Vehicle passing method and device, vehicle and storage medium
By obtaining vehicle status information and driving intentions, identifying collision risks and conducting pass sequence games, optimizing pass time, solving the safety and efficiency problems at the intersection without signal lights, and achieving safe interaction and efficient passage between vehicles.
Patent Information
- Application Number
- CN202510563946.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-29
- Publication Date
- 2025-07-11
AI Technical Summary
In an environment without signal lights and centralized roadside equipment, the driving safety of smart vehicles cannot be guaranteed, resulting in traffic chaos and inefficient traffic.
By obtaining the status information and driving intentions of the vehicle and the vehicle on the other road, identifying the collision risk, and triggering the pass sequence game, determining the game object from the vehicle on the other road, performing Nash equilibrium solution to optimize the pass time, and broadcasting control instructions to ensure safety and efficiency.
In the intersection scenario without signal lights and centralized controllers, the interaction characteristics between vehicles are improved, safety is ensured and the traffic efficiency of the intersection is improved.
Smart Images
Figure CN120299272A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the technical field of vehicles, and particularly relates to a vehicle passing method, device, vehicle and storage medium. Background Art
[0002] The core contents of intersection research are safety and passing efficiency. On the one hand, for driving safety, for intelligent vehicles, the indication of traffic lights and the distribution of road rights by centralized roadside devices are effective ways to allocate passing sequences. However, in an environment without traffic lights and centralized roadside devices, the driving safety of intelligent vehicles cannot be guaranteed, and there are phenomena of chaotic driving and traffic congestion, resulting in low passing efficiency. Summary of the Invention
[0003] In view of the above problems, this application proposes a vehicle passing method, device, vehicle and storage medium to solve the above problems.
[0004] In a first aspect, an embodiment of this application provides a vehicle passing method, which is applied to a vehicle traveling in an intersection area without a centralized roadside device and without traffic lights. The method includes: obtaining the state information and driving intentions of the vehicle itself and vehicles in different lanes, where the vehicles in different lanes are vehicles in lanes within the intersection range that do not belong to the lane where the vehicle itself is located but whose trajectories intersect with the lane where the vehicle itself is located; when it is determined based on the state information and the driving intentions that there is a collision risk between the vehicle itself and the vehicles in different lanes, triggering a passing sequence game, and determining at least one game object from all the vehicles in different lanes, where the game object includes a game monomer and / or a game group, and the game group is a vehicle group composed of multiple vehicles in the same lane and having a collision risk with the vehicle itself; in the passing sequence game stage, solving for the Nash equilibrium through the passing times of the vehicle itself and the at least one game object, searching for a Pareto optimal solution that meets the conditions in the obtained Nash equilibrium solution set, and then updating the passing times of all vehicles and broadcasting them to other vehicles, where when solving for the Nash equilibrium, there is a game group, and the safety inflation margin of the game group matches the length of the game group, and the passing time is the time for the vehicle to pass through the intersection; when the passing times of all vehicles are the minimum passing times, determining the passing sequences and corresponding control commands of the vehicle itself and the at least one game object, so that each vehicle operates according to the passing sequences and corresponding control commands.
[0005] Second aspect, an embodiment of the present application provides a vehicle passing device, which runs on a vehicle traveling in an intersection area without a centralized roadside device and without traffic lights. The device includes: an acquisition unit, configured to acquire the status information and driving intentions of the vehicle itself and vehicles in different lanes. The vehicles in different lanes are vehicles in lanes within the intersection range that do not belong to the lane where the vehicle is located but whose trajectories intersect with the lane where the vehicle is located; a triggering unit, configured to trigger a passing sequence game when it is determined based on the status information and the driving intentions that there is a collision risk between the vehicle and the vehicles in different lanes, and determine at least one game object from all the vehicles in different lanes. The game object includes a game monomer and / or a game group, and the game group is a vehicle group composed of multiple vehicles in the same lane and having a collision risk with the vehicle; a game unit, configured to solve the Nash equilibrium through the passing times of the vehicle itself and the at least one game object during the passing sequence game stage, search for a Pareto optimal solution that meets the conditions in the obtained Nash equilibrium solution set, and then update the passing times of all vehicles and broadcast them to other vehicles. Among them, when solving the Nash equilibrium, there is a game group, and the safety inflation margin of the game group matches the length of the game group. The passing time is the time for the vehicle to pass through the intersection; a determination unit, configured to determine the passing sequence and corresponding control instructions of the vehicle itself and the at least one game object when the passing times of all vehicles are the minimum passing times, so that each vehicle operates according to the passing sequence and the corresponding control instructions.
[0006] Third aspect, an embodiment of the present application provides a vehicle, which includes one or more processors and a memory; one or more programs, where the one or more programs are stored in the memory and configured to be executed by the one or more processors. The one or more programs are configured to execute the above-mentioned method.
[0007] Fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which program code is stored. When the program code runs, the above-mentioned method is executed.
