Conflict Handling Method, Device, Equipment and Storage Medium

Abstract

The present disclosure provides a conflict handling method, apparatus, device, and storage medium, which relate to the field of artificial intelligence technologies such as autonomous driving and intelligent transportation. The method includes: determining a target obstacle from obstacles based on the trajectory information of a target vehicle and the trajectory information of the obstacles, where the target obstacle is an obstacle whose trajectory information conflicts with the trajectory information of the target vehicle; determining the conflict type between the target vehicle and the target obstacle, where the conflict type includes a deterministic conflict and an indeterministic conflict; determining a target conflict handling result according to the conflict type and the number of target obstacles, and adjusting the driving speed of the target vehicle according to the target conflict handling result. The method provided by the present disclosure can handle conflicts in deterministic / indeterministic conflict scenarios differently, ensuring the driving safety of the vehicle.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, specifically to the fields of autonomous driving and intelligent transportation technology, and particularly to a conflict handling method, apparatus, device, and storage medium. Background Art

[0002] When an autonomous driving vehicle is driving in some complex scenarios, such as a scenario where interacting vehicles appear in the form of a continuous traffic flow, if a spatio-temporal conflict occurs between the autonomous driving vehicle and other interacting vehicles, the autonomous driving vehicle should make its own vehicle decision on the premise of considering the speed, trajectory and other information of all vehicles in the traffic flow, so as to avoid collisions, scratches and other behaviors with other interacting vehicles. Summary of the Invention

[0003] The present disclosure provides a conflict handling method, apparatus, device, and storage medium.

[0004] According to a first aspect of the present disclosure, there is provided a conflict handling method, including: determining a target obstacle from obstacles based on the trajectory information of a target vehicle and the trajectory information of an obstacle, where the target obstacle is an obstacle whose trajectory information conflicts with the trajectory information of the target vehicle; determining a conflict type between the target vehicle and the target obstacle, where the conflict type includes a deterministic conflict and an indeterministic conflict; determining a target conflict handling result according to the conflict type and the number of target obstacles, and adjusting the driving speed of the target vehicle according to the target conflict handling result.

[0005] According to a second aspect of the present disclosure, there is provided a conflict handling apparatus, including: an obstacle determination module configured to determine a target obstacle from obstacles based on the trajectory information of a target vehicle and the trajectory information of an obstacle, where the target obstacle is an obstacle whose trajectory information conflicts with the trajectory information of the target vehicle; a conflict determination module configured to determine a conflict type between the target vehicle and the target obstacle, where the conflict type includes a deterministic conflict and an indeterministic conflict; a result determination module configured to determine a target conflict handling result according to the conflict type and the number of target obstacles, and adjust the driving speed of the target vehicle according to the target conflict handling result.

[0006] According to a third aspect of the present disclosure, there is provided an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; where the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method described in any implementation manner of the first aspect.

[0007] According to a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the method described in any implementation manner of the first aspect.

[0008] According to a fifth aspect of the present disclosure, there is provided a computer program product including a computer program which, when executed by a processor, performs the method described in any implementation manner of the first aspect.

[0009] According to a sixth aspect of the present disclosure, there is provided a self-driving vehicle including the electronic device described in the third aspect.

[0010] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings are used to better understand the solution and do not constitute a limitation to the present disclosure. Among them:

[0012] Figure 1 is a flowchart of a first embodiment of the conflict handling method according to the present disclosure;

[0013] Figure 2 is a schematic diagram of a conflict area;

[0014] Figure 3 is a flowchart of a second embodiment of the conflict handling method according to the present disclosure;

[0015] Figure 4 is a flowchart of a third embodiment of the conflict handling method according to the present disclosure;

[0016] Figure 5 is a flowchart of a fourth embodiment of the conflict handling method according to the present disclosure;

[0017] Figure 6 is a schematic diagram of a horizontal overlap relationship;

[0018] Figure 7 is a flowchart of a fifth embodiment of the conflict handling method according to the present disclosure;

[0019] Figure 8 is a flowchart of a sixth embodiment of the conflict handling method according to the present disclosure;

[0020] Figure 9 is a schematic structural diagram of an embodiment of the conflict handling device according to the present disclosure;

[0021] Figure 10It is a block diagram of an electronic device for implementing the conflict handling method of the embodiments of the present disclosure. Detailed implementation manners

[0022] The following describes exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0023] It should be noted that, without conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other. The present disclosure will be described in detail below with reference to the drawings and in conjunction with the embodiments.

[0024] An exemplary system architecture for implementing the conflict handling method provided by the present disclosure may include a terminal device, a network, and a server. Among them, the network is used to provide a communication link between the terminal device and the server, and may include various connection types, for example, wired communication links, wireless communication links, or fiber optic cables, etc.

[0025] Users can use the terminal device to interact with the server through the network to receive or send information, etc. Various client applications can be installed on the terminal device, such as map applications, navigation applications, entertainment applications, etc.

[0026] The terminal device can be hardware or software. When the terminal device is hardware, it can be various electronic devices, including but not limited to smart phones, tablet computers, laptop portable computers, and desktop computers, etc.; it can also be intelligent devices such as vehicles and intelligent robots, such as autonomous driving vehicles, delivery robots, etc. When the terminal device is software, it can be installed in the above-mentioned electronic devices. It can be implemented as multiple software or software modules, or can be implemented as a single software or software module. No specific limitation is made here.

[0027] The server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules (for example, used to provide distributed services), or can be implemented as a single software or software module. No specific limitation is made here.

[0028] It should be pointed out that the conflict handling method provided by the present disclosure can be executed by the server in the above system architecture, or can be implemented through the above terminal device.

[0029] Figure 1Shows the process 100 of the first embodiment of the conflict handling method according to the present disclosure. The conflict handling method includes the following steps:

[0030] Step 101, based on the trajectory information of the target vehicle and the trajectory information of the obstacle, determine the target obstacle from the obstacles.

[0031] In this embodiment, the execution entity of the conflict handling method, such as a server or a terminal device (such as an in-vehicle terminal), based on the trajectory information of the target vehicle and the trajectory information of the obstacle, determines the target obstacle from the obstacles, where the target obstacle is an obstacle whose trajectory information conflicts with the trajectory information of the target vehicle.

