Vehicle control method, device, equipment, medium and product

Abstract

The embodiment of the invention provides a vehicle control method and device, equipment, a medium and a product. The method comprises the steps of obtaining traffic environment information of game participants; determining first decision information of the first vehicle, second decision information of the second vehicle and a game result of each game strategy in K * L game strategies based on the traffic environment information of the game participants; based on the traffic environment information, the first decision information and the second decision information of the game participants and the game result of each game strategy in the K * L game strategies, constructing an expected utility function corresponding to the first vehicle; and controlling the first vehicle to execute the target behavior. According to the embodiment of the invention, the reliability of vehicle decision making is improved.

Description

Technical Field

[0001] The present application belongs to the field of vehicle control technology, and in particular, relates to a vehicle control method, device, equipment, medium and product. Background Art

[0002] In the prior art, the lane change assistance system in the vehicle detects the vehicles around the vehicle and the lane lines printed on the surface of the road ahead and other related information through sensors arranged around the vehicle, and then determines whether the vehicle is allowed to perform the lane change action. If the lane change assistance system allows the vehicle to perform the lane change action and receives the driver's command input (turn signal lever signal), it can control the vehicle to change lanes into the corresponding lane and continue driving. In other words, the lane change assistance system can only perform the lane change action after receiving the driver's command input. During the process of the vehicle performing the lane change action, if there are traffic anomalies, environmental changes, driver intervention, etc., the lane change may not be completed. The system will choose to return to the original lane according to the current lane change situation, or remind the driver to take over. This may lead to low reliability of the vehicle's lane change decision. Summary of the invention

[0003] The embodiments of the present application provide a vehicle control method, device, equipment, medium and product, which improve the reliability of vehicle lane changing decisions.

[0004] In a first aspect, an embodiment of the present application provides a vehicle control method, the method comprising:

[0005] Acquiring traffic environment information of game participants, where the game participants include a first vehicle and a second vehicle, the first vehicle travels in a first lane, and the second vehicle travels in a second lane;

[0006] Based on the traffic environment information of the game participants, determine the first decision information of the first vehicle, the second decision information of the second vehicle, and the game result of each game strategy in K×L game strategies, the first decision information includes K first potential behaviors, and the second decision information includes L second potential behaviors;

[0007] Based on the traffic environment information of the game participants, the first decision information, the second decision information, and the game results of each game strategy in the K×L game strategies, an expected utility function corresponding to the first vehicle is constructed;

[0008] Control the first vehicle to perform a target behavior, the target behavior is based on expected utility values ​​corresponding to K first potential behaviors, the behavior is determined from the K first potential behaviors, the expected utility values ​​corresponding to the K first potential behaviors are obtained based on the expected utility function corresponding to the first vehicle, and the expected utility value of each first potential behavior is used to evaluate the feasibility of the first vehicle performing the first potential behavior, the target behavior includes a first target behavior characterizing that the first vehicle is traveling in a first lane, or a second target behavior characterizing that the first vehicle is traveling in a second lane.

[0009] In an optional implementation of the first aspect, obtaining traffic environment information of game participants includes:

[0010] receiving a first instruction, where the first instruction is triggered when sensor information acquired by a sensor of the first vehicle meets a preset lane-changing condition, and the first instruction is used to instruct the first vehicle to perform a lane-changing action, where the lane-changing action is an action that enables the first vehicle to switch from a currently traveling first lane to a second lane;

[0011] In response to the first instruction, traffic environment information of the game participants is obtained.

[0012] In an optional implementation of the first aspect, based on traffic environment information of game participants, first decision information, second decision information, and a game result of each game strategy in K×L game strategies, an expected utility function corresponding to the first vehicle is constructed, including:

[0013] Constructing a utility function of the first vehicle based on the first decision information of the first vehicle and the game result of each game strategy in the K×L game strategies;

[0014] Based on the first decision information of the first vehicle, the second decision information of the second vehicle and the traffic environment information of the game participants, a first probability distribution function is constructed, where the first probability distribution function is used to characterize the probability distribution of the game result of each game strategy in the K×L game strategies;

[0015] Based on the first decision information of the first vehicle and the possible decision behavior of the second vehicle, construct a second probability distribution function, where the second probability distribution function is used to characterize the probability distribution of a second potential behavior of the second vehicle, where the possible decision behavior of the second vehicle is any one of the L second potential behaviors;

[0016] Based on the traffic environment information of the game participants, a third probability distribution function is constructed, where the third probability distribution function is used to characterize the probability distribution of possible decision-making behaviors of the second vehicle;

[0017] Based on the possible decision behavior of the first vehicle, construct a fourth probability distribution function, the fourth probability distribution function is used to characterize the probability distribution of the traffic environment information of the game participants, and the possible decision behavior of the first vehicle is any one of the K first potential behaviors;

[0018] Based on the utility function of the first vehicle, the first probability distribution function, the second probability distribution function, the third probability distribution function and the fourth probability distribution function, an expected utility function corresponding to the first vehicle is constructed.

[0019] In an optional implementation of the first aspect, the expected utility function corresponding to the first vehicle satisfies the following formula:

[0020] E A [u A (a,s)|y A ]=∫ Θ ∫ yM ∫ M ∫ S u s (a,s)dP A (s|m,a,θ)dP A (m|a,y M )dP A (y M |θ)dP A (θ|y A )

[0021] Among them, u s (a,s) is the utility function of the first vehicle, P A (s|m,a,θ) is the first probability distribution function, P A (m|a,y M ) is the second probability distribution function, P A (y M |θ) is the third probability distribution function, P A (θ|y A ) is a fourth probability distribution function;

[0022] a is the first decision information of the first vehicle, s includes the game results of each game strategy in K×L game strategies, m is the second decision information of the second vehicle, θ is the traffic environment information of the game participants, y M is the possible decision behavior of the second vehicle, y A is the possible decision behavior of the first vehicle.

[0023] In an optional implementation of the first aspect, constructing a second probability distribution function based on the first decision information of the first vehicle and the possible decision behavior of the second vehicle includes:

[0024] Obtaining a target utility function corresponding to the second vehicle, where the target utility function corresponding to the second vehicle is determined based on a simulation random utility equation, a first random utility distribution function, and a second random utility distribution function;

[0025] For each possible decision behavior of the second vehicle, based on the first decision information of the first vehicle and the second decision information of the second vehicle, a plurality of groups of random values ​​corresponding to the possible decision behavior of the second vehicle are obtained, each group of random values ​​including a first random value corresponding to the simulation random utility simulation, a second random value corresponding to the first random utility distribution function, and a third random value corresponding to the second random utility distribution function;

[0026] For each group of random values ​​in the multiple groups of random values, solving the target utility function corresponding to the second vehicle based on each group of random values, obtaining an optimal solution for each group of random values, and obtaining multiple optimal solutions;

[0027] A second probability distribution function is obtained based on simulation of multiple optimal solutions.