[0008] The embodiments of the present application provide a vehicle passing method, apparatus, vehicle, and storage medium. First, obtain the status information and driving intentions of the vehicle itself and the vehicles in different lanes. When it is determined based on the status information and driving intentions that there is a collision risk between the vehicle itself and the vehicles in different lanes, trigger a passing sequence game, determine at least one game object from all the vehicles in different lanes, and then, in the passing sequence game stage, solve for the Nash equilibrium through the passing times of the vehicle itself and at least one game object. After searching for the Pareto optimal solution that meets the conditions in the obtained Nash equilibrium solution set, update the passing times of all vehicles and broadcast them to other vehicles. When the passing times of all vehicles are the minimum passing times, determine the passing sequences and corresponding control instructions of the vehicle itself and at least one game object, so that each vehicle operates according to the passing sequences and corresponding control instructions. Through the above method, in the intersection scenario without traffic lights and centralized controllers, by using the passing between vehicles, direct games are carried out between individual vehicles and vehicle groups, which can effectively enhance the interaction characteristics between vehicles and improve the passing efficiency of intersections while ensuring safety. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those skilled in the art, without creative efforts, other drawings can also be obtained based on these drawings.
[0010] Figure 1 FIG. shows a flowchart of a vehicle passing method proposed in an embodiment of the present application;
[0011] Figure 2 FIG. shows a scene diagram of vehicle passing at an intersection in an embodiment of the present application;
[0012] Figure 3 FIG. shows a flowchart of a vehicle passing method proposed in another embodiment of the present application;
[0013] Figure 4 FIG. shows a schematic diagram of a collision point in vehicle passing at an intersection in another embodiment of the present application;
[0014] Figure 5 FIG. shows a schematic diagram of a collision point in vehicle passing at an intersection in another embodiment of the present application;
[0015] Figure 6 FIG. shows a structural block diagram of a vehicle passing apparatus proposed in an embodiment of the present application;
[0016] Figure 7 FIG. shows a structural block diagram of a vehicle passing system proposed in an embodiment of the present application;
[0017] Figure 8 A structural block diagram of a vehicle for executing a vehicle passing method according to an embodiment of the present application is shown;
[0018] Figure 9 A storage unit for storing or carrying program codes for implementing the vehicle passing method according to an embodiment of the present application is shown. Detailed implementation manners
[0019] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.
[0020] An embodiment of the present application provides a vehicle passing method, device, vehicle, and storage medium. First, obtain the state information and driving intentions of the vehicle itself and the vehicles in different lanes. When it is determined based on the state information and driving intentions that there is a collision risk between the vehicle itself and the vehicles in different lanes, trigger a passing sequence game, determine at least one game object from all the vehicles in different lanes, and then in the passing sequence game stage, solve the Nash equilibrium through the passing times of the vehicle itself and at least one game object. After searching for the Pareto optimal solution that meets the conditions in the obtained Nash equilibrium solution set, update the passing times of all vehicles and broadcast them to other vehicles. When the passing times of all vehicles are the minimum passing times, determine the passing sequences and corresponding control instructions of the vehicle itself and at least one game object, so that each vehicle operates according to the passing sequences and corresponding control instructions. Through the above method, in the intersection scenario without traffic lights and centralized controllers, the passing between vehicles is utilized to enable direct game between single vehicles and vehicle groups, which can effectively enhance the interaction characteristics between vehicles and improve the passing efficiency of intersections while ensuring safety.
[0021] Next, each embodiment of the present application will be specifically described in conjunction with the accompanying drawings.
[0022] Please refer to Figure 1 , a vehicle passing method provided by an embodiment of the present application, which is applied to a vehicle traveling in an intersection area without a centralized roadside device and without traffic lights. The method includes:
[0023] Step S110: Obtain the state information and driving intentions of the vehicle itself and the vehicles in different lanes. The vehicles in different lanes are vehicles in lanes within the intersection range that do not belong to the lane where the vehicle itself is located but have trajectory intersections with the lane where the vehicle itself is located.
[0024] In an embodiment of the present application, the state information includes: the position information of the vehicle and the speed information of the vehicle; the driving intention includes: one of going straight, turning left, and turning right.
[0025] Among them, the position information of the vehicle may include the longitude, latitude, and altitude information of the vehicle; the speed information of the vehicle may include the speed information of the vehicle, the acceleration information of the vehicle, the heading information of the vehicle, etc. The intersection range refers to the range of vehicle communication that can be provided by the intersection V2X (Vehicle-to-Everything) technology, as well as the effective range of direct information interaction between vehicles V2V (Vehicle-to-Vehicle). The intersection is a regular road 4-branch orthogonal intersection, and the intersection range is defined as a circle with a radius of 150 m centered at the intersection point of the extended lines of the road driving direction isolation lines. For special-shaped intersections, such as intersections with multiple branches and non-orthogonal intersections, the range is changed accordingly. To prevent too many vehicles from participating in the game, within the intersection range, at most 5 vehicles in the same driving direction lane participate.
[0026] Vehicles in different lanes refer to vehicles in lanes within the intersection range that do not belong to the lane where the vehicle is located but whose trajectories intersect with the lane where the vehicle is located. For example, as Figure 2 shown, in Figure 2 there are vehicle 1, vehicle 2, vehicle 3, vehicle 4, and vehicle 5. In the intersection scenario shown in Figure 2 , if vehicle 1 is the vehicle itself and goes straight, then vehicle 2, vehicle 3, and vehicle 4 are vehicles in different lanes of the vehicle itself; vehicle 5 belongs to the vehicle's different lane vehicles only when turning left, and does not belong to the vehicle's different lane vehicles when turning right or going straight.
