Vehicle speed planning method and device, vehicle and storage medium

Abstract

Embodiments of the present application provide a vehicle speed planning method and device, a vehicle and a storage medium, and relate to the technical field of automatic driving. The method determines a target vehicle, a recursion starting point and a recursion direction according to a driving trajectory of a host vehicle and a driving trajectory of a neighboring vehicle. The method recursively plans a trajectory of the target vehicle for a preset time period in the recursion direction according to the recursion starting point, and obtains a trajectory after recursion. The method plans a speed of the host vehicle according to the trajectory after recursion, thereby increasing a safety redundancy distance between the host vehicle and an obstacle when the vehicle changes lanes, and improving the safety of automatic driving.

Description

Technical Field

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

[0002] Existing speed planning schemes typically reduce speed changes to improve comfort, which may result in the vehicle being too close to adjacent vehicles (such as the vehicle in front and behind) when changing lanes, posing a safety hazard of friction or collision between the vehicle and adjacent vehicles. Summary of the Invention

[0003] This application provides a vehicle speed planning method, apparatus, vehicle, and storage medium to improve the above-mentioned problems.

[0004] Firstly, embodiments of this application provide a vehicle speed planning method. The method includes: determining a target vehicle, a recursion starting point, and a recursion direction based on the driving trajectory of the vehicle and the driving trajectories of adjacent vehicles, wherein the target vehicle is a vehicle with a collision risk with the vehicle, the recursion starting point is the trajectory point of the target vehicle corresponding to the collision risk, and the recursion direction includes forward recursion or backward recursion; based on the recursion starting point, recursively extending the driving trajectory of the target vehicle towards the recursion direction for a preset time period to obtain the recursed trajectory; and planning the vehicle speed based on the recursed trajectory.

[0005] Secondly, embodiments of this application provide a vehicle speed planning device. The device includes: a target determination module, used to determine a target vehicle, a recursion starting point, and a recursion direction based on the driving trajectory of the vehicle and the driving trajectories of adjacent vehicles, wherein the target vehicle is a vehicle with a collision risk with the vehicle, the recursion starting point is the trajectory point of the target vehicle corresponding to the collision risk, and the recursion direction includes forward recursion or backward recursion; a trajectory recursion module, used to recursively calculate the trajectory of the target vehicle for a preset time period in the recursion direction based on the recursion starting point, to obtain the recursed trajectory; and a vehicle speed planning module, used to plan the vehicle speed based on the recursed trajectory.

[0006] Thirdly, embodiments of this application provide a vehicle. The vehicle includes a memory, one or more processors, and one or more application programs. The one or more application programs are stored in the memory and configured to execute the methods provided in embodiments of this application when invoked by one or more processors.

[0007] Fourthly, embodiments of this application provide a computer-readable storage medium. This computer-readable storage medium stores program code configured to execute the method provided in embodiments of this application when invoked by a processor.

[0008] This application provides a vehicle speed planning method, device, vehicle, and storage medium. By determining the recursive starting point (collision point or interference point), obstacles can be responded to in advance, thereby improving the safety of autonomous driving. Compared to the vehicle trajectory planned according to existing vehicle speed planning methods, the vehicle trajectory planned according to the vehicle speed planning method provided in this application avoids the target vehicle's trajectory and maintains a certain distance from it. This increases the safety redundancy distance between the vehicle and obstacles when changing lanes, thus improving the safety of autonomous driving. Attached Figure Description

[0009] 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.

[0010] Figure 1 This is a schematic diagram illustrating an application scenario of the vehicle speed planning method provided in an exemplary embodiment of this application;

[0011] Figure 2 This is a schematic flowchart of a vehicle speed planning method provided in an embodiment of this application;

[0012] Figure 3 This is a schematic diagram of a scene at a certain moment during the vehicle's driving process, provided in an exemplary embodiment of this application;

[0013] Figure 4 This is a flowchart illustrating a vehicle speed planning method provided in another embodiment of this application;

[0014] Figure 5 This is a schematic diagram of a vehicle lane-changing situation provided in an exemplary embodiment of this application;

[0015] Figure 6 This is an exemplary embodiment provided by this application. Figure 5 The ST diagram corresponding to the vehicle lane change situation shown;

[0016] Figure 7 This is a schematic diagram of a vehicle changing lanes according to another exemplary embodiment of this application;

[0017] Figure 8 This is an exemplary embodiment provided by this application. Figure 7The ST diagram corresponding to the vehicle lane change situation shown;

[0018] Figure 9 This is a schematic diagram of a vehicle changing lanes, provided in yet another exemplary embodiment of this application;

[0019] Figure 10 This is an exemplary embodiment provided by this application. Figure 10 The ST diagram corresponding to the vehicle lane change situation shown;

[0020] Figure 11 This is a structural block diagram of a vehicle speed planning device provided in one embodiment of this application;

[0021] Figure 12 This is a structural block diagram of a vehicle provided in one embodiment of this application;

[0022] Figure 13 This is a structural block diagram of a computer-readable storage medium provided in an embodiment of this application. Detailed Implementation

[0023] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0024] Please see Figure 1 , Figure 1 This is a schematic diagram illustrating an application scenario of the vehicle speed planning method provided in an exemplary embodiment of this application. The vehicle speed planning system 10 includes a vehicle 11 and an obstacle 12. The vehicle 11 and the obstacle 12 can communicate with each other to exchange data.