[0028] In an optional implementation of the first aspect, the expected utility function corresponding to the second vehicle satisfies the following formula:

[0029]

[0030] Among them, U M (m,s) is the simulation random utility equation, Π M (s|m,a,θ) is the first random utility distribution function, Π M (θ|y M ) is the second random utility distribution function;

[0031] a is the first decision information of the first vehicle, s includes the game results of each game strategy in K×L game strategies, m is the second decision information of the second vehicle, θ is the traffic environment information of the game participants, y M is the possible decision behavior of the second vehicle, y A is the possible decision behavior of the first vehicle.

[0032] In a second aspect, an embodiment of the present application provides a vehicle control device, the device comprising:

[0033] An acquisition module, used for acquiring traffic environment information of game participants, the game participants including a first vehicle and a second vehicle, the first vehicle traveling in a first lane, and the second vehicle traveling in a second lane;

[0034] A determination module, used to determine first decision information of a first vehicle, second decision information of a second vehicle, and a game result of each of K×L game strategies based on traffic environment information of game participants, wherein the first decision information includes K first potential behaviors, and the second decision information includes L second potential behaviors;

[0035] A construction module, used to construct an expected utility function corresponding to the first vehicle based on traffic environment information of the game participants, the first decision information, the second decision information, and the game result of each game strategy in the K×L game strategies;

[0036] A control module is used to control the first vehicle to perform a target behavior, the target behavior is based on expected utility values ​​corresponding to K first potential behaviors, the behavior is determined from the K first potential behaviors, the expected utility values ​​corresponding to the K first potential behaviors are obtained based on the expected utility function corresponding to the first vehicle, the expected utility value of each first potential behavior is used to evaluate the feasibility of the first vehicle performing the first potential behavior, the target behavior includes a first target behavior that characterizes the first vehicle traveling in a first lane, or a second target behavior that characterizes the first vehicle traveling in a second lane.

[0037] In a third aspect, an electronic device is provided, comprising: a memory for storing computer program instructions; and a processor for reading and running the computer program instructions stored in the memory to execute the vehicle control method provided in any optional embodiment of the first aspect.

[0038] In a fourth aspect, a computer storage medium is provided, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the vehicle control method provided by any optional implementation in the first aspect is implemented.

[0039] In a fifth aspect, a computer program product is provided, the computer program product comprising a computer program, and when the computer program is executed by a processor, the vehicle control method provided by any optional implementation in the first aspect is implemented.

[0040] In an embodiment of the present application, traffic environment information of game participants can be obtained, and the game participants include a first vehicle and a second vehicle, and the first vehicle is traveling in a first lane, and the second vehicle is traveling in a second lane. Based on this, first decision information of the first vehicle, second decision information of the second vehicle, and game results of each of K×L game strategies can be determined based on the traffic environment information of the game participants. Then, based on the traffic environment information of the game participants, the first decision information, the second decision information, and the game results of each of the K×L game strategies, an expected utility function corresponding to the first vehicle can be constructed. In this way, the expected utility function corresponding to the first vehicle can be solved to obtain expected utility values ​​corresponding to K first potential behaviors, respectively, so that the first vehicle can be controlled to perform a target behavior with a higher expected utility value subsequently. The target behavior may include a first target action representing that the first vehicle is traveling in the first lane, or a second target behavior representing that the first vehicle is traveling in the second lane. In this way, the potential risks and uncertainties in the vehicle's driving process can be taken into account, that is, the changes in opponent's behavior can be taken into account, and the lane change decision can be adjusted in time based on real-time environmental information and opponent's behavior, thereby improving the robustness and reliability of the vehicle's lane change decision, thereby ensuring the safety of vehicle driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0042] Figure 1 It is one of the flow charts in a related technology provided in an embodiment of the present application;

[0043] Figure 2 This is the second flow chart of a related technology provided in an embodiment of the present application;

[0044] Figure 3 This is a schematic diagram of the architecture of a lane change assistance system provided in an embodiment of the present application.

[0045] Figure 4 It is one of the flow charts of a vehicle control method provided in an embodiment of the present application;

[0046] Figure 5 This is a second flow chart of a vehicle control method provided in an embodiment of the present application;

[0047] Figure 6 This is a third flow chart of a vehicle control method provided in an embodiment of the present application;

[0048] Figure 7This is a fourth flow chart of a vehicle control method provided in an embodiment of the present application;

[0049] Figure 8 This is one of the scenario schematic diagrams of a vehicle control method provided in an embodiment of the present application;

[0050] Fig. 9 (a) is a second schematic diagram of a scenario of a vehicle control method provided in an embodiment of the present application;

[0051] Fig. 9 (b) is a third scenario schematic diagram of a vehicle control method provided in an embodiment of the present application;

[0052] Fig.10 This is a fourth scenario schematic diagram of a vehicle control method provided in an embodiment of the present application;

[0053] Fig.11 is a structural schematic diagram of a vehicle control device provided in an embodiment of the present application;

[0054] Fig.12 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0056] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0057] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0058] In the prior art, when a vehicle is driving, if the driving conditions in the original lane are poor and a lane change action is required, the following can be done: Figure 1 As shown, the lane changing process in the prior art may specifically include the following steps:

[0059] S101, receiving an input for instructing a vehicle to perform a lane change action.

[0060] S102, collecting environmental information.

[0061] Specifically, after receiving the input of the vehicle performing a lane change action, the lane change assistance system can use the Advanced Driving Assistance System (ADAS) to collect environmental information around the vehicle.

[0062] S103, judging whether the vehicle meets the lane change condition based on the environmental information. If yes, execute S104, if no, execute S107.

[0063] S104, decide whether to execute the vehicle lane change action. If yes, execute S105, if no, execute S107.

[0064] S105, executing the vehicle lane changing action.

[0065] S106, controlling the vehicle to change lanes.

[0066] S107, controlling the vehicle to continue driving in the original lane.

[0067] Based on the above Figure 1 The lane changing process shown, for the above S104, if the vehicle's autonomous driving level is L2, that is, the vehicle is a semi-autonomous driving vehicle, the driver needs to manually input commands to control the vehicle to perform or not perform the lane changing action.

[0068] If the vehicle's autonomous driving level is L3, that is, the vehicle is a conditionally autonomous vehicle, since its lane change decision is not controlled by humans, the lane change assistance system can directly execute the lane change action after determining that the vehicle meets the lane change conditions. In other words, it lacks the decision-making action on whether the vehicle executes the lane change. If the basic game theory method is used, the information of the autonomous driving vehicle and the adjacent road vehicles must be exchanged (common knowledge) to meet the game theory conditions. In this case, the vehicle must have a vehicle-to-vehicle communication (V2V) function to achieve this. However, V2V is not currently applicable to most vehicles, so there are also great limitations.

[0069] In addition, if the vehicle encounters traffic anomalies, environmental changes, driver intervention, etc. during the lane change process, the vehicle may not be able to complete the lane change. The lane change assistance system will choose to return to the original lane or remind the driver to take over and exit according to the current lane change situation. This may result in low reliability of the vehicle's lane change decision.