[0027] As a way, vehicles in different lanes can be determined from the surrounding vehicles of the vehicle itself. Specifically, based on the broadcasts of the surrounding vehicles, the vehicle itself receives the state information and driving intentions of the surrounding vehicles. Furthermore, the vehicle itself can determine the vehicles in different lanes of the vehicle itself from the surrounding vehicles according to the driving intentions of the vehicle itself and the surrounding vehicles, where the determined vehicles in different lanes can be at least one vehicle. Screening vehicles in different lanes according to the driving intentions of the vehicle itself and the surrounding vehicles can reduce the time and computing power required for negotiation.
[0028] After determining the vehicles in different lanes of the vehicle itself through the above method, the state information and driving intentions of only the vehicle itself and the vehicles in different lanes can be further retained to avoid occupying the memory of the vehicle itself. Among them, the vehicle itself can be understood as the vehicle driven by the user himself.
[0029] In the embodiments of the present application, the vehicle's longitude and latitude, speed, acceleration, and heading angle can be obtained in real time through in-vehicle sensors (such as GPS, IMU, speed sensors). The dynamic information (position, speed, acceleration, heading) and driving intentions (going straight, turning left, turning right) of surrounding vehicles can be received through V2X communication (such as DSRC / C-V2X).
[0030] Step S120: When it is determined based on the state information and the driving intention that there is a collision risk between the host vehicle and a vehicle in a different lane, trigger a passing sequence game, and determine at least one game object from all vehicles in different lanes. The game object includes a game single entity and / or a game group. The game group is a vehicle group composed of multiple vehicles in the same lane and having a collision risk with the host vehicle.
[0031] In the embodiments of the application, the collision risk means that in a certain adjacent future time period, if there is an intersection point between the predicted trajectories of the host vehicle and a vehicle in a different lane, it is determined that there is a collision risk. The game object refers to a vehicle having a collision risk with the host vehicle; the game single entity refers to a single vehicle in a different lane, and the game group refers to multiple vehicles in a different lane; the game single entity and the game group respectively correspond to a single-entity game and a group game. Among them, the single-entity game means that the object of the game of the host vehicle is a single vehicle, and the group game means that the object of the game of the host vehicle is a group composed of multiple vehicles in the same lane and having a collision risk with the host vehicle.
[0032] After obtaining the state information and driving intentions of the host vehicle and vehicles in different lanes, it is possible to determine whether there is a collision risk between the host vehicle and a vehicle in a different lane based on the state information and driving intentions of the host vehicle and vehicles in different lanes respectively.
[0033] Through the foregoing explanation of the collision risk, it can be known that it is necessary to predict the future driving trajectories of the host vehicle and a vehicle in a different lane, that is, it is necessary to know the predicted driving trajectories of the host vehicle and a vehicle in a different lane. Among them, the predicted driving trajectory is the trajectory that the host vehicle and a vehicle in a different lane will travel in a certain future time period.
[0034] In the embodiments of the present application, the passing sequence game refers to judging the order of vehicles passing through the intersection. The game refers to the host vehicle and a vehicle in a different lane playing a single-entity or group game to judge whether the host vehicle can pass through the middle of the game object, that is, cut off the traffic flow.
[0035] When it is determined that there is a collision risk between the host vehicle and a vehicle in a different lane, the vehicles in different lanes can be combined in permutation and combination to form game objects (which can include game single entities and / or game groups) for the game. For example, Figure 2As shown in the figure, the subscripts 1-4 are vehicle IDs respectively. If V1 is the vehicle itself, there are five groups of reasonable game objects. The first group of game objects is V2 (single vehicle); the second group of game objects is V2 (single vehicle), V3 (single vehicle); the third group of game objects is the group composed of V2 (single vehicle), V3 and V4; the fourth group of game objects is the group composed of V2 and V3, V4 (single vehicle); the fifth group of game objects is the group composed of V2, V3, and V4.
[0036] Step S130: In the passing sequence game stage, solve the Nash equilibrium through the passing times of the vehicle itself and the at least one game object respectively, search for the Pareto optimal solution that meets the conditions in the obtained Nash equilibrium solution set, and then update the passing times of all vehicles and broadcast them to other vehicles. Among them, when solving the Nash equilibrium, there are game groups, and the safety inflation margin of the game group matches the length of the game group. The passing time is the time for the vehicle to pass through the intersection.
[0037] In the embodiment of the present application, the passing times of all vehicles refer to: Among them, g() is a function definition with the function of solving the passing time; Related to the optimization of the acceleration a, it means that each game object selects a control quantity to participate in the Nash equilibrium calculation; u * is the optimized control quantity, u s is the progressive control quantity, "this" and "game" respectively represent the vehicle itself and the game object; the time for a single vehicle to pass through the intersection Among them, v is the speed, a is the acceleration, m is the vehicle ID, i is the iteration number, and p is the distance from the collision point.
[0038] The update of the passing times of all vehicles refers to: Among them, the definition of g() is the same as above, The superscript p in it is the control quantity for distinguishing the Pareto optimum, is the control quantity optimized according to the change range of the length of the game object.