[0025] Vehicle 11 can acquire information such as the trajectory, speed, and position of obstacle 12 in real time or at preset intervals. The preset interval can be set according to actual needs, for example, 0.5 seconds, without specific limitations. Vehicle 11 can perform different functions based on the acquired information about obstacle 12. For example, vehicle 11 can create an ST diagram based on its own position and the position of obstacle 12 to clarify the positions of both vehicles. Vehicle 11 can also create an ST diagram based on the trajectory of either vehicle 11 or obstacle 12 to clarify their trajectories. The ST diagram describes the longitudinal movement of obstacle 12 in the lane where vehicle 11 is located, i.e., its longitudinal speed. S refers to the distance traveled forward along the vehicle's trajectory with the vehicle as the origin, and T refers to time. As another example, vehicle 11 can calculate the distance between obstacle 12 and vehicle 11 based on its own trajectory and the trajectory of obstacle 12.

[0026] Obstacle 12 can be a single obstacle or include multiple obstacles. An obstacle can be a vehicle or other equipment capable of communicating with vehicle 11. When obstacle 12 includes multiple vehicles, these vehicles can be the same or different. For example, the multiple vehicles can be vehicles produced by the same manufacturer or vehicles produced by different manufacturers. Alternatively, the multiple vehicles can be vehicles of the same model or vehicles of different models. Vehicles can be gasoline vehicles or electric vehicles, etc., where electric vehicles can be pure electric vehicles, hybrid electric vehicles, or fuel cell vehicles, etc., without specific limitations.

[0027] Please see Figure 2 , Figure 2 This is a schematic flowchart of a vehicle speed planning method provided in an embodiment of this application. This vehicle speed planning method can be applied to... Figure 1 The vehicle shown is 11, or as mentioned below. Figure 11 The speed planning device 300 shown, or as mentioned below Figure 12 The vehicle 400 is shown. The vehicle speed planning method may include the following steps S110 to S130.

[0028] Step S110: Determine the target vehicle, the starting point of the recursion, and the direction of the recursion based on the driving trajectory of the vehicle itself and the driving trajectories of adjacent vehicles.

[0029] In this embodiment, the vehicle's trajectory refers to the predicted trajectory based on the vehicle's destination and current driving environment, rather than the actual trajectory. Similarly, the adjacent vehicle's trajectory refers to the predicted trajectory based on the adjacent vehicle's destination and current driving environment, rather than the actual trajectory.

[0030] In this embodiment, adjacent vehicles refer to vehicles whose centers are located within a preset range centered on the vehicle itself. The preset range can be a range encompassed by a regular shape (e.g., a circle, rectangle, or cone) or a range encompassed by an irregular shape. The specific preset range can be set according to actual needs and is not specifically limited here.

[0031] In some implementations, the preset range can be a circular area centered on the vehicle, and the diameter of this circle can be the total width of all lanes corresponding to the vehicle's direction of travel. Dividing the preset range into a circle allows for the uniform acquisition of the driving trajectories of adjacent vehicles in each direction, enabling subsequent execution of speed planning methods based on these trajectories, thereby improving the comprehensiveness of the speed planning method.

[0032] In other implementations, the preset range can be a rectangular area centered on the vehicle. This rectangle can be a square, and its width can be the total width of all lanes corresponding to the vehicle's direction of travel. Alternatively, the rectangle can be a rectangle, where the shorter side can be the total width of all lanes corresponding to the vehicle's direction of travel, and the longer side is longer than the shorter side; for example, the longer side can be three times the length of the shorter side. Dividing the preset range into rectangles increases the longitudinal (parallel to the lane) range, allowing for the acquisition of more longitudinally adjacent vehicle trajectories, thus increasing data richness. This allows for subsequent execution of speed planning methods based on the richer trajectories, thereby improving the accuracy of speed planning.

[0033] In some other implementations, the preset range can be a cone-shaped area centered on the vehicle. The diameter of the base circle of the cone can be the total width of all lanes corresponding to the vehicle's direction of travel, and the height of the cone is greater than the total width of all lanes corresponding to the vehicle's direction of travel. Dividing the preset range into a cone shape allows for accurate acquisition of adjacent vehicles in front of the vehicle, while increasing the range behind the vehicle allows for acquisition of more adjacent vehicles located behind it, thus avoiding the inability to acquire adjacent vehicles in the vehicle's blind spot, thereby improving the accuracy and safety of speed planning.

[0034] As an example, please refer to Figure 3 , Figure 3 This is a schematic diagram of a scene at a certain moment during the driving process of a vehicle, provided in an exemplary embodiment of this application. Figure 3 This includes the three lanes corresponding to the vehicle's direction of travel, with the bold black solid lines indicating the boundaries of each lane. Figure 3 This includes vehicles A, B, C, D, and E.

[0035] If the preset range is a circular range, for example, Figure 3 The area enclosed by the dashed circle 1 in the diagram is then the adjacent vehicles are vehicle A, vehicle B, vehicle C, and vehicle D.

[0036] If the preset range is a rectangular range, for example, Figure 3 The area enclosed by the dashed rectangle 2 in the diagram is then defined as the adjacent vehicles: vehicle A, vehicle B, vehicle C, vehicle D, and vehicle E.

[0037] If the preset range is a conical range, for example, Figure 3 The area enclosed by the dashed cone 3 in the diagram is then the adjacent vehicles are vehicle B, vehicle C, vehicle D, and vehicle E.

[0038] In this embodiment, the target vehicle refers to a vehicle that poses a collision risk with the vehicle itself. Specifically, at some point in the future, the distance between the trajectory points of the target vehicle and the trajectory points of the vehicle itself may be too close, resulting in a risk of a collision between the target vehicle and the vehicle itself.

[0039] In this embodiment, the recursive starting point refers to the trajectory point of the target vehicle (which can be called the collision point or interference point) when there is a risk of collision between the target vehicle and the driver vehicle. At the location corresponding to the collision point, there is a risk of collision between the target vehicle and the driver vehicle. Therefore, by using the collision point as the recursive starting point, the driving trajectory of the target vehicle can be recursively extrapolated, extending the position of the collision point forward or backward. In other words, by extending the driving trajectory of the target vehicle forward or backward, a response to the collision point can be initiated in advance. This increases the distance between the driver vehicle and the target vehicle at the location of the collision point, preventing the target vehicle from getting too close to the driver vehicle, eliminating the safety hazard of friction or collision between the driver vehicle and adjacent vehicles, and thus improving the safety of autonomous driving.