[0070] In order to more accurately describe the overall process of a vehicle performing a lane change action in the prior art, the overall process of a vehicle performing a lane change action in the related art can be described as follows: Figure 2As shown, OFF is used to indicate that the lane change assist system is in the off state, that is, the lane change assist system cannot perform lane changing actions; Inhibited: is used to indicate that the lane change assist system is in the inhibited state, that is, there are inhibition conditions for the lane change assist system, and the lane change assist system cannot perform lane changing actions normally; Enable: is used to indicate that the lane change assist system is in a pending condition to meet the enabling condition. If the lane change assist system does not have an inhibition condition and has not received a lane change instruction, the lane change system needs to maintain this state. Here, the lane change assist system still cannot perform lane changing actions normally. It should also be noted that the above enabling conditions and the above inhibition conditions can be determined according to the actual situation of the vehicle, and no specific restrictions are made here. Wait: is used to indicate that the lane change assist system is in a waiting state. Here, the lane change assist system can wait for a preset time length to meet the preset lane change advance operation time, wherein the above preset time length can be preset according to actual conditions or experience. For example, the preset time can be 3 seconds, which is not specifically limited here. It should be noted that when the lane change assist system is in the waiting state, it can control the vehicle to drive in the center, but the prerequisite must be met. The prerequisite is that there are no other conditions except that the turn signal lever is turned. Lane Changing: It is used to indicate that the lane change assist system is in the lane change working state, that is, the lane change assist system is performing the lane change action. At this time, its longitudinal control is still in the active state, and the lateral centering control is temporarily suppressed. Lane Changed: It is used to indicate that the lane change assist system has successfully completed the lane change action. At this time, the vehicle can drive to the center line of the target lane, and the lane change assist system will automatically jump from the current state to the suppressed state. Cancel: It is used to indicate that the lane change action is canceled, that is, the lane change assist system does not need to continue to perform the lane change action. In this way, the lane change assist system can warn the driver through the human-computer interaction interface to take over the vehicle immediately. At this time, the lane change assist system will automatically jump from the current state to the suppressed state. Retreated: It is used to indicate that the lane change action is canceled, that is, the lane change assist system does not need to continue to perform the lane change action. In this way, the vehicle can exit the center line of the original lane, and the lane change assist system will automatically jump from the current state to the inhibited state. Failure: It is used to indicate that when a system failure, steering lever failure, or turn signal failure occurs, the lane change assist system will automatically jump from the current state to the lane change failure state (Failure).

[0071] So, based on Figure 2 From the content shown, we can see that the Enable State of Standby means that the conditions for lane change are met, but the lane change assistance system has not received the decision / instruction to change lanes. Then the 5 in the figure from the Enabled state to the Wait state is the decision-making process of the decision-making unit; in autonomous driving below L2, it is the driver's manual operation; above L3, the vehicle needs to make its own judgment and control.

[0072] In order to accurately describe the overall process of a vehicle performing a lane change action in the related art, it is necessary to first explain that FIG. 1 can accurately describe the overall process of a vehicle performing a lane change action in the prior art, which can be specifically described as follows: Figure 2 As shown, when the lane change assistance system in the vehicle is in the off state (that is, the lane change assistance system in the vehicle is currently unable to perform a lane change action), if the lane change assistance system receives a switch signal from a switch module, such as an automated-driving control unit (ACU), sent through a bus, the lane change assistance system can switch the current state from the off state to the on state, and can feedback the current state of the lane change assistance system to the ACU through the bus.

[0073] Based on this, in order to solve the above-mentioned problems in the prior art, the embodiments of the present application provide a vehicle control method, device, equipment, medium and product, which can obtain traffic environment information of game participants, and the game participants include a first vehicle and a second vehicle, and the first vehicle is traveling in a first lane, and the second vehicle is traveling in a second lane. Based on this, the first decision information of the first vehicle, the second decision information of the second vehicle and the game results of each game strategy in K×L game strategies can be determined based on the traffic environment information of the game participants, and then the expected utility function corresponding to the first vehicle can be constructed based on the traffic environment information of the game participants, the first decision information, the second decision information and the game results of each game strategy in K×L game strategies. In this way, the expected utility function corresponding to the first vehicle can be solved to obtain the expected utility values ​​corresponding to the K first potential behaviors, respectively, so that the first vehicle can be controlled to perform a target behavior with a higher expected utility value subsequently. The target behavior may include a first target action representing that the first vehicle is traveling in the first lane, or a second target behavior representing that the first vehicle is traveling in the second lane. In this way, the potential risks and uncertainties in the vehicle's driving process can be taken into account, that is, the changes in opponent's behavior can be taken into account, and the lane change decision can be adjusted in time based on real-time environmental information and opponent's behavior, thereby improving the robustness and reliability of the vehicle's lane change decision, thereby ensuring the safety of vehicle driving.

[0074] The vehicle control method provided in the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0075] Figure 3 It is an architecture diagram of a lane change assistance system provided in an embodiment of the present application.

[0076] like Figure 3As shown, the lane change assist system includes a condition judgment module, a mode management module and a vehicle control module. The condition judgment module is respectively connected to the visual system-level chip, the sensor, and the mode management module, the mode management module is respectively connected to the vehicle control module, the human-computer interaction interface, and the turn signal control device, and the vehicle control module is connected to the electric power steering device.

[0077] based on Figure 3 As shown in the architecture diagram, the system functional components of the lane change assist system (i.e., the above-mentioned condition judgment module, mode management module, and vehicle control module) can determine whether the vehicle meets the lane change conditions through the relevant information detected by the visual system-level chip and the sensor, and input it to the mode management module for management decision-making to determine the current vehicle mode. At the same time, the mode management module outputs it to the human-computer interaction interface and the turn signal controller. If the vehicle needs to change lanes or cancel the lane change, it needs to be input to the vehicle control module to determine whether electric power steering is needed.

[0078] It should be noted that the relevant information detected by the above-mentioned visual system-level chip and sensors may include the distance between the vehicle and surrounding vehicles or other objects. Accordingly, the above-mentioned lane change condition can set a safety distance threshold and determine whether the distance between the vehicle and surrounding vehicles or other objects is greater than the safety distance threshold. The safety distance threshold can also be set to the front safety distance threshold, the rear safety distance threshold, and the left and right safety distance thresholds according to actual conditions, and no specific limitation is made here.

[0079] Based on this, based on the above Figure 3 The architecture diagram of the lane change assist system shown in the figure is combined with the following drawings to introduce in detail the vehicle control method provided in the embodiment of the present application.

[0080] like Figure 4 As shown, the execution subject of the vehicle control method may be a lane change assist system, which may be a lane change assist (Lane Change Assist, LCA) system and an indicated lane change (Indicated Lane Change, ILC) system and other systems for controlling vehicle lane change, which are not specifically limited here. Based on this, the vehicle control method may specifically include the following steps:

[0081] S410, obtaining traffic environment information of game participants.

[0082] In some embodiments, the game participants may include a first vehicle and a second vehicle, wherein the first vehicle may travel in a first lane, and the second vehicle may travel in a second lane. It should be noted that the first lane and the second lane may be different lanes, which is not specifically limited herein.

[0083] Correspondingly, the traffic environment information of the above-mentioned game participants may include first environment information collected by various sensors of the first vehicle, and second environment information collected by various sensors of the above-mentioned second vehicle.

[0084] S420, determining first decision information of the first vehicle, second decision information of the second vehicle, and a game result of each of the K×L game strategies based on traffic environment information of the game participants.