[0032] The above-mentioned execution entity will first obtain the trajectory information of its own vehicle. Here, the trajectory information can refer to the planned trajectory, and it will also obtain the pose, speed and other information of its own vehicle. Here, the own vehicle is the autonomous vehicle and also the target vehicle. Then the above-mentioned execution entity will also obtain the trajectory information of other interacting vehicles (i.e., obstacles). Here, the trajectory information of the obstacle can be the predicted trajectory, and it will also obtain the pose, speed and other information of the obstacle. The obstacle here can be one or more, and the number of obstacles is not limited in this embodiment.

[0033] After that, the above-mentioned execution entity will determine the target obstacle according to the trajectory information of the target vehicle and the trajectory information of the obstacle, that is, determine the obstacle whose trajectory information conflicts with the trajectory information of the target vehicle. Correspondingly, the number of target obstacles can also be one or more. Specifically, the above-mentioned execution entity will judge whether the trajectory of the obstacle and the trajectory of the target vehicle will conflict at a certain moment or during a certain period according to the speed, trajectory and other information of the target vehicle and the speed, trajectory and other information of the obstacle, that is, whether there is an overlapping area between the two trajectories. If a conflict occurs, the obstacle is determined as the target obstacle.

[0034] It should be noted that if there are multiple obstacles, it is necessary to judge whether the trajectory of each obstacle will conflict with the trajectory of the target vehicle respectively, so as to determine whether the current obstacle is the target obstacle.

[0035] Step 102, determine the conflict type between the target vehicle and the target obstacle.

[0036] In this embodiment, the above-mentioned execution entity will determine the conflict type between the target vehicle and the target obstacle, where the conflict type includes a deterministic conflict and an indeterministic conflict. A deterministic conflict refers to an obvious collision relationship, and an indeterministic conflict means that there may not be an obvious collision relationship.

[0037] Specifically, the execution subject will determine whether there is a conflict zone between the target vehicle and the obstacle according to the predicted trajectory of the target vehicle and the predicted trajectory of the obstacle. If there is a conflict zone, it is determined that the conflict type between the target vehicle and the obstacle is a deterministic conflict.

[0038] It should be noted that the boundary of the conflict zone is taken from the projection position of the overlap area of ​​the vehicle path and other obstacle predicted trajectories on their respective paths. Figure 2 A schematic diagram of the conflict zone is shown in Figure 2 As shown, ABCD is the interactive conflict area between the ego vehicle and the other vehicle, A is the front boundary of the ego vehicle arriving at the conflict area, B is the rear boundary of the ego vehicle leaving the conflict area, C is the front boundary of the other vehicle arriving at the conflict area, and D is the rear boundary of the other vehicle leaving the conflict area.

[0039] Uncertainty conflict means that there is no clear collision relationship between the target vehicle and the obstacle, but there is a conflict trend, or a slight change in the driving state of one party will pose a driving threat to the other party. For example, in strong interaction areas such as merging and diverging, there is a merging lane in front of the lane where the obstacle is located, but the obstacle is currently in the straight lane, then it may have a collision risk with the vehicle when it merges into the lane later. In this case, the conflict type between the obstacle and the target vehicle is uncertain conflict.

[0040] Step 103: determining a target conflict processing result according to the conflict type and the number of target obstacles, and adjusting the driving speed of the target vehicle according to the target conflict processing result.

[0041] In this embodiment, the execution subject further determines the number of target obstacles, which can be a specific number or divided into one or more. Then, the target conflict result is determined according to the conflict type and the number of target obstacles. The target conflict result includes yielding and overtaking, that is, for the conflict situation of the target obstacle, the target vehicle chooses to overtake or yield, and the driving speed of the target vehicle is adjusted according to the target conflict result. For example, if the target vehicle chooses to overtake, it will speed up; if it chooses to yield, it will slow down to avoid collision with the target obstacle.

[0042] For example, when the conflict type is a deterministic conflict and there is only one target obstacle, the execution entity will calculate the probability of the ego vehicle cutting in and the probability of the target obstacle cutting in, and then determine whether the ego vehicle cuts in or gives way based on the calculated probabilities.

[0043] For another example, when the conflict type is deterministic and there are multiple target obstacles, the above-mentioned execution entity will reduce the size of the set of interactive agents (i.e., target obstacles) as much as possible to avoid selecting more low-risk obstacles that affect the traffic efficiency of the vehicle.

[0044] For another example, in the case where the conflict type is an uncertainty conflict and there is one target obstacle, the host vehicle will decelerate, so as to respond through a preventive deceleration strategy, ensuring that the host vehicle has more sufficient adjustment time at the moment when the uncertainty risk turns into a certainty risk.

[0045] For another example, in the case where the conflict type is an uncertainty conflict and there are multiple target obstacles, since there is no specific avoidance object, the goal of the host vehicle becomes to continuously process the agents that successively catch up with the host vehicle, so as to take into account lateral safety while ensuring traffic efficiency.

[0046] The conflict handling method provided by the embodiments of the present disclosure first determines a target obstacle that conflicts with a target vehicle, then determines a target conflict handling result for coping with the conflict according to the number of target obstacles and the conflict type between the target vehicle and the target obstacle, and finally adjusts the driving speed of the target vehicle according to the target conflict handling result, so as to handle conflicts in deterministic / uncertainty conflict scenarios differently, ensuring the driving safety of the vehicle.

[0047] In addition, in the technical solutions involved in the present disclosure, the acquisition, storage, use, processing, transportation, provision, and disclosure of the user's personal information (such as the trajectory information of the vehicle involved in the subsequent part of the present disclosure, etc.) comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0048] Continue to refer to Figure 3 , Figure 3 shows a flow 300 of a second embodiment of the conflict handling method according to the present disclosure. The conflict handling method includes the following steps:

[0049] Step 301, based on the trajectory information of the target vehicle and the trajectory information of the obstacle, determine the target obstacle from the obstacles.

[0050] In this embodiment, the execution subject of the conflict handling method, such as a server or a terminal device (such as an in-vehicle terminal), based on the trajectory information of the target vehicle and the trajectory information of the obstacle, determines the target obstacle from the obstacles, where the target obstacle is an obstacle whose trajectory information conflicts with the trajectory information of the target vehicle.

[0051] Step 301 is basically the same as step 101 of the foregoing embodiment, and the specific implementation manner can refer to the description of step 101 above, which will not be elaborated here.