[0040] The recursion direction in this application embodiment includes forward recursion or backward recursion. Specifically, forward recursion refers to recursing from the time of the recursion point, while backward recursion refers to recursing from the time of the recursion starting point.

[0041] In some implementations, the vehicle can acquire its driving trajectory in real time or at preset intervals. The preset interval can be set according to actual needs, for example, 0.5 seconds, and no specific limitation is made here.

[0042] In some implementations, the vehicle can receive the driving trajectories of neighboring vehicles in real time or at preset intervals. The preset interval can be set according to actual needs, for example, 0.5 seconds, and no specific limitation is made here.

[0043] In some implementations, the vehicle can determine lane change status based on its own driving trajectory and the driving trajectories of adjacent vehicles, and determine the target vehicle, the starting point, and the direction of recursion based on the lane change status. If the lane change status matches a preset lane change pattern, the target vehicle, the starting point, and the direction of recursion are determined based on the preset lane change pattern. If the lane change status does not match the preset lane change pattern, step S110 continues, that is, the operation of "determining the target vehicle, the starting point, and the direction of recursion based on the driving trajectory of the vehicle and the driving trajectories of adjacent vehicles" continues.

[0044] The aforementioned preset lane-changing scenarios can include one or more combinations of the following: a vehicle in an adjacent lane cuts into the vehicle's lane from in front of it; a vehicle in the current lane cuts out of the current lane from in front of it; or the vehicle cuts into an adjacent lane from in front of a vehicle in the current lane. The preset lane-changing scenarios can be selected according to actual needs, or different scenarios can be reset. For example, a preset lane-changing scenario could also be a vehicle in an adjacent lane cutting into the current lane from behind it. Specific preset lane-changing scenarios are not limited here.

[0045] As an example, if the preset lane-changing situation is that a vehicle in the adjacent lane cuts into the vehicle's trajectory from in front of the vehicle, then the target vehicle is the vehicle in the adjacent lane, the recursion direction is forward recursion, and the starting point of the recursion is the trajectory point of the target vehicle when there is a risk of collision between the target vehicle and the vehicle.

[0046] As another example, if the preset lane-changing situation is that the vehicle in front of the current vehicle cuts out of the current vehicle's lane from in front of the current vehicle, then the target vehicle is the vehicle in front, the recursion direction is forward and backward, and the starting point of the recursion is the trajectory point of the target vehicle when there is a risk of collision between the target vehicle and the current vehicle.

[0047] As another example, if the preset lane-changing situation is that the vehicle changes lanes from its own lane into the adjacent lane from in front of the vehicle in the adjacent lane, then the target vehicle is the vehicle in the adjacent lane, the recursion direction is forward recursion, and the recursion starting point is the trajectory point of the target vehicle when there is a risk of collision between the target vehicle and the vehicle.

[0048] Step S120: Based on the starting point of the recursion, the trajectory of the target vehicle for a preset time period is recursively calculated in the recursion direction to obtain the trajectory after the recursion.

[0049] The preset time period in this embodiment can be 1 second. The specific value of the preset time period can be set according to actual needs, and no specific restrictions are imposed here.

[0050] In some implementations, the trajectory of the target vehicle can be extrapolated in the recursive direction for a preset period based on the speed of the target vehicle at the recursive starting point (i.e., the slope of the target vehicle's trajectory at the collision point). Extrapolating based on the target vehicle's speed ensures that the extrapolated trajectory differs from the original trajectory of the target vehicle. This ensures that the subsequent trajectory of the self-driving vehicle after speed planning maintains a certain distance from the original trajectory of the target vehicle, thereby increasing the distance between the self-driving vehicle and the target vehicle at the collision point and avoiding safety hazards caused by excessive proximity, thus improving the safety of autonomous driving.

[0051] In other implementations, a preset recursion value can be set. Based on this preset recursion value, starting from the recursion starting point, the trajectory of the target vehicle for a preset time period is recursively extrapolated in the recursion direction to obtain the extrapolated trajectory. Using the preset recursion value for extrapolation saves data acquisition time, thereby increasing the extrapolation speed and thus improving the vehicle speed planning speed.

[0052] In some implementations, a recursive algorithm can be used to extrapolate the target vehicle's trajectory for a preset time period based on the starting point, thus obtaining the extrapolated trajectory. The recursive algorithm can be selected from existing recursive algorithms.

[0053] Step S130: Based on the recursive trajectory, plan the vehicle speed.

[0054] After obtaining the recursive trajectory, the recursive trajectory can be used as the obstacle trajectory for vehicle speed planning, and vehicle speed planning can be performed based on the obstacle trajectory and the vehicle trajectory.

[0055] In some implementations, the distance between the obstacle trajectory point and the vehicle trajectory point at the same moment can be calculated. Based on this distance, the corresponding vehicle speed limit value can be found, and the vehicle speed can be planned according to the vehicle speed limit value so that the vehicle speed is less than or equal to the vehicle speed limit value. Here, there is a mapping relationship between the distance between the vehicle trajectory point and the obstacle trajectory point at the same moment and the vehicle speed limit value. This mapping relationship can be pre-set and stored, and it can be one of the following: one-to-one mapping, one-to-many mapping, many-to-one mapping, and many-to-many mapping.