[0039] The calculation formula for the distance from the collision point is: Among them, d1 is the distance from the centroid of the host vehicle to the centroid of the game object at the time of collision; 2h is the distance from the host vehicle to the centroid of the game object at the time of collision when the host vehicle travels behind; d2r is the distance from the host vehicle to the centroid of the game object at the time of collision when the host vehicle travels ahead; L and W are the length and width after the vehicle is safely inflated. Among them, "L_host" and "L_game" respectively represent the length after the host vehicle is safely inflated and the length after the game object is safely inflated, and "W_host" and "W_game" respectively represent the width after the host vehicle is safely inflated and the width after the game object is safely inflated. The safe inflation is to expand the length and width of the vehicle in proportion; p1 is the distance of the host vehicle from the collision point; p2h is the distance of the game object from the collision point when the host vehicle travels behind; p2r is the distance of the game object from the collision point when the host vehicle travels ahead.
[0040] In the embodiments of the present application, the safe inflation refers to expanding the length and width of the vehicle in proportion, that is, a rectangle that coincides with the centroid of the vehicle and has the same heading, and the specific proportion is determined by oneself.
[0041] When the game object is a game monomer, the width after the game object is safely inflated is the width after the game monomer is safely inflated, the length after the game object is safely inflated is the length after the game monomer is safely inflated, and the centroid position of the game object is the centroid position of the game monomer; when the game object is a game group, the width after the game object is safely inflated is the maximum width after each vehicle included in the game group is safely inflated respectively, the length after the game object is safely inflated is the length from the front of the leading vehicle to the rear of the trailing vehicle in the game group, and the centroid position of the game object is at the midpoint of the line connecting the centroids of the vehicles included in the game group.
[0042] Exemplarily, as Figure 2 shown, if the game object of the host vehicle V1 is V2, then the length after the game object is safely inflated is the length after V2 is safely inflated, the width after the game object is safely inflated is the width after V2 is safely inflated, and the centroid position of the game object is the centroid position of V2; if the game object of the host vehicle V1 is a group composed of V2 and V3, then the length after the game object is safely inflated is the length from the front of V2 to the rear of V3, the width after the game object is safely inflated is max(W2, W3), and the centroid position of the game object is at the midpoint of the line connecting the centroids of V2 and V3.
[0043] Optionally, in the embodiments of the present application, the host vehicle conducts a travel time game with at least one game object respectively, and obtains a Pareto solution by traversing the obtained Nash equilibrium solution set. The travel times of all vehicles (including the host vehicle and the game objects) can be determined based on the distances from the collision point. The travel times of all vehicles are the times for all the vehicles involved within the intersection range at the current moment to pass through the intersection, that is, the sum of the times for each vehicle to reach the center of the intersection range from the current moment, specifically Among them, the time for a single vehicle to pass through the intersection From this formula, it can be known that the passing time T of all vehicles total is strongly correlated with the distance p from the collision point. When p is determined, v and a can be iteratively calculated by the optimization algorithm. Therefore, the purpose of game negotiation is to optimize T by optimizing the value of the distance p from the collision point. Among them, the vehicles involved within the intersection range at the current moment refer to the vehicle itself and the vehicles in different lanes that need to be involved at the start of the game, excluding the vehicles outside the intersection communication range and also excluding the vehicles that newly enter the intersection range after the start of the game. The newly entered vehicles at the intersection will be recombined to participate in a new game. total
[0044] Step S140: When the passing time of all vehicles is the minimum passing time, determine the passing order and corresponding control instructions of the vehicle itself and the at least one game object, so that each vehicle operates according to the passing order and corresponding control instructions.
[0045] In the embodiment of the present application, within a preset distance (such as 50 m) from the center of the intersection, the determined passing order shall not be changed to prevent danger caused by sudden changes in the passing order.
[0046] When the minimum passing time of all vehicles is found, based on this minimum passing time, the optimized control quantities and passing order of the vehicle itself and the at least one game object can be inversely deduced using the aforementioned formula. After obtaining the optimized control quantities and passing order of the vehicle itself and the at least one game object, the optimized control quantities and passing order can be broadcast to other vehicles, and then other vehicles can perform corresponding operations based on the passing order and corresponding optimized control quantities.
[0047] For the process described in steps S130 - S140, such as single - vehicle game, in the intersection scenario shown in Figure 2 if the first group of game objects of the vehicle itself is determined to be V2 (single vehicle); the second group of game objects is V2 (single vehicle), V3 (single vehicle); the third group of game objects is a group composed of V2 (single vehicle), V3, and V4; the fourth group of game objects is a group composed of V2 and V3, V4 (single vehicle); the fifth group of game objects is a group composed of V2, V3, and V4.
[0048] Then for the first group, in the single game between V1 (the vehicle itself) and V2 (the game object), there are two passing orders for V1. One is to pass before V2, and the other is to pass after V2. The two passing methods of V1 are closely related to the collision point. When the distance p from the collision point is determined, using the formula The passing time of each vehicle can be calculated. By adjusting the acceleration a, the passing time can be optimized. Therefore, the calculation formula for the passing time of all vehicles can be transformed into where g() is a function definition with the function of solving the passing time, which is related to the optimization of the acceleration a. It means that each vehicle selects a control quantity to participate in the Nash equilibrium calculation. For example, the combination, where u * is the optimized control quantity, and u s is the progressive control quantity. The Nash equilibrium is a series of feasible solution sets that satisfy the optimization goal when solving the optimization problem.
[0049] The time is obtained through different combinations. Therefore, the solution sets of the times of V1 and V2 are 1×4 vectors, that is, there are four different combinations, but each combination needs to be enumerated and calculated.