[0052] Step 302, determine the conflict type between the target vehicle and the target obstacle.

[0053] In this embodiment, the above-mentioned execution entity determines the conflict type between the target vehicle and the target obstacle, where the conflict type includes a deterministic conflict and an indeterministic conflict.

[0054] Step 302 is basically the same as step 102 of the foregoing embodiment. The specific implementation manner can refer to the description of step 102 above and will not be elaborated here.

[0055] Step 303, in response to determining that the conflict type is a deterministic conflict and the number of target obstacles is one, improves the yielding benefit of the target vehicle in the pre-constructed game payment matrix according to the yielding waiting time of the target vehicle, and improves the yielding benefit of the target obstacle in the game payment matrix according to the yielding waiting time of the target obstacle, to obtain an improved game payment matrix.

[0056] In this embodiment, if it is determined that the conflict type is a deterministic conflict and there is only one target obstacle, considering that long-term queuing and waiting are likely to cause traffic jams and other situations, therefore, on the basis of the general game payment matrix, considering the concept of waiting time, the benefit of the target vehicle choosing to yield will decrease as the waiting time increases, so as to obtain an improved game payment matrix.

[0057] Table 1 is the general game payment matrix. In Table 1, vehicle M is the target obstacle and vehicle N is the own vehicle (i.e., the target vehicle). Each value in the matrix represents the benefit. For example, the value in the first row and the first column of the matrix is the benefit value of the decision of vehicle M cutting in and vehicle N cutting in. Table 1 is as follows:

[0058] Table 1 General game payment matrix

[0059]

[0060] According to the general game payment matrix in Table 1 and formula (1), the cutting-in probabilities of the own vehicle (vehicle N) and the target obstacle (vehicle M) can be further calculated. Formula (1) is as follows:

[0061] ,

[0062] ; (1)

[0063] Wherein, and are the cutting-in probabilities of the own vehicle and the target obstacle respectively; and are the risk perception utility values of the own vehicle and the target obstacle respectively, and , is the time for the own vehicle to reach the collision area, and They are the time loss utility values of the host vehicle and the target obstacle respectively, and their values are equal to the time for each interactive agent to pass through the conflict area; a and c are the time loss utility coefficient and the conflict time loss coefficient respectively, reflecting the time loss of yielding and the additional time loss when a conflict occurs.

[0064] Then, the above-mentioned execution entity will improve the yielding benefit of the target vehicle in the general game payment matrix in Table 1 according to the yielding waiting time of vehicle N, and improve the yielding benefit of the target obstacle in the general game payment matrix in Table 1 according to the yielding waiting time of vehicle M, to obtain an improved game payment matrix. Table 2 is the improved game payment matrix, which is shown as follows:

[0065] Table 2 Improved game payment matrix

[0066]

[0067] Step 304: Calculate the first cut-in probability of the target vehicle and the second cut-in probability of the target obstacle according to the improved game payment matrix.

[0068] In this embodiment, the above-mentioned execution entity will further calculate the first cut-in probability and the second cut-in probability according to the improved game matrix shown in Table 2 and formula (2). Formula (2) is shown as follows:

[0069] ,

[0070] ; (2)

[0071] Among them, is the first cut-in probability, is the second cut-in probability; is the braking and waiting time of the host vehicle, is the braking and waiting time of the target obstacle, and are the waiting time influence coefficients, and .

[0072] Step 305: Determine the first processing result according to the first cut-in probability and the second cut-in probability, determine the first processing result as the target conflict processing result, and adjust the driving speed of the target vehicle according to the target conflict processing result.

[0073] In this embodiment, the above-mentioned execution entity determines a first processing result according to the calculated first cutting-in probability and second cutting-in probability. The first processing result is the processing result of a single-obstacle deterministic conflict, and the first processing result is determined as the target conflict processing result, where the first processing result includes cutting in or yielding. Specifically, if the first cutting-in probability is greater than the second cutting-in probability, the first processing result is that the host vehicle cuts in; if the first cutting-in probability is not greater than the second cutting-in probability, the first processing result is that the target obstacle cuts in, that is, the host vehicle yields. Finally, the driving speed of the host vehicle is adjusted according to the target conflict processing result, so as to avoid collision with the target obstacle.

[0074] It can be seen from Figure 3 that compared with the corresponding embodiment, in the conflict processing method of this embodiment, when the conflict type is a deterministic conflict and the number of target obstacles is one, an improved game payment matrix is obtained according to the yielding waiting time of the target vehicle, and the cutting-in probabilities of the target vehicle and the target obstacle are calculated according to the improved game payment matrix, and the final processing result is determined according to the two cutting-in probabilities, so as to ensure the driving safety of the vehicle in the single-obstacle deterministic conflict scenario. Figure 1

[0075] Figure 4 Continuing to refer to Figure 4 which shows the flowchart 400 of the third embodiment of the conflict processing method according to the present disclosure. The conflict processing method includes the following steps:

[0076] Step 401, based on the trajectory information of the target vehicle and the trajectory information of the obstacle, determine the target obstacle from the obstacles.

[0077] Step 402, determine the conflict type between the target vehicle and the target obstacle.

[0078] Step 403, in response to determining that the conflict type is a deterministic conflict and the number of target obstacles is one, improve the yielding benefit of the target vehicle in the pre-constructed game payment matrix according to the yielding waiting time of the target vehicle, and improve the yielding benefit of the target obstacle in the game payment matrix according to the yielding waiting time of the target obstacle, to obtain an improved game payment matrix.

[0079] Step 404, calculate the first cutting-in probability of the target vehicle and the second cutting-in probability of the target obstacle according to the improved game payment matrix.

[0080] Steps 401-404 are basically the same as steps 301-304 of the foregoing embodiment, and the specific implementation manner can refer to the description of steps 301-304 above, which will not be elaborated here.

[0081] ​​Step 405: Determine the right-of-way correction amount according to the right-of-way information of the target vehicle relative to the target obstacle, and correct the first cutting-in probability according to the right-of-way correction amount to obtain the corrected first cutting-in probability.