[0056] In other embodiments, the obstacle trajectory includes multiple first rectangular boxes representing obstacles. The length of each first rectangular box can be greater than or equal to the length of the obstacle, such as the target vehicle, and the width of each first rectangular box can be greater than or equal to the width of the obstacle, such as the target vehicle. The vehicle trajectory includes multiple second rectangular boxes representing the vehicle. The length of each second rectangular box can be greater than or equal to the length of the vehicle, and the width of each second rectangular box can be greater than or equal to the width of the vehicle. The shortest distance between the first and second rectangular boxes at the same moment can be calculated. Based on the shortest distance, the corresponding vehicle speed limit value can be found. The vehicle speed can be planned according to the vehicle speed limit value so that the vehicle speed is less than or equal to the vehicle speed limit value. A mapping relationship exists between the shortest distance and the vehicle speed limit value. This mapping relationship can be pre-set and stored, and it can be one of a one-to-one mapping, a one-to-many mapping, a many-to-one mapping, or a many-to-many mapping.

[0057] By replacing the original trajectory of the target vehicle with the recursive trajectory, the vehicle's speed is planned. This ensures that the vehicle's trajectory, calculated based on the recursive trajectory, avoids the target vehicle's trajectory and maintains a certain distance from it. This increases the safety redundancy distance between the vehicle and obstacles when changing lanes, thereby improving the safety of autonomous driving.

[0058] The vehicle speed planning method provided in this application can respond to obstacles in advance by determining the recursive starting point (collision point or interference point), thereby improving the safety of autonomous driving. Compared with the vehicle trajectory planned according to existing vehicle speed planning methods, the vehicle trajectory planned according to the vehicle speed planning method provided in this application will avoid the target vehicle's trajectory and maintain a certain distance from the target vehicle's trajectory. This can increase the safety redundancy distance between the vehicle and obstacles when changing lanes, thereby improving the safety of autonomous driving.

[0059] Please see Figure 4 , Figure 4 This is a flowchart illustrating a vehicle speed planning method provided in another embodiment of this application. This vehicle speed planning method can be applied to... Figure 1 The vehicle shown is 11, or as mentioned below. Figure 11 The speed planning device 300 shown, or as mentioned below Figure 12 The vehicle 400 shown. The vehicle speed planning method may include the following steps S210 to S240.

[0060] Step S210: Determine the lane change situation based on the driving trajectory of the vehicle and the driving trajectories of adjacent vehicles.

[0061] In some implementations, the driving trajectory of the vehicle and the driving trajectories of adjacent vehicles can be mapped onto the ST diagram. Based on the driving trajectory of the vehicle and the driving trajectories of adjacent vehicles in the ST diagram, it can be determined whether there is a lane change.

[0062] If the trajectory of the vehicle in the ST diagram intersects with the trajectory of an adjacent vehicle, it is determined that a lane change has occurred, and the intersection point is identified as the collision point, with the adjacent vehicle being the target vehicle.

[0063] If the closest distance between the vehicle's trajectory and the trajectory of an adjacent vehicle in the ST diagram is less than a preset distance threshold, it is determined that a lane change has occurred, and the trajectory point of the adjacent vehicle corresponding to the closest distance is identified as the collision point, and this adjacent vehicle is the target vehicle. The preset distance threshold can be set according to actual needs; for example, the preset distance threshold can be the width of the vehicle, without specific limitations here.

[0064] If neither of the above two situations exists in the ST diagram, it is assumed that there is no lane change situation, and step S210 is executed, that is, the operation of "determining the lane change situation based on the driving trajectory of the vehicle and the driving trajectory of the adjacent vehicles" continues.

[0065] When a lane change is detected, the changes in the driving directions of adjacent vehicles and the vehicle itself can be obtained. Based on these changes, the lane change situation can be determined. For example, if the vehicle's driving direction does not change, but the adjacent vehicle's driving direction changes, and the adjacent vehicle is in front of the vehicle when its driving direction change ends, then the trajectory of the vehicle in the adjacent lane cutting into the vehicle from in front of the vehicle can be determined.

[0066] In other implementations, the vehicle's trajectory and the trajectories of adjacent vehicles can be input into a preset model to obtain lane-change information. This preset model is a model pre-trained and stored in the vehicle or a server communicatively connected to it. This model is used to determine lane-change situations based on the vehicle's trajectory and the trajectories of adjacent vehicles. Using a preset model to determine lane-change situations can save computation time and resources, improving the overall implementation efficiency of the solution.

[0067] Step S220: Determine the target vehicle based on the vehicle lane change situation, and deduce the starting point and direction of the deduction.

[0068] Lane changing scenarios can include one or more combinations of the following: a vehicle in an adjacent lane cuts into the lane from in front of the vehicle; a vehicle in front of the vehicle cuts out of the vehicle's lane from in front of the vehicle; or the vehicle cuts into an adjacent lane from in front of a vehicle in the adjacent lane. The lane changing scenarios can be selected according to actual needs, or different scenarios can be set. For example, a lane changing scenario could also be a vehicle in an adjacent lane cutting into the vehicle's lane from behind. Specific lane changing scenarios are not limited here.

[0069] In some implementations, the lane change situation is when a vehicle in an adjacent lane cuts into the vehicle's trajectory from in front of the vehicle, and the target vehicle is identified as the vehicle in the adjacent lane; the starting point for the recursion is the trajectory point of the target vehicle when there is a risk of collision between the target vehicle and the vehicle; and the direction of the recursion is forward recursion.

[0070] In other implementations, the lane change situation is when the vehicle in front of the current vehicle cuts out of the current vehicle's lane from in front of the current vehicle, and the target vehicle is identified as the vehicle in front; the starting point for the recursion is the trajectory point of the target vehicle when there is a risk of collision between the target vehicle and the current vehicle; and the direction of the recursion is backward.

[0071] In some other implementations, the lane change situation is that the vehicle cuts into the adjacent lane from the front of the vehicle in the adjacent lane, and the target vehicle is identified as the vehicle in the adjacent lane; the starting point of the recursion is determined as the trajectory point of the target vehicle when there is a risk of collision between the target vehicle and the vehicle; and the direction of the recursion is determined to be forward recursion.