[0050] Thus, through the selection of the elements in the solution set of T total , that is, the element with the smallest value, the passing time of all vehicles can be updated through this element with the smallest value. Furthermore, the passing order and the corresponding optimized control quantities can be deduced inversely. For example, For the combination corresponding to T total if the element in it is the smallest, then are the control quantities that V1 and V2 need to execute in the future respectively. At the same time, the passing order can be judged by the distance p from the corresponding distance collision point. Here, it is assumed that V1 passes before V2. If not, that is, V1 passes after V2, then V1 needs to conduct a new game negotiation with the single vehicle V3 and the group composed of V3 and V4 to determine the passing order of V1 among V3 and V4.
[0051] For example, in the group game, for the fourth group, since the vehicle V1 cannot pass in front of V3, it needs to play a game with the group composed of V2 and V3 and the single vehicle V4.
[0052] At this time, the same parts of the game process as the first group's game process will not be elaborated. The passing time of all vehicles where the subscript 23 represents the group composed of V2 and V3. Due to the existence of the virtual group of V2V3, the length of the virtual group will change with the change of V3, resulting in the change of the centroid position of the virtual group, and thus the distance from the distance collision point is unstable. Therefore, the passing time of all vehicles involving the virtual group is updated as where the definition of g() is the same as above. The superscript p in it is the control quantity for distinguishing the Pareto optimum. The control quantity is obtained by optimizing the range of changes in the length of the virtual group. Then, the time is obtained through different combinations in the same way as the above-mentioned single-unit game. The time solution set of this group is a 1×27 vector. The passage order is thus determined. After iterative games, if the passage order is V2V3V1V4, the group composed of V2 and V3 is still established, and the distance between V2 and V3 will continue to shorten to reduce the overall passing time. While the distance is shortened, the formula is still used. Iteration, thus the change of the passing order will gradually decrease, and the passing order will gradually become clear. For the group composed of V2 and V3, the restriction of V3 on the optimization calculation of the control quantity is that it cannot rear-end with V2.
[0053] The present application provides a vehicle passage method that utilizes the passage between vehicles in an intersection scenario without traffic lights and centralized controllers, allowing single vehicles and vehicle groups to directly compete with each other, which can effectively enhance the interaction characteristics between vehicles and improve the passage efficiency of intersections while ensuring safety.
[0054] See also Figure 3 A vehicle passing method provided in an embodiment of the present application is applied to a vehicle traveling in an intersection area without centralized roadside equipment and without traffic lights, and the method includes:
[0055] Step S210: Obtaining the status information and driving intention of the host vehicle and the vehicle in another lane, wherein the vehicle in another lane is a vehicle in a lane that does not belong to the host vehicle's lane but has a trajectory intersecting with the lane in which the host vehicle is located within the intersection.
[0056] Step S220: Based on the state information and the driving intention, the predicted driving trajectories of the vehicle and all other-lane vehicles are determined.
[0057] In an embodiment of the present application, after obtaining the respective status information and driving intentions of the vehicle and the vehicle in the other lane, the respective status information and driving intentions of the vehicle and the vehicle in the other lane can be respectively input into a pre-trained trajectory prediction model, so that the trajectory prediction model can output the predicted driving trajectories of the vehicle and the vehicle in the other lane.
[0058] Alternatively, based on the respective state information (such as speed, acceleration) and driving intention (such as steering angle) of the vehicle and the vehicle in the other lane, the respective driving trajectories of the vehicle and the vehicle in the other lane are predicted through a kinematic model (such as a constant acceleration model).
[0059] Step S230: Based on the predicted driving trajectory, determine whether there is a risk of collision between the vehicle and the vehicle in the other lane. If so, execute steps S240, S250 and S260; if not, execute step S270.
[0060] In an embodiment of the present application, determining whether there is a collision risk between the host vehicle and a vehicle in a different lane based on the predicted driving trajectory may refer to determining whether there is an intersection between the predicted driving trajectories of the host vehicle and the vehicle in the different lane within a certain future time period. If there is an intersection, it can be determined that there is a collision risk; if there is no intersection, it can be determined that there is no collision risk.
[0061] As a method, based on the predicted driving trajectory, determine the potential collision point between the host vehicle and the vehicle in the different lane; based on the predicted driving trajectory and the state information, determine the time difference between the host vehicle and the vehicle in the different lane to reach the potential collision point; based on the time difference, determine whether there is a collision risk between the host vehicle and the vehicle in the different lane.
[0062] Among them, the potential collision point refers to the position point where the host vehicle and the vehicle in the different lane may collide, that is, it can be understood as the intersection of the predicted driving trajectories of the host vehicle and the vehicle in the different lane.
[0063] In an embodiment of the present application, since the driving intentions of the host vehicle and the vehicle in the different lane are different, therefore, different driving intentions and different passing sequences will result in different potential collision points, and different potential collision points will affect the evaluation of the collision time. For example, as Figure 4 shown in the head-on collision point of two vehicles when going straight - straight, this figure shows that V1 goes first; as Figure 5 shown in the head and tail collision points of two vehicles when going straight - straight, this figure shows that V2 goes first. According to Figure 4 and Figure 5 ( Figure 4 and Figure 5 the dashed boxes in are the future predictions of the vehicle which are unknown) it can be found that even in the same straight - ahead scenario, due to different passing sequences, there will also be problems where the collision positions of the two vehicles are different. The same is true for the collision points when the vehicle goes straight and turns.