[0082] In this embodiment, the execution subject of the conflict handling method, such as a server or a terminal device (such as an in-vehicle terminal), further dynamically corrects the decision probability according to the right-of-way. Since the right-of-way is a relative concept, that is, the right-of-way attribute of A to B and the right-of-way attribute of A to C are independent, the right-of-way is defined as three categories: dominant, equal, and inferior. Taking the lane-changing scenario as an example, the right-of-way information of the target vehicle relative to the target obstacle is calculated through the following steps:

[0083] Obtain the lane 1 where the host vehicle is located, the lane 2 where the target obstacle is located, and their common successor lane 3, and define the lane continuity threshold ;

[0084] Calculate the heading difference between lane 1 and lane 3, denoted as ; where, heading is the lane line direction in the world coordinate system;

[0085] Calculate the heading difference between lane 2 and lane 3, denoted as ;

[0086] Compare , The numerical relationship between them. If and , then the host vehicle has a dominant right-of-way compared to the target obstacle; if and , then the host vehicle has an equal right-of-way compared to the target obstacle; if and , then the host vehicle has an inferior right-of-way compared to the target obstacle.

[0087] For different right-of-way attributes, the decision probability should be dynamically corrected. Therefore, the right-of-way correction amounts corresponding to the dominant, equal, and inferior right-of-ways are defined as: dominant correction amount , equal correction amount and inferior correction amount . Correct the first cutting-in probability according to the right-of-way correction amount to obtain the corrected first cutting-in probability expressed as:

[0088] ;

[0089] It should be noted that generally is taken as 0, and there is > > .

[0090] Step 406: Determine a first processing result based on the corrected first cut-in probability and the second cut-in probability, determine the first processing result as the target conflict processing result, and adjust the driving speed of the target vehicle according to the target conflict processing result.

[0091] In this embodiment, the above-mentioned execution entity determines a first processing result according to the corrected first cut-in probability and the second cut-in probability, and determines the first processing result as the target conflict processing result, where the first processing result includes cut-in or yielding. Specifically, if the corrected first cut-in probability is greater than the second cut-in probability, the first processing result is that the vehicle itself cuts in; if the corrected first cut-in probability is not greater than the second cut-in probability, the first processing result is that the target obstacle cuts in, that is, the vehicle itself yields. Finally, adjust the driving speed of the vehicle itself according to the target conflict processing result, so as to avoid collision with the target obstacle.

[0092] From Figure 4 it can be seen that compared with the Figure 3 corresponding embodiment, in the conflict processing method of this embodiment, when the conflict type is a deterministic conflict and the number of target obstacles is one, an improved game payment matrix is obtained according to the yielding waiting time of the target vehicle, and the cut-in probability of the target vehicle and the cut-in probability of the target obstacle are calculated according to the improved game payment matrix. On this basis, the cut-in probability of the vehicle itself is further corrected according to the right-of-way attribute of the target vehicle relative to the target obstacle, and the final processing result is determined according to the corrected cut-in probability of the vehicle itself and the cut-in probability of the target obstacle, so as to ensure the driving safety of the vehicle in the single-obstacle deterministic conflict scenario.

[0093] Continue to refer to Figure 5 , Figure 5 shows a flow 500 of a fourth embodiment of the conflict processing method according to the present disclosure. The conflict processing method includes the following steps:

[0094] Step 501: Based on the trajectory information of the target vehicle and the trajectory information of the obstacle, determine a target obstacle from the obstacles.

[0095] Step 502: Determine the conflict type between the target vehicle and the target obstacle.

[0096] Steps 501-502 are basically the same as steps 101-102 of the foregoing embodiment, and the specific implementation manner can refer to the description of steps 101-102 above, which will not be elaborated here.

[0097] Step 503: In response to determining that the conflict type is a deterministic conflict and the number of target obstacles is multiple, perform rough clustering on the multiple target obstacles according to the lateral distance between the multiple target obstacles and the road boundary to obtain multiple obstacle queues after clustering.

[0098] In this embodiment, the execution subject of the conflict handling method, such as a server or a terminal device (such as an in-vehicle terminal), if it determines that the conflict type is a deterministic conflict and the number of target obstacles is multiple, the above execution subject will roughly cluster the multiple target obstacles according to the lateral distance between the multiple target obstacles and the road boundary, so as to obtain multiple obstacle queues after clustering. The specific algorithm is as follows:

[0099] A. Initialization: Define sets open set, close set, and buffer set. Place all obstacles in the open set in the order from front to back. The close set and the buffer set are empty sets. Define the maximum longitudinal queuing gap threshold ;

[0100] B. Move the first element of the open set to the buffer set;

[0101] C. Traverse the open set collection in the upper layer to query whether there is a lateral overlap relationship between the obstacle and any obstacle in the buffer set, and traverse the buffer set in the lower layer;

[0102] c.1. If there is no overlap relationship, continue to traverse the upper layer;

[0103] c.2. If there is an overlap relationship, calculate the longitudinal distance between the obstacle and the obstacle in the buffer set, denoted as d. If d < , move the obstacle to the buffer set, otherwise, continue to traverse the lower layer;

[0104] D. Place the buffer set in the close set and empty the buffer set;

[0105] E. Repeat steps B to D until the open set is empty.

[0106] The close set finally obtained by the above algorithm is the rough clustering result.

[0107] Among them, the schematic definition of the lateral overlap relationship is as Figure 6 shown, in Figure 6In this case, there is no lateral overlap relationship between obstacle 1 and obstacle 2, while there is a lateral overlap relationship between agent 3 (obstacle 3) and agent 1 (obstacle 1), and agent 2 (obstacle 2). Specifically, the lateral positions of obstacle 1, obstacle 2, and obstacle 3 in the SL coordinate system can be obtained first, and then it can be determined whether there is a lateral overlap relationship by judging whether there is an overlapping relationship between the lateral coordinates of obstacle 1, obstacle 2, and obstacle 3. If there is an overlapping relationship, there is a lateral overlap relationship. For example, there is an overlap between the lateral coordinates of obstacle 3 and both obstacle 1 and obstacle 2. Therefore, there is a lateral overlap relationship between obstacle 3 and obstacle 1, and obstacle 2. If there is no overlapping relationship, there is no lateral overlap relationship. For example, there is no overlap between the lateral coordinates of obstacle 1 and obstacle 2. Therefore, there is no lateral overlap relationship between obstacle 1 and obstacle 2.

