vehicle 11 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 9Not shown; usually referred to as a "hard drive"). Although Figure 9 As not shown, disk drives for reading and writing to removable non-volatile disks (e.g., "floppy disks") and optical disc drives for reading and writing to removable non-volatile optical discs (e.g., CD-ROMs, DVD-ROMs, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application.

[0183] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of this application.

[0184] Vehicle 11 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with vehicle 11, and / or with any device that enables vehicle 11 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 22. Furthermore, vehicle 11 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20.

[0185] like Figure 9 As shown, network adapter 20 communicates with other modules of vehicle 11 via bus 18. It should be understood that, although... Figure 9 As not shown in the diagram, other hardware and / or software modules may be used in conjunction with vehicle 11, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0186] The processing unit 16 executes various functional applications and page displays by running programs stored in the system memory 28, such as implementing a method for optimizing the predicted trajectory of surrounding vehicles provided in any embodiment of this application.

[0187] This application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements, for example, a method for optimizing the predicted trajectory of surrounding vehicles provided in any embodiment of this application.

[0188] The computer storage medium of this embodiment can be any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. For example, a computer-readable storage medium can be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0189] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0190] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0191] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0192] Those skilled in the art will understand that the modules or steps described above in this application can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device, or fabricating them separately as individual integrated circuit modules, or fabricating multiple modules or steps as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0193] Furthermore, the acquisition, storage, use, and processing of data in this application's technical solution all comply with relevant national laws and regulations.

[0194] Note that the above are merely preferred embodiments and the technical principles employed in this application. Those skilled in the art will understand that this application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments. Many other equivalent embodiments may be included without departing from the inventive concept of this application, and the scope of this application is determined by the scope of the appended claims.

Claims

1. A method for optimizing the predicted trajectories of surrounding vehicles, characterized in that, The method includes: Obtain the initial predicted trajectory of the vehicles surrounding the current vehicle, and determine the starting lane corresponding to the starting point of the initial predicted trajectory and the ending lane corresponding to the ending point of the trajectory. The optimal lane for the endpoint lane is determined based on the position of the starting lane and the position of the endpoint lane, and the direction of the initial predicted trajectory is optimized based on the starting lane and the optimized lane to obtain the intermediate predicted trajectory. The preceding vehicle of the surrounding vehicles is determined based on the intermediate predicted trajectory; Based on the intermediate predicted trajectory, the interaction trajectory points between the surrounding vehicles and the vehicle in front are determined, and the interaction trajectory points are moved to obtain the optimized trajectory points of the interaction trajectory points. Based on the optimized trajectory points, the speed of the intermediate predicted trajectory is optimized to obtain the target predicted trajectory of the surrounding vehicles; Before determining the optimal lane for the destination lane based on the positions of the starting lane and the destination lane, the process also includes: determining the lane change situation based on the positions of the starting lane and the destination lane; and when the lane change situation is a continuous lane change, triggering the determination of the optimal lane for the destination lane based on the positions of the starting lane and the destination lane. When the lane change situation is no lane change, the middle lane corresponding to the middle point of the initial predicted trajectory is determined; when the middle lane is not the same as the starting lane, the direction of the initial predicted trajectory is optimized according to the starting lane and the ending lane to obtain the intermediate predicted trajectory; the lane corresponding to each trajectory point in the intermediate predicted trajectory is the same as the starting lane.

2. The method for optimizing the predicted trajectory of surrounding vehicles according to claim 1, characterized in that, The step of determining the optimized lane for the destination lane based on the position of the starting lane and the position of the destination lane includes: The lane change direction is determined based on the position of the starting lane and the position of the ending lane; The adjacent lanes of the starting lane are determined based on the lane change direction, and the adjacent lanes are determined as the optimized lanes; Correspondingly, the lane corresponding to the endpoint in the intermediate predicted trajectory is the optimized lane.

3. The method for optimizing the predicted trajectory of surrounding vehicles according to claim 1, characterized in that, Before moving the interaction trajectory point to obtain the optimized trajectory point of the interaction trajectory point, the method further includes: The first speed of the surrounding vehicles at the interaction trajectory point is obtained, and the second speed of the vehicle in front at the interaction trajectory point is obtained; When the first speed is greater than the second speed, the process of moving the interaction trajectory point to obtain the optimized trajectory point of the interaction trajectory point is triggered.

4. The method for optimizing the predicted trajectory of surrounding vehicles according to claim 3, characterized in that, The step of moving the interaction trajectory point to obtain the optimized trajectory point of the interaction trajectory point includes: The optimized trajectory point is obtained by moving the interactive trajectory point a preset distance toward the trajectory starting point.

5. The method for optimizing the predicted trajectory of surrounding vehicles according to claim 3 or 4, characterized in that, The step of optimizing the speed of the intermediate predicted trajectory based on the optimized trajectory points to obtain the target predicted trajectory of the surrounding vehicles includes: The trajectory contraction ratio is determined based on the interaction trajectory points and the optimized trajectory points; Based on the trajectory shrinkage ratio, the speed of each trajectory point in the intermediate predicted trajectory is optimized to obtain the target predicted trajectory of the surrounding vehicles, wherein each trajectory point does not include the trajectory starting point.