[0085] Among them, the first decision information of the above-mentioned first vehicle may include relevant decision information that can be executed by the first vehicle, and the first decision information may include K first potential behaviors. Exemplarily, the K first potential behaviors may include lane changing behaviors and no lane changing behaviors. In addition, the K first potential behaviors may include other decision behaviors that can be executed by the first vehicle, which are not specifically limited here.

[0086] Similarly, the second decision information of the second vehicle may include relevant decision information that the second vehicle can perform, and the second decision information may include L second potential behaviors, and the L second potential behaviors may include yielding behavior and not yielding behavior. In addition, the L second potential behaviors may also include other decision behaviors that the second vehicle can perform, which are not specifically limited here. Wherein, K and L are both positive integers, and the embodiments of the present application do not specifically limit the values ​​of K and L.

[0087] Specifically, the lane change assistance system can determine the first decision information of the first vehicle and the second decision information of the second vehicle based on the traffic environment information of the game participants after obtaining the traffic environment information of the game participants. Since the first decision information can include K first potential behaviors and the second decision information can include L second potential behaviors, the lane change assistance system can also determine the game results of each of the K×L game strategies based on the first decision information and the second decision information after obtaining the first decision information and the second decision information based on the traffic environment information of the game participants.

[0088] S430, constructing an expected utility function corresponding to the first vehicle based on the traffic environment information of the game participants, the first decision information, the second decision information, and the game result of each game strategy in the K×L game strategies.

[0089] Specifically, after determining the first decision information of the first vehicle, the second decision information of the second vehicle and the results of each game strategy in K×L game strategies, the lane change assistance system can construct the expected utility function corresponding to the first vehicle based on the traffic environment information of the game participants, the first decision information, the second decision information and the game results of each game strategy in K×L game strategies.

[0090] S440, controlling the first vehicle to execute a target behavior.

[0091] In some embodiments, the target behavior involved above can be a behavior determined from the K first potential behaviors based on the expected utility values ​​corresponding to the K first potential behaviors. The expected utility values ​​corresponding to the K first potential behaviors can be obtained by solving the expected utility function corresponding to the first vehicle, and the expected utility value of each first potential behavior is used to evaluate the feasibility of the first vehicle executing the first potential behavior.

[0092] In addition, the target behavior may include a first target behavior that indicates that the first vehicle is traveling in the first lane, that is, indicating that the first vehicle does not perform a lane change action, or a second target behavior that indicates that the first vehicle is traveling in the second lane, that is, indicating that the second vehicle performs a lane change action. It should be noted that the first target behavior may include multiple behaviors that enable the first vehicle to travel in the first lane, and similarly, the second target behavior may include multiple behaviors that enable the first vehicle to travel in the yield lane.

[0093] Specifically, after constructing the expected utility function corresponding to a vehicle, the lane change assistance system can solve the expected utility function corresponding to the first vehicle to obtain the expected utility value corresponding to each of the K first potential behaviors, and then determine the target behavior from the K first potential behaviors based on the expected utility value corresponding to each of the K first potential behaviors, and then control the first vehicle to perform the target behavior.

[0094] In order to more accurately determine the target behavior, in one embodiment, before controlling the first vehicle to perform the target behavior, the vehicle control method may further include the following steps:

[0095] Based on the expected utility values ​​respectively corresponding to the K first potential behaviors, the first potential behavior with the largest expected utility value is determined as the target behavior.

[0096] Specifically, since the expected utility value of each first potential behavior is used to evaluate the feasibility of the first vehicle executing the first potential behavior, the lane change assistance system can solve the expected utility function corresponding to the first vehicle to obtain the expected utility value corresponding to each of the K first potential behaviors. Then, based on the expected utility values ​​corresponding to the K first potential behaviors, the first potential behavior with the largest expected utility value can be determined as the target behavior from the K first potential behaviors.

[0097] In this embodiment, before controlling the first vehicle to perform the target behavior, the first potential behavior with the largest expected utility value can be determined as the target behavior based on the expected utility values ​​corresponding to the K first potential behaviors. In this way, the target behavior can be accurately determined, thereby improving the reliability of the vehicle's decision-making behavior.

[0098] In an embodiment of the present application, traffic environment information of game participants can be obtained, and the game participants include a first vehicle and a second vehicle, and the first vehicle is traveling in a first lane, and the second vehicle is traveling in a second lane. Based on this, first decision information of the first vehicle, second decision information of the second vehicle, and game results of each of K×L game strategies can be determined based on the traffic environment information of the game participants. Then, based on the traffic environment information of the game participants, the first decision information, the second decision information, and the game results of each of the K×L game strategies, an expected utility function corresponding to the first vehicle can be constructed. In this way, the expected utility function corresponding to the first vehicle can be solved to obtain expected utility values ​​corresponding to K first potential behaviors, respectively, so that the first vehicle can be controlled to perform a target behavior with a higher expected utility value subsequently. The target behavior may include a first target action representing that the first vehicle is traveling in the first lane, or a second target behavior representing that the first vehicle is traveling in the second lane. In this way, the potential risks and uncertainties in the vehicle's driving process can be taken into account, that is, the changes in opponent's behavior can be taken into account, and the lane change decision can be adjusted in time based on real-time environmental information and opponent's behavior, thereby improving the robustness and reliability of the vehicle's lane change decision, thereby ensuring the safety of vehicle driving.

[0099] In order to more accurately describe the vehicle control method provided by the embodiment of the present application, in one embodiment, as Figure 5 As shown, the above-mentioned S410 may specifically include the following steps:

[0100] S510, receiving a first instruction.

[0101] In some embodiments, the first instruction is used to instruct the first vehicle to perform a lane changing action, where the lane changing action is an action that enables the first vehicle to switch from a currently traveling first lane to a second lane.

[0102] The first instruction is used to instruct the first vehicle to perform a lane-changing action. The lane-changing action may be an action that enables the first vehicle to switch from a currently traveling first lane to a second lane.

[0103] It should also be noted that the above-mentioned first instruction may be an instruction generated in response to the driver's input to a control for instructing the vehicle to change lanes. The control may be a physical control or a virtual control, which is not specifically limited here.

[0104] In addition, the first instruction may also be sent by a target system to a lane change assistance system, and the target system may be a related system that can be used to instruct the vehicle to perform a lane change action. For example, the target system may be a navigation system, or the target system may be a related system that can detect congestion, control, or other scenarios that are not suitable for vehicle traffic ahead of the vehicle's current lane, which is not specifically limited here.

[0105] S520: In response to the first instruction, obtain traffic environment information of the game participants.

[0106] Specifically, the lane change assistance system can receive a first instruction. Since the first instruction is used to instruct the first vehicle to perform a lane change action, the lane change action is an action that enables the first vehicle to switch from the first lane it is currently traveling in to the second lane. In this way, the lane change assistance system can respond to the first instruction and obtain the traffic environment information of the game participants.

[0107] In this embodiment, by receiving a first instruction for instructing a first vehicle to perform a lane change action and responding to the first instruction, traffic environment information of the game participants can be obtained, thereby facilitating subsequent consideration of changes in the surrounding environment and opponent behavior, accurately determining the target behavior, and improving the reliability of the vehicle's lane change decision.