[0072] In some embodiments, vehicle lane change scenarios include multiple scenarios, each corresponding to a different target vehicle, a recursive starting point, and a recursive direction. Therefore, the mapping relationship between each lane change scenario and its corresponding target vehicle, recursive starting point, and recursive direction can be stored in the vehicle's memory, forming a mapping table between lane change scenarios and their corresponding target vehicles, recursive starting points, and recursive directions. A lookup process can be performed based on the lane change scenario, i.e., by searching the mapping table for the target vehicle, recursive starting point, and recursive direction corresponding to the lane change scenario, the desired target vehicle, recursive starting point, and recursive direction can be obtained.

[0073] Table 1

[0074]

[0075]

[0076] As an example, the mapping table above can be shown in Table 1. Authorized users can modify, delete, or add mapping relationships in this table at any time during the application process, based on actual needs, so as to continuously improve and update vehicle lane-changing situations and enhance the flexibility and robustness of the speed planning method.

[0077] In some implementations, the method for determining that there is a collision risk between the target vehicle and the vehicle itself may include the following steps: calculating the distance between the driving trajectory of the target vehicle and the driving trajectory of the vehicle itself; if the distance is less than a preset distance threshold, determining that there is a collision risk between the target vehicle and the vehicle itself; if the distance is not less than the preset distance threshold, determining that there is no collision risk between the target vehicle and the vehicle itself.

[0078] The distance between the target vehicle's trajectory and the driver's trajectory refers to the shortest distance between them.

[0079] The aforementioned preset distance threshold can be set according to actual needs. For example, the preset distance threshold can be the width of the vehicle, without any specific restrictions.

[0080] In some implementations, Euclidean distance can be used to calculate the shortest distance between the target vehicle's trajectory and the driver's trajectory.

[0081] In other implementations, the travel trajectories of the target vehicle and the driver vehicle can be input into a preset distance calculation model to obtain the shortest distance between them. This preset distance calculation model is a pre-trained model stored in the driver vehicle, and it can be used to calculate the shortest distance between the target vehicle's trajectory and the driver vehicle's trajectory. Using a model to calculate the shortest distance improves the overall efficiency of the solution.

[0082] Step S230: Based on the starting point of the recursion, the trajectory of the target vehicle for a preset time period is recursively calculated in the recursion direction to obtain the trajectory after the recursion.

[0083] Step S240: Based on the recursive trajectory, plan the vehicle speed.

[0084] Please refer to steps S120 and S130 above for steps S230 and S240 respectively, and they will not be repeated here.

[0085] The vehicle speed planning method provided in this application improves the safety of autonomous driving by determining the recursive starting point (collision point or interference point) and responding to obstacles in advance. Compared to the vehicle trajectory planned by existing vehicle speed planning methods, the trajectory planned by the method provided in this application avoids the target vehicle's trajectory and maintains a certain distance from it. This increases the safety redundancy distance between the vehicle and obstacles when changing lanes, thus improving the safety of autonomous driving. Furthermore, this embodiment accurately and effectively determines vehicle changes by transforming the abstract vehicle trajectory into a specific ST diagram. By setting the aforementioned mapping table, lane change information can be dynamically updated, thereby improving the flexibility and robustness of the vehicle speed planning method.

[0086] For ease of understanding, this application provides several exemplary embodiments. Figures 5-10 These exemplary embodiments are provided to explain the above methods and should be understood as illustrative examples of the above methods, and do not constitute a limitation on the above methods of this application.

[0087] It should be noted that, Figures 5-10 In this context, S represents the distance traveled forward along the vehicle's trajectory from its current position, T represents time, m represents meters, and s represents seconds.

[0088] It should also be noted that, Figure 5 , Figure 7 , Figure 9The solid boxes in the diagram represent the actual current vehicle positions, while the dashed boxes represent the predicted vehicle positions based on the vehicle's trajectory, rather than the actual current vehicle positions.

[0089] Please see Figure 5 and Figure 6 , Figure 5 This is a schematic diagram of a vehicle changing lanes according to an exemplary embodiment of this application. Figure 6 This is an exemplary embodiment provided by this application. Figure 5 The ST diagram corresponding to the vehicle lane-changing situation shown. For example... Figure 5 As shown, the lane change scenario involves a vehicle (Vehicle A) cutting into the lane from in front of the driver's vehicle. Vehicle A begins cutting into the driver's lane at 0 seconds. Two seconds later, at a distance of 30 meters in front of the driver, there is a risk of collision between Vehicle A and the driver. The corresponding collision point occurs at 2 seconds and at a distance of 30 meters.

[0090] Assuming vehicle A travels at a constant speed, Figure 5 The vehicle lane change situation is transformed to Figure 6 In the ST diagram, the solid line L1 represents the trajectory of vehicle A (for ease of understanding, only the trajectory of the target vehicle after the collision point is drawn). Figure 6 Point p in the equation is the collision point.

[0091] Based on the aforementioned lane-changing situation, the target vehicle is identified as vehicle A, the starting point for the recursion is the collision point p, and the recursion direction is forward. Assume the preset time period is 1 second. Starting from the collision point p, using the speed of vehicle A at collision point p, the trajectory of vehicle A is recursively extrapolated forward by 1 second to obtain the extrapolated trajectory. This extrapolated trajectory includes at least the dashed line qp. Speed ​​planning is then performed based on this extrapolated trajectory, resulting in the vehicle's trajectory, as shown by the bold solid line L3. Figure 6 The solid line L2 in the figure represents the vehicle trajectory obtained by speed planning based on the original driving trajectory of vehicle A.