[0108] Step 504, for multiple obstacle queues, according to the first processing result between the target vehicle and the leading obstacle in the obstacle queue, divide the obstacle queue into a queue set of cutting-in obstacles or a queue set of yielding obstacles.

[0109] In this embodiment, for the multiple obstacle queues obtained by rough clustering, they will be further divided into a queue set of cutting-in obstacles and a queue set of yielding obstacles. The specific algorithm is as follows:

[0110] A. Initialization: Define the yield set and the rush set to record the set of self-vehicle cutting-in agents and the set of yielding agents.

[0111] B. Traverse the close set (rough clustering result) and judge the single-agent decision (i.e., the first processing result) between the self-vehicle and the leading obstacle.

[0112] b.1. If the decision result is to cut in, place the leading obstacle in the rush set.

[0113] b.2. If the decision result is to yield, place the trailing obstacle in the yield set.

[0114] Thus, the queue set of cutting-in obstacles (yield set) or the queue set of yielding obstacles (rush set) is obtained.

[0115] Step 505, perform combined optimization on the queue set of cutting-in obstacles and the queue set of yielding obstacles, determine the second processing result according to the solution result, determine the second processing result as the target conflict processing result, and adjust the driving speed of the target vehicle according to the target conflict processing result.

[0116] In this embodiment, the above-mentioned execution entity shrinks the scale of decision-making obstacles to the yield set and the rush set, and obtains the final planning result through combinatorial optimization, thereby obtaining the second processing result, which is the processing result of multi-obstacle deterministic conflict, and taking the second processing result as the target conflict processing result. Finally, the driving speed of the host vehicle is adjusted according to the target conflict processing result to avoid collision with the target obstacle.

[0117] It should be noted that the above decision-making process is based on the strong assumption that the obstacles in the queue cannot pass over the previous obstacles, and this assumption holds and is universal in general cases.

[0118] From Figure 5 it can be seen that compared with the corresponding embodiment of Figure 1 in this embodiment, for the conflict handling method, when the conflict type is deterministic conflict and the number of target obstacles is multiple, the method first performs rough clustering on the multiple obstacles to obtain multiple queues, and then divides the multiple queues into the rush obstacle queue set or the yield obstacle queue set according to the single-obstacle deterministic processing result between the host vehicle and the leading obstacle of each queue. Finally, the final processing result is obtained through combinatorial optimization, so as to ensure the driving safety of the vehicle in the multi-obstacle deterministic conflict scenario.

[0119] Continuing to refer to Figure 7 , Figure 7 shows the flow 700 of the fifth embodiment of the conflict handling method according to the present disclosure. The conflict handling method includes the following steps:

[0120] Step 701, based on the trajectory information of the target vehicle and the trajectory information of the obstacle, determine the target obstacle from the obstacles.

[0121] Step 702, determine the conflict type between the target vehicle and the target obstacle.

[0122] Steps 701-702 are basically the same as steps 101-102 of the foregoing embodiment, and the specific implementation manner can refer to the description of steps 101-102 above, and will not be elaborated here.

[0123] Step 703, in response to determining that the conflict type is an uncertain conflict and the number of target obstacles is one, determine the yield waiting time of the target vehicle according to the lateral distance between the target obstacle and the target vehicle.

[0124] In this embodiment, the execution subject of the conflict handling method, such as a server or a terminal device (such as a vehicle-mounted terminal), if it determines that the conflict type is an uncertainty conflict and there is only one target obstacle, the host vehicle responds through a preventive speed reduction strategy, so as to ensure that the host vehicle has more sufficient adjustment time at the moment when the uncertainty risk turns into a certainty risk. In addition, in order to ensure the traffic efficiency, only the vehicles side by side with the host vehicle are subject to preventive response handling. For side-by-side avoidance, the response decision quantity is defined as the time required for the host vehicle to avoid the target obstacle and go first (yield waiting time), and this time should be related to the lateral distance between the target obstacle and the host vehicle, and can be specifically calculated according to formula (3):

[0125] ; (3)

[0126] where T is the avoidance time, λ is the influence coefficient of the distance on the avoidance time, is the lateral distance between the target obstacle and the host vehicle, is the maximum lateral consideration distance, is the minimum lateral tolerance distance, is the time required for the host vehicle to avoid the obstacle under the limit deceleration, which is calculated through the following formula (4):

[0127] ; (4)

[0128] where and are the speeds of the current host vehicle and the target obstacle respectively, is the limit deceleration, is the distance between the rear of the current host vehicle and the rear of the obstacle (with the vehicle driving direction as the positive direction), is the length of the host vehicle.

[0129] Step 704: Determine a speed control quantity for controlling the driving speed of the target vehicle according to the yield waiting time, use the speed control quantity as the target conflict handling result, and adjust the driving speed of the target vehicle according to the target conflict handling result.

[0130] In this embodiment, the above-mentioned execution subject will determine the speed control quantity according to the yield waiting time , which can be specifically calculated according to formula (5):

[0131] ; (5)

[0132] Finally, use the speed control quantity as the target conflict handling result, and adjust the driving speed of the target vehicle according to the target conflict handling result, so as to avoid possible conflicts with the target obstacle.

[0133] From Figure 7It can be seen that compared with the embodiment corresponding to Figure 1 in this embodiment, for the conflict handling method, when the conflict type is an uncertain conflict and the number of target obstacles is one, the host vehicle responds through a preventive speed reduction strategy, so as to ensure that the host vehicle has more sufficient adjustment time at the moment when the uncertain risk turns into a certain risk, and avoid possible conflicts with the target obstacles.

[0134] Continue to refer to Figure 8 , Figure 8 shows a flowchart 800 of a sixth embodiment of the conflict handling method according to the present disclosure. The conflict handling method includes the following steps:

[0135] Step 801, based on the trajectory information of the target vehicle and the trajectory information of the obstacle, determine the target obstacle from the obstacles.

[0136] Step 802, determine the conflict type between the target vehicle and the target obstacle.

[0137] Steps 801-802 are basically the same as steps 101-102 of the foregoing embodiment. The specific implementation manner can refer to the description of steps 101-102 above, and will not be elaborated here.

[0138] Step 803, in response to determining that the conflict type is an uncertain conflict and the number of target obstacles is multiple, generate an obstacle trajectory set according to the trajectory information of the multiple target obstacles.