[0108] In order to more accurately describe the vehicle control method provided by the embodiment of the present application, in one embodiment, Figure 6 As shown, the above-mentioned S430 may specifically include the following steps:

[0109] S610 , constructing a utility function of the first vehicle based on the first decision information of the first vehicle and the game result of each game strategy in the K×L game strategies.

[0110] S620: construct a first probability distribution function based on the first decision information of the first vehicle, the second decision information of the second vehicle, and the traffic environment information of the game participants.

[0111] Among them, the above-mentioned first probability distribution function can be used to characterize the probability distribution of the game results of each game strategy in K×L game strategies.

[0112] S630: construct a second probability distribution function based on the first decision information of the first vehicle and the possible decision behavior of the second vehicle.

[0113] The second probability distribution function mentioned above can be used to characterize the probability distribution of the second potential behavior of the second vehicle. In addition, the possible decision behavior of the second vehicle can be any one of the L second potential behaviors mentioned above.

[0114] S640: construct a third probability distribution function for characterizing the distribution of possible decision behaviors of the second vehicle based on the traffic environment information of the game participants.

[0115] The third probability distribution function may be used to characterize the probability distribution of possible decision-making behaviors of the second vehicle.

[0116] S650: construct a fourth probability distribution function based on the possible decision behavior of the first vehicle.

[0117] In some embodiments, the fourth probability distribution function is used to characterize the probability distribution of traffic environment information of game participants, and in addition, any one of the K first potential behaviors of the possible decision-making behavior of the first vehicle.

[0118] S660, constructing an expected utility function corresponding to the first vehicle based on the utility function of the first vehicle, the first probability distribution function, the second probability distribution function, the third probability distribution function and the fourth probability distribution function.

[0119] Specifically, the lane change assistance system can construct a utility function of the first vehicle based on the first decision information of the first vehicle and the game results of each game strategy in K×L game strategies; and can construct a first probability distribution function based on the first decision information of the first vehicle, the second decision information of the second vehicle and the traffic environment information of the game participants; it can also construct a second probability distribution function based on the first decision information of the first vehicle and the possible decision behavior of the second vehicle; and can construct a third probability distribution function for characterizing the distribution of possible decision behaviors of the second vehicle based on the traffic environment information of the game participants; it can also construct a fourth probability distribution function based on the possible decision behavior of the first vehicle. In this way, after obtaining the utility function corresponding to the first vehicle, the second probability distribution function for characterizing the probability distribution of the second potential behavior of the second vehicle, the third probability distribution function for characterizing the probability distribution of the possible decision behavior of the second vehicle, and the fourth probability distribution function for characterizing the probability distribution of the traffic environment information of the game participants, based on the utility function corresponding to the first vehicle, the first probability distribution function, the second probability distribution function, the third probability distribution function and the fourth probability distribution function, the expected utility function corresponding to the first vehicle can be constructed.

[0120] In this embodiment, the expected utility function corresponding to the first vehicle can be accurately constructed by constructing a utility function corresponding to the first vehicle, a second probability distribution function for characterizing the probability distribution of the second potential behavior of the second vehicle, a third probability distribution function for characterizing the probability distribution of the possible decision-making behavior of the second vehicle, and a fourth probability distribution function for characterizing the probability distribution of the traffic environment information of the game participants, so that the expected utility function corresponding to the first vehicle can be accurately calculated subsequently.

[0121] Based on this, in some embodiments, the expected utility function corresponding to the first vehicle involved above may satisfy the following formula (1):

[0122] E A [u A (a,s)|y A ]=∫ Θ ∫ yM ∫ M ∫ S u s (a,s)dP A (s|m,a,θ)dP A (m|a,y M )dP A (y M |θ)dP A (θ|y A ) (1)

[0123] Among them, u s (a,s) is the utility function of the first vehicle, P A (s|m,a,θ) is the first probability distribution function, P A (m|a,y M ) is the second probability distribution function, P A (y M |θ) is the third probability distribution function, P A (θ|y A ) is a fourth probability distribution function;

[0124] a is the first decision information of the first vehicle, s includes the game results of each game strategy in K×L game strategies, m is the second decision information of the second vehicle, θ∈Θ is the traffic environment information of the game participants, y M is the possible decision behavior of the second vehicle, y A is the possible decision behavior of the first vehicle.

[0125] Based on this, it should be noted that when solving for the expected utility value corresponding to each first potential behavior, the following formula (2) can be obtained by using the above formula (1) for solution, as shown below:

[0126]

[0127] In this embodiment, the expected utility value of each first potential behavior can be accurately calculated according to the above formula, which facilitates the subsequent accurate determination of the target behavior to be performed by the first vehicle based on the expected utility value of each first potential behavior, thereby improving the accuracy of vehicle decision-making.

[0128] Based on this, it should be noted that due to the above u s (a,s),P A (s|m,a,θ),P A (y M |θ) and P A (θ|y A ) can be solved by standard methods according to the decision analysis method. A (m|a,y M ) It is necessary to predict the distribution of the decision-making behavior of vehicle M. In this way, the vehicle lane change control method provided in the embodiment of the present application can stand from the perspective of vehicle M and use the decision analysis of vehicle M To simulate P A (m|a,y M ), and then solve the overall utility expectation equation, and finally get the optimal solution. The specific process is as follows:

[0129] First, based on the expected utility model of vehicle A, the optimal decision solution of vehicle M predicted from the perspective of vehicle M can be obtained in the same way, which can be specifically shown in the following formula (3):

[0130]

[0131] Among them, the state control and utility expression involved in the optimal solution of vehicle M are the same as above, indicating that the performance perspective is the perspective of vehicle M. However, since it is impossible to know the specific utility of vehicle M or to determine the probability distribution of its related behavior, a simulated random utility equation u is obtained through vehicle A's preference behavior for vehicle M. M (m,s) and the random utility distribution equation Π M () is used to approximate the optimal solution judgment of vehicle M. In this way, the solution can be transformed into the content shown in the following formula (4):

[0132]

[0133] Among them, U M (m,s) is the simulation random utility equation, Π M (s|m,a,θ) is the first random utility distribution function, Π M (θ|y M ) is the second random utility distribution function;

[0134] a is the first decision information of the first vehicle, s includes the game results of each game strategy in K×L game strategies, m is the second decision information of the second vehicle, θ is the traffic environment information of the game participants, y M is the possible decision behavior of the second vehicle, y A is the possible decision behavior of the first vehicle.

[0135] In this way, the lane change assistance system can know a, y M , for each known a, y M By combining , multiple groups of random values ​​can be obtained. Each group of random values ​​may include a first random value corresponding to the simulation random utility, a second random value corresponding to the first random utility distribution function, and a third random value corresponding to the second random utility distribution function. The multiple groups of random values ​​can be obtained based on sampling. Thus, each group of random values ​​is introduced into the above formula (4), and based on the calculation result of the above formula (4), the formula (3) is reversed to obtain the optimal solution corresponding to each group of random values, that is, the current optimal behavior of the second vehicle. Then, the above second probability distribution function can be determined by the following formula (5), as shown below:

[0136]

[0137] Among them, N is the number of groups of random values, I is the optimal solution corresponding to each group of random values, and m *.i is the utility value of the optimal solution corresponding to each set of random values.