[0064] In an embodiment of the present application, the time difference (ΔT) between the two vehicles to reach the collision point can be calculated according to the predicted driving trajectories of the host vehicle and the vehicle in the different lane respectively. If ΔT is less than the safety threshold (for example, 3 seconds), it is determined that there is a collision risk and the game process is triggered; otherwise, the vehicle proceeds according to the original plan.
[0065] Step S240: Trigger the passing sequence game and determine at least one game object from all vehicles in different lanes.
[0066] Step S250: In the passing sequence game stage, solve the Nash equilibrium through the passing times of the host vehicle and the at least one game object respectively, search for the Pareto - optimal solution that meets the conditions in the obtained Nash equilibrium solution set, and then update the passing times of all vehicles and broadcast them to other vehicles.
[0067] Step S260: When the passing time of all vehicles is the minimum passing time, determine the passing order and corresponding control instructions of the vehicle itself and the at least one game object, so that each vehicle operates according to the passing order and corresponding control instructions.
[0068] Step S270: Each vehicle drives away under the speed limit specified at the intersection.
[0069] In the embodiment of the present application, when it is determined that there is no collision risk between the vehicle itself and the vehicles in different lanes, each vehicle can pass through and leave the intersection at a speed not greater than the speed limit specified at the intersection.
[0070] A vehicle passing method provided by the present application is applied to an intersection area without signal lights and without centralized roadside equipment deployed with fully intelligent vehicles. By using V2X communication, vehicle groups obtain the passing order at the intersection through a game method, improving the passing efficiency at the intersection while ensuring safety.
[0071] Please refer to Figure 6 , a vehicle passing device 300 provided by an embodiment of the present application runs on a vehicle traveling in an intersection area without centralized roadside equipment and without signal lights. The device 300 includes:
[0072] An acquisition unit 310, configured to acquire the state information and driving intentions of the vehicle itself and vehicles in different lanes. The vehicles in different lanes are vehicles in lanes within the intersection range that do not belong to the lane where the vehicle itself is located but whose trajectories intersect with the lane where the vehicle itself is located.
[0073] A trigger unit 320, configured to trigger a passing order game when it is determined based on the state information and the driving intentions that there is a collision risk between the vehicle itself and the vehicles in different lanes, and determine at least one game object from all the vehicles in different lanes. The game object includes a game monomer and / or a game group, and the game group is a vehicle group composed of multiple vehicles in the same lane and having a collision risk with the vehicle itself.
[0074] A game unit 330, configured to solve the Nash equilibrium through the passing times of the vehicle itself and the at least one game object during the passing order game stage, search for a Pareto optimal solution that meets the conditions in the obtained Nash equilibrium solution set, and then update the passing times of all vehicles and broadcast them to other vehicles. Among them, when solving the Nash equilibrium, there is a game group, and the safety inflation margin of the game group matches the length of the game group. The passing time is the time for the vehicle to pass through the intersection.
[0075] Among them, the passing times of all vehicles refer to: Among them, g() is a function definition with the function of solving the passing time; Related to the optimization of acceleration a, which means that each game object selects a control quantity to participate in the Nash equilibrium calculation; u * is the optimized control quantity, u s is the progressive control quantity, where "this" and "game" respectively represent the vehicle itself and the game object; the time for a single vehicle to pass through the intersection where v is the speed, a is the acceleration, m is the vehicle ID, i is the iteration number, and p is the distance from the collision point; the updating of the passing time of all vehicles means: where g() is defined as above, the superscript p in it is used to distinguish the control quantity of Pareto optimality, is the control quantity optimized according to the change range of the length of the game object.
[0076] The calculation formula for the distance from the collision point is:
[0077] where d1 is the distance from the centroid of the vehicle itself to the centroid of the game object when a collision occurs; d2h is the distance from the vehicle itself to the centroid of the game object when the vehicle itself is moving backward and a collision occurs; d2r is the distance from the vehicle itself to the centroid of the game object when the vehicle itself is moving forward and a collision occurs; L and W are the length and width after the vehicle safety inflation, where "L vehicle itself" and "L game" respectively represent the length after the vehicle safety inflation of the vehicle itself and the length after the vehicle safety inflation of the game object, "W vehicle itself" and "W game" respectively represent the width after the vehicle safety inflation of the vehicle itself and the width after the vehicle safety inflation of the game object, and the safety inflation is to expand the length and width of the vehicle in proportion; p1 is the distance from the vehicle itself to the collision point; p2h is the distance from the game object to the collision point when the vehicle itself is moving backward; p2r is the distance from the game object to the collision point when the vehicle itself is moving forward.
[0078] The determination unit 340 is used to determine the passing order and the corresponding control instruction of the vehicle itself and the at least one game object when the passing time of all vehicles is the minimum passing time, so that each vehicle operates according to the passing order and the corresponding control instruction.
[0079] As a way, the determination unit 340 is also used to, if it is determined that there is no collision risk between the vehicle itself and the vehicles in different lanes, each vehicle drives away under the speed limit specified at the intersection.
[0080] Optionally, as Figure 7 shown, the vehicle passing device 300 further includes:
[0081] The judgment unit 350 is used to determine the predicted driving trajectories of the vehicle itself and all vehicles in different lanes respectively based on the state information and the driving intention; and determine whether there is a collision risk between the vehicle itself and the vehicles in different lanes based on the predicted driving trajectories.