[0139] In this embodiment, for the execution subject of the conflict handling method, such as a server or a terminal device (such as an in-vehicle terminal), if it is determined that the conflict type is an uncertain conflict and the number of target obstacles is multiple, the above execution subject will first generate a target obstacle set, which includes multiple target obstacles, and then traverse the target obstacle set to collect the future driving trajectories of each target obstacle, so as to obtain an obstacle trajectory set , where n is the number of target obstacles, is the trajectory of the nth target obstacle.

[0140] Step 804, solve the optimal boundary value according to the start state and end state of the relative trajectory of the target vehicle.

[0141] In this embodiment, the above execution subject will solve the optimal boundary value according to the start state and end state of the relative trajectory of the target vehicle, where the relative trajectory is the relative trajectory between the trajectory information of the target vehicle and the obstacle trajectory in the obstacle trajectory set.

[0142] That is, the above-mentioned execution entity will first generate the relative trajectory between the trajectory information of the target vehicle and the obstacle trajectories in the obstacle trajectory set. Specifically, the above-mentioned execution entity will first traverse the obstacle trajectory set , and then re-project the ego-vehicle trajectory using the trajectory as the reference line to obtain the ego-vehicle relative trajectory . Among them, is a function that represents projecting the ego-vehicle trajectory using the obstacle trajectory as the reference line. That is, the input of this function is the ego-vehicle trajectory, and the output is the relative trajectory of the ego-vehicle relative to the obstacle trajectory . Then, the optimal boundary value is solved according to the starting state and the ending state of the relative trajectory of the target vehicle

[0143] In some optional implementation manners of this embodiment, step 804 further includes: traversing the obstacle trajectory set, respectively using the current obstacle trajectory as the reference line to project the trajectory information of the target vehicle, and obtaining multiple segments of the projected relative trajectory of the target vehicle; for each segment of the projected relative trajectory of the target vehicle, determining the starting state and the ending state of the relative trajectory, and solving the optimal boundary value according to the starting state and the ending state

[0144] In this implementation manner, the worst-case assumption is followed when generating the reference trajectory: multiple obstacles (traffic flow) do not overtake continuously in time sequence

[0145] First, judge the relative position between the obstacle and the ego-vehicle. Denote the ego-vehicle driving direction vector as , and the connection vectors between the ego-vehicle geometric center and the corner points of the obstacle (box) are respectively , , , . Define the following functions

[0146]

[0147] If f = 4, the obstacle is on the left side of the ego-vehicle. If f = -4, the obstacle is on the right side of the ego-vehicle, and the direction is denoted as .

[0148] Secondly, collect the boundary points of the obstacle predicted trajectory. The boundary selection direction is opposite to the direction of the obstacle relative to the ego-vehicle, that is direction. The set of driving trajectory points is denoted as

[0149] , o ∈ ;

[0150] Densify the driving trajectory points, and denote the set of cumulative S values at each point . Among them

[0151] , ;

[0152] Denote the minimum dense unit as Δs, then at the k-th dense point, is:

[0153] ;

[0154] Perform a binary search in the set s of S values to obtain the S-value interval corresponding to the dense point k , and further, the corresponding driving trajectory point interval is , and the coordinates of this dense point are denoted as:

[0155] = + ;

[0156] Denote the driving trajectory of agent i as:

[0157] ;

[0158] Perform the same processing on the ego-vehicle driving trajectory to obtain the ego-vehicle driving trajectory as:

[0159] ;

[0160] Since the driving direction of the ego-vehicle is basically the same as the driving road direction of the obstacle set, therefore, to speed up the search speed, define the search lower bound index χ that increases and updates, and search for the closest projection point of the ego-vehicle trajectory point on the reference trajectory and its index j, denoted as:

[0161] ,

[0162] ;

[0163] When searching for the ego-vehicle trajectory point , its matching range is [χ, N]. Repeat the above steps to obtain . Repeat the execution for all to obtain . For , handle it according to the worst-case assumption, and the g function has:

[0164] ;

[0165] After that, consider the envelope range between the local extreme points of the ego-vehicle projected trajectory when selecting the interval. Assume there are n extreme points, then there are n - 1 speed limit intervals, and the extreme points satisfy:

[0166] ;

[0167] The interval speed limit is executed for each interval one by one backward from the current state. In the first interval, the starting state is the current state:

[0168] ;

[0169] Among them, is the current cumulative S value of the host vehicle, generally 0; and are the current speed and acceleration of the host vehicle respectively.

[0170] Assume that the projection point at the first extreme point is , then the speed limit at this extreme point is defined as:

[0171] ;

[0172] Among them, is the road speed limit, is the lateral distance at time t (the lateral distance from the obstacle trajectory), is the maximum considered lateral distance or the safety distance, and k is a hyperparameter.

[0173] At the first extreme point:

[0174] ;

[0175] Among them, represents the dense unit distance, and t is the time.

[0176] Therefore, the end state of the first segment is , is a random quantity.

[0177] Then the above-mentioned execution entity will solve the optimal boundary value according to the starting state and the end state.

[0178] Step 805: Determine the interval speed of the target vehicle on the relative trajectory according to the solution result, use the interval speed as the target conflict processing result of the relative trajectory, and adjust the driving speed of the target vehicle according to the target conflict processing result.

[0179] In this embodiment, the above-mentioned execution entity will determine the interval speed of the target vehicle on the relative trajectory according to the solution result. Specifically:

[0180] The state transition process is connected by a quartic spline curve, and it is defined as:

[0181] ;

[0182] Among them, are the coefficients of a quartic polynomial.

[0183] make:

[0184] ,

[0185] ,

[0186] ;

[0187] have

[0188] ;

[0189] The transfer time t is:

[0190] ;

[0191] According to the minimum time step Δt of the frame, the time interval speed constraint is calculated according to the above process:

[0192] ;

[0193] At the next extreme point, the current state is updated to ,in, . Repeat the above process to get:

[0194] ;

[0195] in, is the speed of the first interval, For the speed of the second interval...

[0196] Finally, the speed of each interval is used as the target conflict processing result of the relative trajectory, and the driving speed of the target vehicle is adjusted according to the target conflict processing result to avoid possible conflict with the target obstacle.