[0138] Thus, M*(a,y M ) can be obtained by the expected maximum utility value of a repeated random simulation M, thus obtaining The approximate value of P A (m|a,y M ). The more simulations are performed, the more accurate the approximation will be.

[0139] Based on the above, in one embodiment, Figure 7 As shown, the above-mentioned S630 may specifically include the following steps:

[0140] S710, obtaining a target utility function corresponding to the second vehicle.

[0141] In some embodiments, the target utility function corresponding to the second vehicle involved is determined based on the simulation random utility equation, the first random utility distribution function and the second random utility distribution function. It should be noted that the target utility function can be detailed in the above formula (4).

[0142] S720, for each possible decision behavior of the second vehicle, based on the first decision information of the first vehicle and the second decision information of the second vehicle, obtain multiple groups of random values ​​corresponding to the possible decision behavior of the second vehicle.

[0143] Each group of random values ​​may include a first random value corresponding to the simulated random utility simulation, a second random value corresponding to the first random utility distribution function, and a third random value corresponding to the second random utility distribution function.

[0144] S730, for each group of random values ​​in the multiple groups of random values, solving the target utility function corresponding to the second vehicle based on each group of random values, obtaining an optimal solution for each group of random values, and obtaining multiple optimal solutions.

[0145] S740, obtain a second probability distribution function based on simulation of multiple optimal solutions.

[0146] Specifically, the lane change assistance system can obtain the target utility function corresponding to the second vehicle, and for each possible decision-making behavior of the second vehicle, based on the first decision information of the first vehicle and the second decision information of the second vehicle, obtain multiple groups of random values ​​corresponding to the possible decision-making behaviors of the second vehicle, and then, for each group of random values ​​in the multiple groups of random values, the target utility function corresponding to the second vehicle can be solved based on each group of random values ​​to obtain the optimal solution for each group of random values, and multiple optimal solutions can be obtained. Finally, the second probability distribution function can be simulated based on the multiple optimal solutions.

[0147] In this embodiment, the expected maximum utility value of M can be obtained by repeating a random simulation multiple times, thereby obtaining The approximate value of P A (m|a,y M ). This makes it easier to accurately construct the expected utility function corresponding to the first vehicle in the future.

[0148] Thus, based on the vehicle control method provided by the embodiment of the present application, in one embodiment, Figure 8 As shown, vehicle A is driving in the first lane, and vehicle M is driving in the second lane. When vehicle B is in front of vehicle A and affects the driving of vehicle A, the lane change assistance system in vehicle A will receive a first instruction, which is used to instruct vehicle A to change lanes from the first lane to the second lane. Since vehicle M is driving in the second lane, the lane change assistance system in vehicle A needs to determine whether vehicle A can successfully change lanes based on the current driving environment, that is, whether vehicle M will cause vehicle A to fail to change lanes during the process of vehicle A changing lanes from the first lane to the second lane where vehicle M is located.

[0149] Based on this, based on the vehicle lane change control method provided in the embodiment of the present application, the decision model of vehicle A can be established from the perspective of vehicle A, and the decision model of vehicle M can be established from the perspective of vehicle M. Specifically, Fig. 9 As shown, Fig. 9 (a) is a schematic diagram of the decision model of vehicle A. Fig. 9(b) is a schematic diagram of the decision model of the vehicle M. In this way, based on the decision model of the vehicle A, the utility of the vehicle A can be considered from the perspective of the vehicle A. By observing or inferring the behavior of the vehicle M, the vehicle A can be controlled to make a choice that maximizes the utility of the vehicle A. It can be simply understood that the choice here is to perform a lane change action and not to perform a lane change action (i.e., continue driving in the first lane). Similarly, based on the decision model of the vehicle M, the utility of the vehicle M and the utility of the vehicle A can be considered from the perspective of the vehicle M to determine the choice of the vehicle M. It can be simply understood here that the choice of the vehicle M can be to accelerate without giving way and to slow down to avoid. It should be noted that as a problem centered on the decision of the vehicle A as a whole, the modeling of the vehicle M as a whole belongs to a prediction model.

[0150] Specifically, Fig. 9 (a) Fig. 9 As shown in (b), θ∈Θ can refer to the current environment information, and can also be understood as all relevant information of the current objective environment, which is not specifically limited here. A It is the first environmental information perceived by vehicle A through various sensors, that is, the environmental information from the perspective of vehicle A. M It is the second environmental information perceived by vehicle M through various sensors, that is, the environmental information from the perspective of vehicle M. A can be the decision-making behavior of vehicle A, which can include two decision-making behaviors: executing lane changing action and not executing lane changing action. M can be the decision-making behavior of vehicle M, which can include two decision-making behaviors: executing acceleration action (that is, vehicle M does not give way to vehicle A) and executing deceleration action (that is, vehicle M gives way to vehicle A). S can be the game result obtained by playing the game based on the decision-making behavior of vehicle A and the decision-making behavior of vehicle M. It can be a probability distribution s∈S. This result distribution produces utility values ​​for vehicle A and vehicle M respectively from different perspectives, that is, the utility value u of vehicle A. A , which is used to evaluate the feasibility of vehicle A’s decision behavior and the utility value u of vehicle M M , which is used to evaluate the occurrence probability of the decision-making behavior of vehicle M.

[0151] Based on this, combining the game perspectives of vehicle A and vehicle M, we can get the following: Fig.10 The schematic diagram of the decision model combining the two game perspectives is shown. Based on this, the vehicle lane changing method provided in the embodiment of the present application can be based on Fig.10 The content shown in the figure starts to build a decision model. Specifically, according to Bayesian theory, the probability distribution of the probability of a specific event can be obtained in each state space to calculate the four state spaces θ, y of vehicle A. M , M, S under the expected utility function. It should be noted that when constructing the expected utility function of vehicle A, it is necessary to first construct PA (m|a,y M ). In this way, the expected utility of each potential behavior of vehicle A can be solved based on the expected utility function of vehicle A, so as to facilitate the subsequent accurate determination of the target behavior to control vehicle A accordingly.

[0152] Based on the same inventive concept, the embodiment of the present application also provides a vehicle control device, which can be applied to a lane change assist system. Fig.11 The vehicle control device provided in the embodiment of the present application is described in detail.

[0153] Fig.11 It is a structural schematic diagram of a vehicle control device provided in an embodiment of the present application.

[0154] like Fig.11 As shown, the vehicle control device 1100 may include:

[0155] An acquisition module 1110 is used to acquire traffic environment information of game participants, where the game participants include a first vehicle and a second vehicle, the first vehicle travels in a first lane, and the second vehicle travels in a second lane;

[0156] A determination module 1120 is used to determine first decision information of the first vehicle, second decision information of the second vehicle, and a game result of each of K×L game strategies based on traffic environment information of the game participants, wherein the first decision information includes K first potential behaviors, and the second decision information includes L second potential behaviors;

[0157] A construction module 1130 is used to construct an expected utility function corresponding to the first vehicle based on the traffic environment information of the game participants, the first decision information, the second decision information, and the game result of each game strategy in the K×L game strategies;

[0158] A control module 1140 is used to control the first vehicle to perform a target behavior, wherein the target behavior is based on expected utility values ​​corresponding to K first potential behaviors, respectively. The behavior is determined from the K first potential behaviors, and the expected utility values ​​corresponding to the K first potential behaviors are obtained based on the expected utility function corresponding to the first vehicle. The expected utility value of each first potential behavior is used to evaluate the feasibility of the first vehicle performing the first potential behavior. The target behavior includes a first target behavior that characterizes the first vehicle traveling in a first lane, or a second target behavior that characterizes the first vehicle traveling in a second lane.