6. The method for optimizing the predicted trajectory of surrounding vehicles according to claim 5, characterized in that, The step of optimizing the speed of each trajectory point in the intermediate predicted trajectory based on the trajectory contraction ratio to obtain the target predicted trajectory of the surrounding vehicles includes: Based on the trajectory shrinkage ratio, the distance corresponding to each trajectory point is shrunk proportionally to obtain the corrected distance corresponding to each trajectory point. The distance corresponding to each trajectory point is the distance between each trajectory point and the trajectory starting point. The velocity corresponding to each trajectory point is optimized to obtain the corrected velocity for each trajectory point. The target predicted trajectory is determined based on the correction distance and correction speed corresponding to each trajectory point.

7. The method for optimizing the predicted trajectory of surrounding vehicles according to claim 6, characterized in that, The step of optimizing the velocity corresponding to each trajectory point to obtain the corrected velocity corresponding to each trajectory point includes: For each trajectory point, when the distance corresponding to the current trajectory point is less than the distance corresponding to the interactive trajectory point, the correction speed corresponding to the current trajectory point is determined based on the correction distance corresponding to each trajectory point; When the distance to the current trajectory point is not less than the distance to the interaction trajectory point, the correction speed corresponding to the current trajectory point is determined based on the second speed of the preceding vehicle at the interaction trajectory point.

8. The method for optimizing the predicted trajectory of surrounding vehicles according to claim 7, characterized in that, The step of determining the correction speed corresponding to the current trajectory point based on the correction distance corresponding to each trajectory point includes: Select a trajectory point corresponding to a first preset distance from the current trajectory point toward the trajectory starting point to obtain a first trajectory point; Select a trajectory point corresponding to a second preset distance from the current trajectory point toward the trajectory endpoint to obtain a second trajectory point; Based on the correction distance corresponding to the first trajectory point, the time corresponding to the first trajectory point, the correction distance corresponding to the second trajectory point, and the time corresponding to the second trajectory point, the correction speed corresponding to the current trajectory point is determined. The time corresponding to the first trajectory point is the time required for the surrounding vehicles to travel from the trajectory starting point to the first trajectory point, and the time corresponding to the second trajectory point is the time required for the surrounding vehicles to travel from the trajectory starting point to the second trajectory point.

9. The method for optimizing the predicted trajectory of surrounding vehicles according to claim 6, characterized in that, The method further includes: The starting speeds of the surrounding vehicles at the starting point of the trajectory are obtained, and the target distance and target time of the target trajectory point in the target predicted trajectory are determined. The target distance is the corrected distance corresponding to the target trajectory point, and the target time is the time required for the surrounding vehicles to travel from the starting point of the trajectory to the target trajectory point. Calculate the distance traveled by the surrounding vehicles from the starting point of the trajectory at the starting speed, taking the time it takes to reach the target, and obtain the predetermined distance; The longitudinal intention of the surrounding vehicles is determined based on the target distance and the predetermined distance.

10. The method for optimizing the predicted trajectory of surrounding vehicles according to claim 9, characterized in that, Determining the longitudinal intention of the surrounding vehicles based on the target distance and the predetermined distance includes: When the target distance is greater than the sum of the predetermined distance and the set threshold, the longitudinal intention of the surrounding vehicles is determined to be acceleration; When the target distance is less than the sum of the predetermined distance and the set threshold, the longitudinal intention of the surrounding vehicles is determined to be deceleration; When the target distance is equal to the sum of the predetermined distance and the set threshold, the longitudinal intention of the surrounding vehicles is determined to be uniform speed.

11. A device for predicting and optimizing the trajectory of surrounding vehicles, characterized in that, The device includes: The lane determination module is used to obtain the initial predicted trajectory of the surrounding vehicles of the current vehicle, and determine the starting lane corresponding to the starting point of the initial predicted trajectory and the ending lane corresponding to the ending point of the trajectory. The direction optimization module is used to determine the optimized lane of the end lane based on the position of the starting lane and the position of the end lane, and to optimize the direction of the initial predicted trajectory based on the starting lane and the optimized lane to obtain the intermediate predicted trajectory. A preceding vehicle determination module is used to determine the preceding vehicle of the surrounding vehicles based on the intermediate predicted trajectory. The trajectory point optimization module is used to determine the interaction trajectory points between the surrounding vehicles and the vehicle in front based on the intermediate predicted trajectory, and to move the interaction trajectory points to obtain the optimized trajectory points of the interaction trajectory points. The speed optimization module is used to optimize the speed of the intermediate predicted trajectory based on the optimized trajectory points to obtain the target predicted trajectory of the surrounding vehicles. The device further includes: a continuous lane change optimization module, used to determine the lane change situation based on the positions of the starting lane and the ending lane before determining the optimized lane of the ending lane based on the positions of the starting lane and the ending lane; when the lane change situation is continuous lane change, it triggers the execution of determining the optimized lane of the ending lane based on the positions of the starting lane and the ending lane. The unchanging lane optimization module is used to determine the intermediate lane corresponding to the intermediate point of the initial predicted trajectory when the lane change situation is unchanging. When the intermediate lane is not the same as the starting lane, the initial predicted trajectory is optimized according to the starting lane and the ending lane to obtain the intermediate predicted trajectory. The lane corresponding to each trajectory point in the intermediate predicted trajectory is the same as the starting lane.

12. A vehicle, characterized in that, The vehicles include: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the method for predicting the trajectory of surrounding vehicles as described in any one of claims 1 to 10.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the method for optimizing the predicted trajectories of surrounding vehicles as described in any one of claims 1 to 10.

Images