[0092] like Figure 6 As shown, the thickened solid line L3 is farther from the solid line L1 and farther from the collision point p than the solid line L2, thus increasing the safety redundancy distance between the target vehicle (vehicle A) and the autonomous vehicle. In other words, compared to the autonomous vehicle trajectory obtained by speed planning based on the target vehicle's original driving trajectory, the autonomous vehicle trajectory obtained using the speed planning method provided in this application is farther from the collision point, thereby increasing the safety redundancy distance between vehicles when changing lanes, and thus improving the safety of autonomous driving.

[0093] Please see Figure 7 and Figure 8 , Figure 7 This is a schematic diagram of a vehicle changing lanes according to another exemplary embodiment of this application. Figure 8 This is an exemplary embodiment provided by this application. Figure 7 The ST diagram corresponding to the vehicle lane-changing situation shown. For example... Figure 7 As shown, the lane change scenario involves a vehicle (Vehicle B) cutting out of the lane in front of the current vehicle. Vehicle B begins cutting out of the lane at 0 seconds, at which point the distance between Vehicle B and the current vehicle is 30 meters. Two seconds later, at a distance of 40 meters in front of the current vehicle, there is a risk of collision between Vehicle B and the current vehicle. The corresponding point of collision occurs at 2 seconds and at a distance of 40 meters.

[0094] Assuming vehicle B travels at a constant speed, Figure 7 The vehicle lane change situation is transformed to Figure 8 In the ST diagram, the solid line L1 represents the trajectory of vehicle B (for ease of understanding, only the trajectory of the target vehicle before the collision point is drawn). Figure 8 Point p in the equation is the collision point.

[0095] Based on the aforementioned lane-changing situation, the target vehicle is identified as vehicle B. The starting point for the recursion is the collision point p, and the recursion direction is backward. Assume the preset time period is 1 second. Starting from the collision point p, using the speed of vehicle B at collision point p, the trajectory of vehicle B is recursively extrapolated backward by 1 second to obtain the extrapolated trajectory. This extrapolated trajectory includes at least the dashed line pq. Speed ​​planning is then performed based on this extrapolated trajectory, resulting in the vehicle's trajectory, as shown by the bold solid line L3. Figure 8 The solid line L2 in the figure represents the vehicle trajectory obtained by speed planning based on the original driving trajectory of vehicle B.

[0096] like Figure 8 As shown, the thickened solid line L3 is farther from the solid line L1 and farther from the collision point p than the solid line L2, thus increasing the safety redundancy distance between the target vehicle (vehicle B) and the voluntary vehicle. In other words, compared to the voluntary vehicle trajectory obtained by speed planning based on the target vehicle's original driving trajectory, the voluntary vehicle trajectory obtained using the speed planning method provided in this application is farther from the collision point, thereby increasing the safety redundancy distance between vehicles when changing lanes, and thus improving the safety of autonomous driving.

[0097] Please see Figure 9 and Figure 10 , Figure 9 This is a schematic diagram illustrating a vehicle lane-changing scenario provided in yet another exemplary embodiment of this application. Figure 10 This is an exemplary embodiment provided by this application. Figure 10 The ST diagram corresponding to the vehicle lane-changing situation shown. For example... Figure 9As shown, the lane change scenario involves the vehicle cutting into the adjacent lane from its own lane in front of a vehicle (vehicle E). The vehicle begins cutting into the adjacent lane at 0 seconds, at which point vehicle E is 20 meters behind the vehicle. Two seconds later, there is a risk of collision between the vehicle and the target vehicle. The corresponding collision point occurs at 2 seconds and is 10 meters away.

[0098] Assuming vehicle E travels at a constant speed, Figure 9 The vehicle lane change situation is transformed to Figure 10 In the ST diagram, the solid line L1 represents the trajectory of vehicle E (for ease of understanding, only the trajectory of the target vehicle after the collision point is drawn). Figure 10 Point p in the equation is the collision point.

[0099] Based on the aforementioned lane-changing situation, the target vehicle is identified as vehicle E, with the starting point of the recursion being the collision point p, and the recursion direction being forward. Assume the preset time period is 1 second. Starting from the collision point p, using the speed of vehicle E corresponding to collision point p, the trajectory of vehicle E is recursively extrapolated backward by 1 second to obtain the extrapolated trajectory. This extrapolated trajectory includes at least the dashed line qp. Speed ​​planning is then performed based on this extrapolated trajectory, resulting in the vehicle's trajectory, as shown by the bold solid line L3. Figure 10 The solid line L2 in the figure represents the vehicle trajectory obtained by speed planning based on the original driving trajectory of vehicle E.

[0100] like Figure 10 As shown, the thickened solid line L3 is farther from the solid line L1 and farther from the collision point p than the solid line L2, thus increasing the safety redundancy distance between the target vehicle (vehicle E) and the autonomous vehicle. In other words, compared to the autonomous vehicle trajectory obtained by speed planning based on the target vehicle's original driving trajectory, the autonomous vehicle trajectory obtained using the speed planning method provided in this application is farther from the collision point, thereby increasing the safety redundancy distance between vehicles when changing lanes, and thus improving the safety of autonomous driving.

[0101] Please see Figure 11 , Figure 11 This is a structural block diagram of a vehicle speed planning device provided in one embodiment of this application. The vehicle speed planning device 300 can be applied to... Figure 1 The vehicle 11 shown is a vehicle speed planning device 300. The vehicle speed planning device 300 includes a target determination module 310, a trajectory recursion module 320, and a vehicle speed planning module 330 that are interconnected.

[0102] The target determination module 310 is used to determine the target vehicle, the starting point, and the direction of recursion based on the driving trajectory of the vehicle itself and the driving trajectories of adjacent vehicles.

[0103] The trajectory recursion module 320 is used to recursively calculate the trajectory of the target vehicle for a preset time period in the recursion direction based on the recursion starting point, so as to obtain the recursed trajectory.