[0159] In one embodiment, the acquisition module is specifically used for:

[0160] receiving a first instruction, where the first instruction is triggered when sensor information acquired by a sensor of the first vehicle meets a preset lane-changing condition, and the first instruction is used to instruct the first vehicle to perform a lane-changing action, where the lane-changing action is an action that enables the first vehicle to switch from a currently traveling first lane to a second lane;

[0161] In response to the first instruction, traffic environment information of the game participants is obtained.

[0162] In one embodiment, the above building blocks are specifically used for:

[0163] Constructing a utility function of the first vehicle based on the first decision information of the first vehicle and the game result of each game strategy in the K×L game strategies;

[0164] Based on the first decision information of the first vehicle, the second decision information of the second vehicle and the traffic environment information of the game participants, a first probability distribution function is constructed, where the first probability distribution function is used to characterize the probability distribution of the game result of each game strategy in the K×L game strategies;

[0165] Based on the first decision information of the first vehicle and the possible decision behavior of the second vehicle, construct a second probability distribution function, where the second probability distribution function is used to characterize the probability distribution of a second potential behavior of the second vehicle, where the possible decision behavior of the second vehicle is any one of the L second potential behaviors;

[0166] Based on the traffic environment information of the game participants, a third probability distribution function is constructed, where the third probability distribution function is used to characterize the probability distribution of possible decision-making behaviors of the second vehicle;

[0167] Based on the possible decision behavior of the first vehicle, construct a fourth probability distribution function, the fourth probability distribution function is used to characterize the probability distribution of the traffic environment information of the game participants, and the possible decision behavior of the first vehicle is any one of the K first potential behaviors;

[0168] Based on the utility function of the first vehicle, the first probability distribution function, the second probability distribution function, the third probability distribution function and the fourth probability distribution function, an expected utility function corresponding to the first vehicle is constructed.

[0169] In some embodiments, the expected utility function corresponding to the first vehicle satisfies the following formula:

[0170] E A [u A (a,s)|y A ]=∫ Θ ∫ yM ∫ M ∫ S u s (a,s)dP A(s|m,a,θ)dP A (m|a,y M )dP A (y M |θ)dP A (θ|y A )

[0171] Among them, u s (a,s) is the utility function of the first vehicle, P A (s|m,a,θ) is the first probability distribution function, P A (m|a,y M ) is the second probability distribution function, P A (y M |θ) is the third probability distribution function, P A (θ|y A ) is a fourth probability distribution function;

[0172] a is the first decision information of the first vehicle, s includes the game results of each game strategy in K×L game strategies, m is the second decision information of the second vehicle, θ is the traffic environment information of the game participants, y M is the possible decision behavior of the second vehicle, y A is the possible decision behavior of the first vehicle.

[0173] In one embodiment, the above-mentioned building blocks are specifically used for:

[0174] Obtaining a target utility function corresponding to the second vehicle, where the target utility function corresponding to the second vehicle is determined based on a simulation random utility equation, a first random utility distribution function, and a second random utility distribution function;

[0175] For each possible decision behavior of the second vehicle, based on the first decision information of the first vehicle and the second decision information of the second vehicle, a plurality of groups of random values ​​corresponding to the possible decision behavior of the second vehicle are obtained, each group of random values ​​including a first random value corresponding to the simulation random utility simulation, a second random value corresponding to the first random utility distribution function, and a third random value corresponding to the second random utility distribution function

[0176] For each group of random values ​​in the multiple groups of random values, solving the target utility function corresponding to the second vehicle based on each group of random values, obtaining an optimal solution for each group of random values, and obtaining multiple optimal solutions;

[0177] A second probability distribution function is obtained based on simulation of multiple optimal solutions.

[0178] In some embodiments, the expected utility function corresponding to the second vehicle satisfies the following formula:

[0179]

[0180] Among them, U M (m,s) is the simulation random utility equation, Π M (s|m,a,θ) is the first random utility distribution function, Π M (θ|y M ) is the second random utility distribution function;

[0181] a is the first decision information of the first vehicle, s includes the game results of each game strategy in K×L game strategies, m is the second decision information of the second vehicle, θ is the traffic environment information of the game participants, y M is the possible decision behavior of the second vehicle, y A is the possible decision behavior of the first vehicle.

[0182] In an embodiment of the present application, traffic environment information of game participants can be obtained, and the game participants include a first vehicle and a second vehicle, and the first vehicle is traveling in a first lane, and the second vehicle is traveling in a second lane. Based on this, first decision information of the first vehicle, second decision information of the second vehicle, and game results of each of K×L game strategies can be determined based on the traffic environment information of the game participants. Then, based on the traffic environment information of the game participants, the first decision information, the second decision information, and the game results of each of the K×L game strategies, an expected utility function corresponding to the first vehicle can be constructed. In this way, the expected utility function corresponding to the first vehicle can be solved to obtain expected utility values ​​corresponding to K first potential behaviors, respectively, so that the first vehicle can be controlled to perform a target behavior with a higher expected utility value subsequently. The target behavior may include a first target action representing that the first vehicle is traveling in the first lane, or a second target behavior representing that the first vehicle is traveling in the second lane. In this way, the potential risks and uncertainties in the vehicle's driving process can be taken into account, that is, the changes in opponent's behavior can be taken into account, and the lane change decision can be adjusted in time based on real-time environmental information and opponent's behavior, thereby improving the robustness and reliability of the vehicle's lane change decision, thereby ensuring the safety of vehicle driving.

[0183] Each module in the vehicle control device provided in the embodiment of the present application can be implemented Figures 4 to 7 The method steps of any of the embodiments shown in the figure can achieve the corresponding technical effects, which will not be repeated here for the sake of brevity.

[0184] Fig.12 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0185] The electronic device may include a processor 1201 and a memory 1202 storing computer program instructions.

[0186] Specifically, the processor 1201 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0187] The memory 1202 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 1202 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 1202 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 1202 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 1202 is a non-volatile solid-state memory.

[0188] The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0189] The processor 1201 implements any one of the vehicle control methods in the above embodiments by reading and executing computer program instructions stored in the memory 1202 .

[0190] In one example, the electronic device may further include a communication interface 1203 and a bus 1210. Fig.12 As shown, the processor 1201, the memory 1202, and the communication interface 1203 are connected via a bus 1210 and communicate with each other.

[0191] The communication interface 1203 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0192] Bus 1210 includes hardware, software or both, and the components of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 1210 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0193] In addition, in combination with the vehicle control method in the above embodiment, the embodiment of the present application can provide a computer storage medium to implement. The computer storage medium stores computer program instructions; when the computer program instructions are executed by the processor, the vehicle control method provided in the embodiment of the present application is implemented.