[0197] from Figure 8 It can be seen that Figure 1 Compared with the corresponding embodiment, the conflict handling method in this embodiment, when the conflict type is uncertain conflict and the number of target obstacles is multiple, since there is no specific avoidance object, the goal of the vehicle becomes the continuous handling of obstacles that catch up with the vehicle one after another. The vehicle trajectory is re-projected with the obstacle trajectory as the reference line to obtain the relative trajectory of the vehicle, and then the start and end states are set to solve the optimal boundary value problem to obtain the interval speed value. The speed of the vehicle is adjusted according to the interval speed, so as to ensure the traffic efficiency while taking into account the lateral safety and avoid possible conflicts with the target obstacles.

[0198] Further references Figure 9, as an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a conflict handling device, which corresponds to the method embodiment shown in Figure 1 and can be specifically applied to various electronic devices.

[0199] As shown in Figure 9 , the conflict handling device 900 of this embodiment includes: an obstacle determination module 901, a conflict determination module 902, and a result determination module 903. Among them, the obstacle determination module 901 is configured to determine a target obstacle from the obstacles based on the trajectory information of the target vehicle and the trajectory information of the obstacles, where the target obstacle is an obstacle whose trajectory information conflicts with the trajectory information of the target vehicle; the conflict determination module 902 is configured to determine the conflict type between the target vehicle and the target obstacle, where the conflict type includes a deterministic conflict and an indeterministic conflict; the result determination module 903 is configured to determine a target conflict handling result according to the conflict type and the number of target obstacles, and adjust the driving speed of the target vehicle according to the target conflict handling result.

[0200] In this embodiment, in the conflict handling device 900: the specific processing of the obstacle determination module 901, the conflict determination module 902, and the result determination module 903 and the technical effects brought by them can be respectively referred to the relevant descriptions of steps 101-103 in the Figure 1 corresponding embodiment, which will not be elaborated here.

[0201] In some optional implementation manners of this embodiment, the result determination module 903 includes: an improvement sub-module, configured to, in response to determining that the conflict type is a deterministic conflict and the number of target obstacles is one, improve the yielding benefit of the target vehicle in the pre-constructed game payoff matrix according to the yielding waiting time of the target vehicle, and improve the yielding benefit of the target obstacle in the game payoff matrix according to the yielding waiting time of the target obstacle, to obtain an improved game payoff matrix; a calculation sub-module, configured to calculate a first cutting-in probability of the target vehicle and a second cutting-in probability of the target obstacle according to the improved game payoff matrix; a determination sub-module, configured to determine a first processing result according to the first cutting-in probability and the second cutting-in probability, and determine the first processing result as the target conflict handling result, where the first processing result includes cutting in or yielding.

[0202] In some optional implementation manners of this embodiment, the conflict handling device 900 further includes: a correction module, configured to determine a right-of-way correction amount according to the right-of-way information of the target vehicle relative to the target obstacle; correct the first cutting-in probability according to the right-of-way correction amount to obtain a corrected first cutting-in probability; and the determination sub-module is further configured to: determine a first processing result according to the corrected first cutting-in probability and the second cutting-in probability.

[0203] In some alternative implementation manners of this embodiment, the result determination module 903 is further configured to: in response to determining that the conflict type is a deterministic conflict and the number of target obstacles is multiple, perform rough clustering on the multiple target obstacles according to the lateral distances between the multiple target obstacles and the road boundary to obtain multiple obstacle queues after clustering; for the multiple obstacle queues, divide the obstacle queue into a queue of cutting-in obstacles set or a queue of yielding obstacles set according to the first processing result between the target vehicle and the leading obstacle in the obstacle queue; perform combined optimization solution on the queue of cutting-in obstacles set and the queue of yielding obstacles set, determine a second processing result according to the solution result, and determine the second processing result as the target conflict processing result.

[0204] In some alternative implementation manners of this embodiment, the result determination module 903 is further configured to: in response to determining that the conflict type is an uncertain conflict and the number of target obstacles is one, determine the yielding waiting time of the target vehicle according to the lateral distance between the target obstacle and the target vehicle; determine a speed control amount for controlling the driving speed of the target vehicle according to the yielding waiting time, and use the speed control amount as the target conflict processing result.

[0205] In some alternative implementation manners of this embodiment, the result determination module 903 includes: a generation sub-module configured to, in response to determining that the conflict type is an uncertain conflict and the number of target obstacles is multiple, generate an obstacle trajectory set according to the trajectory information of the multiple target obstacles; a solution sub-module configured to solve an optimal boundary value according to the starting state and the ending state of the relative trajectory of the target vehicle, where the relative trajectory is the relative trajectory between the trajectory information of the target vehicle and the obstacle trajectories in the obstacle trajectory set; a result determination sub-module configured to determine the interval speed of the target vehicle on the relative trajectory according to the solution result, and use the interval speed as the target conflict processing result of the relative trajectory.

[0206] In some alternative implementation manners of this embodiment, the result determination sub-module is further configured to: traverse the obstacle trajectory set, respectively use the current obstacle trajectory as a reference line, project the trajectory information of the target vehicle, and obtain multiple projected relative trajectories of the target vehicle; for each projected relative trajectory of the target vehicle, determine the starting state and the ending state of the relative trajectory, and solve the optimal boundary value according to the starting state and the ending state.

[0207] According to an embodiment of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium, a computer program product, and an autonomous vehicle.

[0208] Figure 10FIG. shows a schematic block diagram of an exemplary electronic device 1000 that can be used to implement embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely exemplary and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0209] As Figure 10 shown, the device 1000 includes a computing unit 1001 that can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1002 or a computer program loaded from a storage unit 1008 into a random access memory (RAM) 1003. In the RAM 1003, various programs and data required for the operation of the device 1000 can also be stored. The computing unit 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0210] Multiple components in the device 1000 are connected to the I / O interface 1005, including: an input unit 1006, such as a keyboard, a mouse, etc.; an output unit 1007, such as various types of displays, speakers, etc.; a storage unit 1008, such as a magnetic disk, an optical disk, etc.; and a communication unit 1009, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1009 allows the device 1000 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0211] The computing unit 1001 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1001 executes the various methods and processes described above, such as the conflict handling method. For example, in some embodiments, the conflict handling method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 1008. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 1000 via the ROM 1002 and / or the communication unit 1009. When the computer program is loaded into the RAM 1003 and executed by the computing unit 1001, one or more steps of the conflict handling method described above can be executed. Alternatively, in other embodiments, the computing unit 1001 can be configured to execute the conflict handling method by any other suitable means (e.g., by means of firmware).