[0082] As a way, the determination unit 350 is further configured to determine a potential collision point between the host vehicle and a vehicle in a different lane based on the predicted driving trajectory; determine a time difference between the host vehicle and the vehicle in a different lane reaching the potential collision point based on the predicted driving trajectory and the status information; and determine whether there is a collision risk between the host vehicle and the vehicle in a different lane based on the time difference.
[0083] It should be noted that the device embodiments in this application correspond to the foregoing method embodiments. The specific principles in the device embodiments can be referred to in the content of the foregoing method embodiments, and will not be elaborated here.
[0084] The following will be combined with Figure 8 to describe a vehicle provided in this application.
[0085] Please refer to Figure 8 , based on the above vehicle passing method and device, another vehicle 800 that can execute the foregoing vehicle passing method is further provided in an embodiment of this application. The vehicle 800 includes one or more (only one is shown in the figure) processors 802, a memory 804, and a network module 806 that are coupled to each other. Among them, a program that can execute the content in the foregoing embodiments is stored in the memory 804, and the processor 802 can execute the program stored in the memory 804.
[0086] Among them, the processor 802 may include one or more processing cores. The processor 802 connects various parts within the entire vehicle 800 using various interfaces and lines, and executes various functions of the vehicle 800 and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 804, and by calling data stored in the memory 804. Optionally, the processor 802 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 802 may integrate a combination of one or several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs, etc.; the GPU is responsible for rendering and drawing the display content; the modem is used to process wireless communication. It can be understood that the above modem may not be integrated into the processor 802 and may be implemented separately through a communication chip.
[0087] The memory 804 may include a Random Access Memory (RAM), or may also include a Read-Only Memory. The memory 804 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 804 may include a program storage area and a data storage area. Among them, the program storage area can store instructions for implementing the operating system, instructions for implementing at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the following various method embodiments, etc. The data storage area can also store data created during the use of the vehicle 800 (such as phone book, audio and video data, chat record data), etc.
[0088] The network module 806 is used to receive and send electromagnetic waves, realize the mutual conversion between electromagnetic waves and electrical signals, so as to communicate with a communication network or other devices, such as communicating with a vehicle. The network module 806 may include various existing circuit elements for performing these functions. For example, an antenna, a radio frequency transceiver, a digital signal processor, an encryption / decryption chip, a Subscriber Identity Module (SIM) card, a memory, etc. The network module 806 can communicate with various networks such as the Internet, an enterprise intranet, a wireless network, or communicate with other devices through a wireless network. The above-mentioned wireless network may include a cellular phone network, a wireless local area network, or a metropolitan area network. For example, the network module 806 can interact with a base station for information.
[0089] Please refer to Figure 9 , which shows a structural block diagram of a computer-readable storage medium provided by an embodiment of the present application. Program code is stored in the computer-readable storage medium 900, and the program code can be called by a processor to execute the method described in the above method embodiments.
[0090] The computer-readable storage medium 900 can be an electronic memory such as a flash memory, an Electrically Erasable Programmable Read-Only Memory (EEPROM), an EPROM, a hard disk, or a ROM. Optionally, the computer-readable storage medium 900 includes a non-transitory computer-readable storage medium. The computer-readable storage medium 900 has a storage space for the program code 910 for executing any method step in the above method. These program codes can be read out from one or more computer program products or written into these one or more computer program products. The program code 910 can be compressed in an appropriate form, for example.
[0091] A vehicle passing method, device, vehicle, and storage medium provided by this application first obtain the status information and driving intentions of the vehicle itself and vehicles in different lanes. When it is determined that there is a collision risk between the vehicle itself and the vehicles in different lanes based on the status information and driving intentions, a passing order game is triggered, and at least one game object is determined from all the vehicles in different lanes. Then, in the passing order game stage, the Nash equilibrium is solved by using the passing times of the vehicle itself and at least one game object respectively. After searching for the Pareto optimal solution that meets the conditions in the obtained Nash equilibrium solution set, the passing times of all vehicles are updated and broadcast to other vehicles. When the passing times of all vehicles are the minimum passing times, the passing order and corresponding control instructions of the vehicle itself and at least one game object are determined, so that each vehicle operates according to the passing order and corresponding control instructions. Through the above method, in the intersection scenario without traffic lights and centralized controllers, by using the passing between vehicles, direct game is carried out between single vehicles and vehicle groups, which can effectively enhance the interaction characteristics between vehicles and improve the passing efficiency of intersections while ensuring safety.
[0092] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms without departing from the spirit and scope protected by the present invention and the claims, and all of them belong to the protection scope of the present invention.
Claims
1. A vehicle passing method, characterized in that, Applied to vehicles traveling in the intersection area without centralized roadside equipment and traffic lights, the method includes: Obtain the status information and driving intentions of the vehicle itself and vehicles in different lanes. The vehicles in different lanes are vehicles in lanes within the intersection range that do not belong to the lane where the vehicle itself is located but whose trajectories intersect with the lane where the vehicle itself is located; When it is determined based on the status information and the driving intentions that there is a collision risk between the vehicle itself and the vehicles in different lanes, trigger a game for the passing order, and determine at least one game object from all the vehicles in different lanes. The game object includes a game monomer and / or a game group. The game group is a vehicle group composed of multiple vehicles in the same lane that have a collision risk with the vehicle itself; In the stage of the game for the passing order, solve the Nash equilibrium through the passing times of the vehicle itself and the at least one game object respectively, search for the Pareto optimal solution that meets the conditions in the obtained Nash equilibrium solution set, and then update the passing times of all vehicles and broadcast them to other vehicles. Among them, when solving the Nash equilibrium, there is a game group, and the safety inflation margin of the game group matches the length of the game group. The passing time is the time for the vehicle to pass through the intersection; When the passing times of all vehicles are the minimum passing times, determine the passing order and corresponding control instructions of the vehicle itself and the at least one game object, so that each vehicle operates according to the passing order and the corresponding control instructions.