[0104] The vehicle speed planning module 330 is used to plan the vehicle speed based on the recursive trajectory.

[0105] In some implementations, the target determination module 310 includes a vehicle condition monitoring submodule and a target determination submodule.

[0106] The vehicle condition monitoring submodule is used to determine the lane change status of a vehicle based on its own driving trajectory and the driving trajectories of adjacent vehicles.

[0107] The target determination submodule is used to determine the target vehicle based on the vehicle's lane change situation, and to deduce the starting point and direction of the recursion.

[0108] In some implementations, the target determination submodule includes a first vehicle determination unit, a first starting point determination unit, and a first direction determination unit.

[0109] The first vehicle determination unit is used to determine the target vehicle as the vehicle in the adjacent lane if the vehicle lane change situation is that a vehicle in the adjacent lane cuts into the vehicle's driving trajectory from in front of the vehicle.

[0110] The first starting point determination unit is used to determine the trajectory point of the target vehicle when there is a risk of collision between the target vehicle and the voluntary vehicle.

[0111] The first direction determination unit is used to determine that the recursion direction is forward recursion.

[0112] In other embodiments, the target determination submodule includes a second vehicle determination unit, a second starting point determination unit, and a second direction determination unit.

[0113] The second vehicle determination unit is used to determine the target vehicle as the preceding vehicle if the vehicle changes lanes by cutting out of the lane in front of the vehicle.

[0114] The second starting point determination unit is used to determine the trajectory point of the target vehicle when there is a risk of collision between the target vehicle and the voluntary vehicle.

[0115] The second direction determination unit is used to determine that the recursion direction is backward recursion.

[0116] In some other implementations, the target determination submodule includes a third vehicle determination unit, a third starting point determination unit, and a third direction determination unit.

[0117] The third vehicle determination unit is used to determine the target vehicle as the vehicle in the adjacent lane if the vehicle lane change situation is that the vehicle cuts into the adjacent lane from the front of the vehicle in the adjacent lane.

[0118] The third starting point determination unit is used to determine the trajectory point of the target vehicle when there is a risk of collision between the target vehicle and the voluntary vehicle.

[0119] The third direction determination unit is used to determine that the recursion direction is forward recursion.

[0120] In some implementations, the trajectory recursion module 320 includes a vehicle speed acquisition submodule and a trajectory recursion submodule.

[0121] The vehicle speed acquisition submodule is used to acquire the vehicle speed of the target vehicle corresponding to the recursive starting point.

[0122] The trajectory recursion submodule is used to recursively calculate the trajectory of the target vehicle for a preset time period from the starting point of the recursion, based on the speed of the target vehicle corresponding to the starting point of the recursion, to obtain the trajectory after recursion.

[0123] In other embodiments, the trajectory recursion module 320 includes a recursion value acquisition submodule and the aforementioned trajectory recursion submodule.

[0124] The recursive value retrieval submodule is used to retrieve preset recursive values.

[0125] The aforementioned trajectory recursion submodule is further configured to, starting from the recursion starting point, use the preset recursion value to recursively calculate the trajectory of the target vehicle for a preset time period in the recursion direction, thereby obtaining the recursed trajectory.

[0126] In some implementations, the first starting point determination unit, the second starting point determination unit, and the third starting point determination unit all include a distance calculation subunit and a collision detection subunit.

[0127] The distance calculation subunit is used to calculate the distance between the driving trajectory of the target vehicle and the driving trajectory of the vehicle itself.

[0128] The collision detection subunit is used to determine whether the distance between the driving trajectory of the target vehicle and the driving trajectory of the self-vehicle is less than a preset distance threshold; if the distance is less than the preset distance threshold, it is determined that there is a risk of collision between the target vehicle and the self-vehicle; if the distance is not less than the preset distance threshold, it is determined that there is no risk of collision between the target vehicle and the self-vehicle.

[0129] Those skilled in the art will clearly understand that the vehicle speed planning device 300 provided in this application embodiment can implement the vehicle speed planning method provided in this application embodiment. The specific working process of the above-mentioned device and module can be found in the process corresponding to the vehicle speed planning method in this application embodiment, and will not be repeated here.

[0130] In the embodiments provided in this application, the coupling, direct coupling, or communication connection between the modules shown or discussed may be indirect coupling or communication coupling through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms. The embodiments of this application do not limit this.

[0131] Furthermore, the functional modules in the embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules, and this application embodiment does not impose any restrictions on this.

[0132] Please see Figure 12 , Figure 12 This is a structural block diagram of a vehicle provided in an embodiment of this application. The vehicle 400 may include one or more components such as a memory 410, one or more processors 420, and one or more application programs. The one or more application programs may be stored in the memory 410 and configured to, when invoked by one or more processors 420, cause the one or more processors 420 to execute the vehicle speed planning method described above in this application embodiment. It should be noted that the vehicle 400 is related to the above... Figure 1 The same as the vehicle 11 shown, vehicle 400 can be applied to the above-mentioned vehicle speed planning system 10.

[0133] Processor 420 may include one or more processing cores. Processor 420 connects to various parts of the vehicle 400 via various interfaces and lines, and is used to run or execute instructions, programs, code sets, or instruction sets stored in memory 410, as well as to call and execute data stored in memory 410, performing various functions and processing data of the vehicle 400. Optionally, processor 420 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). Processor 420 may integrate one or a combination of several of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into processor 420, but implemented separately through a communication chip.

[0134] The memory 410 may include random access memory (RAM) or read-only memory (ROM). The memory 410 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 410 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing the various method embodiments described above, etc. The data storage area may store data created by the vehicle 400 during use.