[0212] The autonomous vehicle provided by the present disclosure may include the above-mentioned electronic device as shown in Figure 10 which can implement the conflict handling method described in any of the above embodiments when executed by its processor.

[0213] The various embodiments of the systems and technologies described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general-purpose programmable processor that receives data and instructions from a storage system, at least one input device, and at least one output device, and transmits the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0214] The program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, a special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine, or entirely on the remote machine or server.

[0215] In the context of the present disclosure, a machine-readable medium may be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0216] In order to provide interaction with a user, the systems and techniques described herein may be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0217] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected with each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), and the Internet.

[0218] A computer system can include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The client-server relationship is generated by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

[0219] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this is not limited herein.

[0220] The above specific embodiments do not constitute a limitation on the protection scope of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the protection scope of this disclosure.

Claims

1. A conflict handling method, comprising: Based on the trajectory information of the target vehicle and the trajectory information of the obstacle, determining a target obstacle from the obstacles, wherein the target obstacle is an obstacle whose trajectory information conflicts with the trajectory information of the target vehicle; Determining a conflict type between the target vehicle and the target obstacle, wherein the conflict type includes a deterministic conflict and an uncertain conflict; Determining a target conflict processing result according to the conflict type and the number of the target obstacles, and adjusting the driving speed of the target vehicle according to the target conflict processing result; Wherein, determining the target conflict processing result according to the conflict type and the number of the target obstacles includes: In response to determining that the conflict type is the deterministic conflict and the number of the target obstacle is one, improving the yielding benefit of the target vehicle in a pre-constructed game payoff matrix according to the yielding waiting time of the target vehicle, and improving the yielding benefit of the target obstacle in the game payoff matrix according to the yielding waiting time of the target obstacle, to obtain an improved game payoff matrix; The target conflict processing result is determined according to the improved game payoff matrix.

2. The method according to claim 1, wherein: Determining the target conflict processing result according to the improved game payoff matrix includes: Calculate a first overtaking probability of the target vehicle and a second overtaking probability of the target obstacle according to the improved game payoff matrix; A first processing result is determined according to the first overtaking probability and the second overtaking probability, and the first processing result is determined as the target conflict processing result, wherein the first processing result includes overtaking or giving way.

3. The method according to claim 2, wherein: Also includes: Determining a right-of-way correction amount according to the right-of-way information of the target vehicle relative to the target obstacle; Correcting the first overtaking probability according to the road right correction amount to obtain a corrected first overtaking probability; as well as The determining the first processing result according to the first preemption probability and the second preemption probability includes: The first processing result is determined according to the corrected first rush-to-go probability and the second rush-to-go probability.

4. The method according to claim 2 or 3, wherein: The determining of the target conflict processing result according to the conflict type and the number of the target obstacles further includes: In response to determining that the conflict type is the deterministic conflict and the number of the target obstacles is multiple, coarsely clustering the multiple target obstacles according to lateral distances between the multiple target obstacles and the road boundary to obtain multiple clustered obstacle queues; For the plurality of obstacle queues, according to a first processing result between the target vehicle and the head obstacle of the obstacle queue, the obstacle queue is divided into a set of grabbing obstacle queues or a set of yielding obstacle queues; A combined optimization solution is performed on the set of rushing obstacle queues and the set of yielding obstacle queues, a second processing result is determined according to the solution result, and the second processing result is determined as the target conflict processing result.

5. The method according to claim 1, wherein: The determining the target conflict processing result according to the conflict type and the number of the target obstacles includes: In response to determining that the conflict type is the uncertain conflict and the number of the target obstacle is one, determining a yield waiting time for the target vehicle according to a lateral distance between the target obstacle and the target vehicle; A speed control amount for controlling the travel speed of the target vehicle is determined according to the yield waiting time, and the speed control amount is used as the target conflict processing result.

6. The method according to claim 1, wherein: The determining the target conflict processing result according to the conflict type and the number of the target obstacles includes: In response to determining that the conflict type is the uncertain conflict and the number of the target obstacles is multiple, generating an obstacle trajectory set according to trajectory information of the multiple target obstacles; Solving the optimal boundary value according to the starting state and the ending state of the relative trajectory of the target vehicle, wherein the relative trajectory is the relative trajectory between the trajectory information of the target vehicle and the obstacle trajectory in the obstacle trajectory set; The interval speed of the target vehicle in the relative trajectory is determined according to the solution result, and the interval speed is used as the target conflict processing result of the relative trajectory.

7. The method according to claim 6, wherein: The step of solving the optimal boundary value according to the starting state and the ending state of the relative trajectory of the target vehicle includes: Traversing the obstacle trajectory set, taking the current obstacle trajectory as a reference line, respectively, projecting the trajectory information of the target vehicle, and obtaining a relative trajectory of the target vehicle after multiple projections; For each relative track of the target vehicle after projection, a starting state and an end state of the relative track are determined, and an optimal boundary value is solved according to the starting state and the end state.

8. A conflict handling device, comprising: An obstacle determination module is configured to determine a target obstacle from the obstacles based on the trajectory information of the target vehicle and the trajectory information of the obstacle, wherein the target obstacle is an obstacle whose trajectory information conflicts with the trajectory information of the target vehicle; A conflict determination module, configured to determine a conflict type between the target vehicle and the target obstacle, wherein the conflict type includes a deterministic conflict and an uncertain conflict; a result determination module, configured to determine a target conflict processing result according to the conflict type and the number of the target obstacles, and adjust the driving speed of the target vehicle according to the target conflict processing result; Wherein, the result determination module is further configured to: In response to determining that the conflict type is the deterministic conflict and the number of the target obstacle is one, improving the yielding benefit of the target vehicle in a pre-constructed game payoff matrix according to the yielding waiting time of the target vehicle, and improving the yielding benefit of the target obstacle in the game payoff matrix according to the yielding waiting time of the target obstacle, to obtain an improved game payoff matrix; The target conflict processing result is determined according to the improved game payoff matrix.

9. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 7.

11. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 7.

12. An autonomous driving vehicle comprising the electronic device as claimed in claim 9.

Images