2. The method according to claim 1, characterized in that, All the vehicle passing times mentioned above refer to: where g() is a function definition with the function of solving the passing time; related to the optimization of acceleration a, indicating that each game object selects a control quantity to participate in the Nash equilibrium calculation; u * is the optimized control quantity, u s is the progressive control quantity. "This" and "game" respectively represent the vehicle itself and the game object; the passing time of a single vehicle through the intersection where v is the speed, a is the acceleration, m is the vehicle ID, i is the iteration number, and p is the distance from the collision point; Said updating all vehicle passing times means that: wherein, the definition of g() is the same as above, The superscript p in the upper right corner is the control quantity for distinguishing the Pareto optimum, is the control quantity optimized according to the change range of the length of the game object.
3. The method according to claim 2, wherein The calculation formula for the distance from the collision point is as follows: Wherein, d1 is the distance from the centroid of the host vehicle to the centroid of the game object at the time of collision; d2h is the distance from the host vehicle to the centroid of the game object at the time of collision when the host vehicle is traveling behind; d2r is the distance from the host vehicle to the centroid of the game object at the time of collision when the host vehicle is traveling ahead; L and W are the length and width after the vehicle safety expansion, wherein, "L_host" and "L_game" respectively represent the length after the safety expansion of the host vehicle and the length after the safety expansion of the game object, "W_host" and "W_game" respectively represent the width after the safety expansion of the host vehicle and the width after the safety expansion of the game object, and the safety expansion is that the length and width of the vehicle are enlarged proportionally; p1 is the distance of the host vehicle from the collision point; p2h is the distance of the game object from the collision point when the host vehicle is traveling behind; p2r is the distance of the game object from the collision point when the host vehicle is traveling ahead.
4. The method according to claim 1, wherein Before triggering the game for the passing order when it is determined based on the status information and the driving intentions that there is a collision risk between the vehicle itself and the vehicles in different lanes, it further includes: Based on the status information and the driving intentions, determine the predicted driving trajectories of the vehicle itself and all vehicles in different lanes; Based on the predicted driving trajectories, determine whether there is a collision risk between the vehicle itself and the vehicles in different lanes.
5. The method according to claim 4, wherein The determining whether there is a collision risk between the vehicle itself and the vehicles in different lanes based on the predicted driving trajectories includes: Based on the predicted driving trajectories, determine the potential collision points of the vehicle itself and the vehicles in different lanes; Based on the predicted driving trajectories and the status information, determine the time difference between the vehicle itself and the vehicles in different lanes to reach the potential collision points; Based on the time difference, determine whether there is a collision risk between the vehicle itself and the vehicles in different lanes.
6. The method according to claim 1, characterized in that, The method further includes: If it is determined that there is no collision risk between the vehicle itself and the vehicles in different lanes, each vehicle drives away under the speed limit specified at the intersection.
7. The method according to any one of claims 1-6, characterized in that, The status information includes: the position information of the vehicle and the speed information of the vehicle; the driving intention includes: one of going straight, turning left, and turning right.
8. A vehicle passing device, characterized in that, Operating on a vehicle traveling in the intersection area without centralized roadside equipment and traffic lights, the device includes: An acquisition unit, configured to acquire the status information and driving intentions of the vehicle itself and vehicles in different lanes. The vehicles in different lanes are vehicles in lanes within the intersection range that do not belong to the lane where the vehicle itself is located but whose trajectories intersect with the lane where the vehicle itself is located; A triggering unit, configured to trigger a passing sequence game when it is determined, based on the state information and the driving intention, that there is a collision risk between the host vehicle and a vehicle in a different lane, and determine at least one game object from all the vehicles in the different lane, where the game object includes a game single body and / or a game group, and the game group is a vehicle group formed by multiple vehicles in the same lane and having a collision risk with the host vehicle; A game unit, configured to, in the passing sequence game stage, solve for the Nash equilibrium through the passing times of the host vehicle and the at least one game object respectively, search for a Pareto optimal solution that meets the conditions from the obtained Nash equilibrium solution set, and then update the passing times of all vehicles and broadcast them to other vehicles. When solving for the Nash equilibrium, there is a game group, and the safety inflation margin of the game group matches the length of the game group, and the passing time is the time for the vehicle to pass through the intersection; A determining unit, configured to determine the passing sequence and the corresponding control instructions of the host vehicle and the at least one game object when the passing times of all vehicles are the minimum passing times, so that each vehicle operates according to the passing sequence and the corresponding control instructions.
9. A vehicle, characterized in that, Comprising one or more processors and a memory; one or more programs are stored in the memory and configured to be executed by the one or more processors to perform the method according to any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, Program code is stored in the computer-readable storage medium, where the method according to any one of claims 1-7 is executed when the program code is run by the processor.