[0135] Please see Figure 13 , Figure 13 This is a structural block diagram of a computer-readable storage medium 500 provided in an embodiment of this application. The computer-readable storage medium 500 stores program code 510, which is configured to, when invoked by a processor, cause the processor to execute the vehicle speed planning method described above in this embodiment of the application.

[0136] The computer-readable storage medium 500 may be an electronic storage device such as flash memory, electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), hard disk, or ROM. Optionally, the computer-readable storage medium 500 includes a non-volatile computer-readable storage medium (Non-TCRSM). The computer-readable storage medium 500 has storage space for program code 510 that performs any of the method steps described above. This program code 510 can be read from or written to one or more computer program products. The program code 510 may be compressed in an appropriate form.

[0137] In summary, this application provides a vehicle speed planning method, device, vehicle, and storage medium. By determining the recursive starting point (collision point or interference point), obstacles can be responded to in advance, thereby improving the safety of autonomous driving. Compared to the vehicle trajectory planned using existing vehicle speed planning methods, the vehicle trajectory planned using the speed planning method provided in this application avoids the target vehicle's trajectory and maintains a certain distance from it. This increases the safety redundancy distance between the vehicle and obstacles when changing lanes, thus improving the safety of autonomous driving.

[0138] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and not to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A vehicle speed planning method, characterized in that, include: Based on the driving trajectory of the vehicle and the driving trajectories of adjacent vehicles, the target vehicle, the starting point for recursion, and the recursion direction are determined. The target vehicle is a vehicle that poses a collision risk with the vehicle. The starting point for recursion is the trajectory point of the target vehicle when there is a collision risk between the target vehicle and the vehicle. The recursion direction includes forward recursion or backward recursion. Based on the starting point of the recursion, the trajectory of the target vehicle is recursively extended in the recursion direction for a preset period of time to obtain the trajectory after the recursion. Based on the recursive trajectory, the vehicle speed is planned. The step of extrapolating the trajectory of the target vehicle for a preset time period based on the extrapolation starting point to obtain the extrapolated trajectory includes: Obtain the speed of the target vehicle corresponding to the recursive starting point; Starting from the recursive starting point, the trajectory of the target vehicle is recursively extended in the recursive direction for a preset period of time based on the speed of the target vehicle corresponding to the recursive starting point, thus obtaining the recursively extended trajectory.

2. The method according to claim 1, characterized in that, The process of determining the target vehicle, the starting point, and the direction of recursion based on the vehicle's own trajectory and the trajectories of adjacent vehicles includes: Determine lane change status based on the vehicle's own driving trajectory and the driving trajectories of adjacent vehicles; The target vehicle, the starting point, and the direction of the recursion are determined based on the vehicle's lane-changing behavior.

3. The method according to claim 2, characterized in that, The step of determining the target vehicle, the starting point, and the direction of the advance based on the vehicle lane change includes: If the lane change occurs when a vehicle in an adjacent lane cuts into the vehicle's trajectory from in front of the vehicle, the target vehicle is identified as the vehicle in the adjacent lane. The starting point for recursion is determined as the trajectory point of the target vehicle when there is a risk of collision between the target vehicle and the voluntary vehicle; The recursion direction is determined to be forward recursion.

4. The method according to claim 2, characterized in that, The step of determining the target vehicle based on the vehicle lane-changing situation, and recursively determining the starting point and direction, includes: If the lane change occurs when the vehicle in front of the vehicle cuts out of the lane from in front of the vehicle, the target vehicle is identified as the vehicle in front. The starting point for recursion is determined as the trajectory point of the target vehicle when there is a risk of collision between the target vehicle and the voluntary vehicle; The recursive direction is determined to be backward.

5. The method according to claim 2, characterized in that, The step of determining the target vehicle based on the vehicle lane-changing situation, and recursively determining the starting point and direction, includes: If the vehicle lane change is a situation where the vehicle cuts into the adjacent lane from the front of a vehicle in the adjacent lane, the target vehicle is determined to be the vehicle in the adjacent lane. The starting point for recursion is determined as the trajectory point of the target vehicle when there is a risk of collision between the target vehicle and the voluntary vehicle; The recursion direction is determined to be forward recursion.

6. The method according to any one of claims 3 to 5, characterized in that, The method for determining that there is a collision risk between the target vehicle and the vehicular vehicle includes: Calculate the distance between the target vehicle's trajectory and the driver's trajectory; If the distance is less than a preset distance threshold, it is determined that there is a risk of collision between the target vehicle and the vehicle itself. If the distance is not less than the preset distance threshold, it is determined that there is no risk of collision between the target vehicle and the vehicle.

7. A vehicle speed planning device, characterized in that, include: The target determination module is used to determine the target vehicle, the starting point of the recursion, and the recursion direction based on the driving trajectory of the vehicle and the driving trajectories of adjacent vehicles. The target vehicle is a vehicle that has a collision risk with the vehicle. The starting point of the recursion is the trajectory point of the target vehicle when there is a collision risk between the target vehicle and the vehicle. The recursion direction includes forward recursion or backward recursion. The trajectory recursion module is used to recursively calculate the trajectory of the target vehicle for a preset time period in the recursion direction based on the recursion starting point, so as to obtain the recursed trajectory. The vehicle speed planning module is used to plan the vehicle speed based on the recursive trajectory. The trajectory recursion module is also used to obtain the speed of the target vehicle corresponding to the recursion starting point; starting from the recursion starting point, the trajectory of the target vehicle is recursively extended for a preset period of time in the recursion direction based on the speed of the target vehicle corresponding to the recursion starting point, so as to obtain the trajectory after recursion.

8. A vehicle, characterized in that, include: Memory; One or more processors; One or more applications, wherein the one or more applications are stored in the memory and configured to, when invoked by the one or more processors, cause the one or more processors to perform the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains program code that, when invoked by a processor, causes the processor to perform the method as described in any one of claims 1 to 6.

Images