[0194] An embodiment of the present application also provides a computer program product, which includes a computer program, and the computer program is executed by a processor to implement the vehicle control method provided in the embodiment of the present application.

[0195] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0196] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0197] The above are only specific implementation methods of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A vehicle control method, characterized in that: The method comprises: Acquiring traffic environment information of game participants, the game participants including a first vehicle and a second vehicle, the first vehicle traveling in a first lane, and the second vehicle traveling in a second lane; Based on the traffic environment information of the game participants, determine the first decision information of the first vehicle, the second decision information of the second vehicle, and the game result of each game strategy in K×L game strategies, wherein the first decision information includes K first potential behaviors and the second decision information includes L second potential behaviors; constructing an expected utility function corresponding to the first vehicle based on the traffic environment information of the game participants, the first decision information, the second decision information, and the game result of each of the K×L game strategies; Control the first vehicle to perform a target behavior, wherein the target behavior is based on expected utility values ​​corresponding to the K first potential behaviors, respectively. The behavior is determined from the K first potential behaviors, and the expected utility values ​​corresponding to the K first potential behaviors are obtained based on the expected utility function corresponding to the first vehicle. The expected utility value of each first potential behavior is used to evaluate the feasibility of the first vehicle performing the first potential behavior. The target behavior includes a first target behavior that characterizes the first vehicle traveling in a first lane, or a second target behavior that characterizes the first vehicle traveling in a second lane.

2. The method according to claim 1, characterized in that The obtaining of the traffic environment information of the game participants includes: receiving a first instruction, where the first instruction is triggered when sensor information acquired by a sensor of the first vehicle meets a preset lane-changing condition, and the first instruction is used to instruct the first vehicle to perform a lane-changing action, where the lane-changing action is an action that enables the first vehicle to switch from a currently traveling first lane to a second lane; In response to the first instruction, traffic environment information of the game participants is obtained.

3. The method according to claim 1, characterized in that: The method of constructing an expected utility function corresponding to the first vehicle based on the traffic environment information of the game participants, the first decision information, the second decision information, and the game result of each of the K×L game strategies includes: constructing a utility function of the first vehicle based on the first decision information of the first vehicle and a game result of each of the K×L game strategies; Based on the first decision information of the first vehicle, the second decision information of the second vehicle, and the traffic environment information of the game participants, construct a first probability distribution function, where the first probability distribution function is used to characterize the probability distribution of the game result of each of the K×L game strategies; Based on the first decision information of the first vehicle and the possible decision behavior of the second vehicle, construct a second probability distribution function, where the second probability distribution function is used to characterize the probability distribution of a second potential behavior of the second vehicle, and the possible decision behavior of the second vehicle is any one of the L second potential behaviors; Based on the traffic environment information of the game participants, construct a third probability distribution function, wherein the third probability distribution function is used to characterize the probability distribution of possible decision-making behaviors of the second vehicle; Based on the possible decision behavior of the first vehicle, constructing a fourth probability distribution function, the fourth probability distribution function is used to characterize the probability distribution of the traffic environment information of the game participants, and the possible decision behavior of the first vehicle is any one of the K first potential behaviors; Based on the utility function of the first vehicle, the first probability distribution function, the second probability distribution function, the third probability distribution function and the fourth probability distribution function, an expected utility function corresponding to the first vehicle is constructed.

4. The method according to claim 3, characterized in that The expected utility function corresponding to the first vehicle satisfies the following formula: Among them, u s (a, s) is the utility function of the first vehicle, P A (s|m,a,θ) is the first probability distribution function, P A (m|a,y M ) is the second probability distribution function, P A (y M |θ) is the third probability distribution function, P A (θ|y A ) is the fourth probability distribution function; a is the first decision information of the first vehicle, s includes the game result of each game strategy in the K×L game strategies, m is the second decision information of the second vehicle, θ∈Θ is the traffic environment information of the game participants, y M is the possible decision behavior of the second vehicle, y A is the possible decision behavior of the first vehicle.

5. The method according to claim 3 or 4, characterized in that: The constructing a second probability distribution function based on the first decision information of the first vehicle and the possible decision behavior of the second vehicle includes: Acquire a target utility function corresponding to the second vehicle, where the target utility function corresponding to the second vehicle is determined based on a simulation random utility equation, a first random utility distribution function, and a second random utility distribution function; For each possible decision behavior of the second vehicle, based on the first decision information of the first vehicle and the second decision information of the second vehicle, a plurality of groups of random values ​​corresponding to the possible decision behavior of the second vehicle are obtained, each group of random values ​​including a first random value corresponding to the simulation random utility simulation, a second random value corresponding to the first random utility distribution function, and a third random value corresponding to the second random utility distribution function; For each group of random values ​​in the plurality of groups of random values, solving the target utility function corresponding to the second vehicle based on each group of the random values, obtaining an optimal solution for each group of the random values, and obtaining a plurality of optimal solutions; The second probability distribution function is obtained by simulation based on the multiple optimal solutions.

6. The method according to claim 5, characterized in that The objective utility function corresponding to the second vehicle satisfies the following formula: Among them, U M (m,s) is the simulation random utility equation, Π M (s|m,a,θ) is the first random utility distribution function, Π M (θ|y M ) is the second random utility distribution function; a is the first decision information of the first vehicle, s includes the game result of each game strategy in the K×L game strategies, m is the second decision information of the second vehicle, θ is the traffic environment information of the game participants, y M is the possible decision behavior of the second vehicle, y A is the possible decision behavior of the first vehicle.

7. A vehicle control device, characterized in that: The device comprises: An acquisition module, used to acquire traffic environment information of game participants, wherein the game participants include a first vehicle and a second vehicle, the first vehicle travels in a first lane, and the second vehicle travels in a second lane; A determination module, configured to determine, based on the traffic environment information of the game participants, first decision information of the first vehicle, second decision information of the second vehicle, and a game result of each of K×L game strategies, wherein the first decision information includes K first potential behaviors, and the second decision information includes L second potential behaviors; A construction module, configured to construct an expected utility function corresponding to the first vehicle based on the traffic environment information of the game participants, the first decision information, the second decision information, and the game result of each of the K×L game strategies; A control module is used to control the first vehicle to perform a target behavior, wherein the target behavior is based on expected utility values ​​corresponding to the K first potential behaviors, respectively, and the behavior is determined from the K first potential behaviors. The expected utility values ​​corresponding to the K first potential behaviors are obtained based on the expected utility function corresponding to the first vehicle. The expected utility value of each first potential behavior is used to evaluate the feasibility of the first vehicle performing the first potential behavior. The target behavior includes a first target behavior that characterizes the first vehicle traveling in a first lane, or a second target behavior that characterizes the first vehicle traveling in a second lane.

8. An electronic device, characterized in that: The electronic device comprises: a processor and a memory storing computer program instructions; The processor reads and executes the computer program instructions to implement the vehicle control method as described in any one of claims 1-6.

9. A computer storage medium, characterized in that: The computer storage medium stores computer program instructions, which, when executed by a processor, implement the vehicle control method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the vehicle control method according to any one of claims 1 to 6 is implemented.

Images