Vehicle control method, apparatus, device, medium, and product

Abstract

Embodiments of the present application provide a vehicle control method, device, equipment, medium and product, traffic environment information of a game participant is obtained; based on the traffic environment information of the game participant, first decision information of a first vehicle, second decision information of a second vehicle and a game result of each game strategy in K*L game strategies are determined; based on the traffic environment information of the game participant, the first decision information, the second decision information and the game result of each game strategy in the K*L game strategies, an expected utility function corresponding to the first vehicle is constructed; and the first vehicle is controlled to perform a target behavior. Embodiments of the present application improve the reliability of vehicle decision.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of vehicle control, and particularly relates to a vehicle control method, device, equipment, medium and product. BACKGROUND

[0002] In the prior art, a lane changing assistance system in a vehicle detects vehicles around the vehicle and lane lines printed on a road surface in front of the vehicle and the like through sensors arranged around the vehicle, and then determines whether the vehicle is allowed to perform a lane changing action. If the lane changing assistance system allows the vehicle to perform the lane changing action, and after receiving an instruction input (a turn signal lever signal) of a driver, the vehicle can be controlled to change lanes into a corresponding lane to continue driving. That is, the lane changing assistance system can only perform the lane changing action after receiving the instruction input of the driver, and during the process of the vehicle performing the lane changing action, if traffic anomalies, environmental changes, driver intervention and the like occur, the lane changing action can not be completed, and the system can return to the original lane or remind the driver to take over according to the current lane changing situation. In this way, the reliability of the lane changing decision of the vehicle can be low. SUMMARY

[0003] Embodiments of the present application provide a vehicle control method, device, equipment, medium and product, and the reliability of the lane changing decision of the vehicle is improved.

[0004] In a first aspect, embodiments of the present application provide a vehicle control method, which comprises:

[0005] obtaining traffic environment information of game participants, the game participants including a first vehicle and a second vehicle, the first vehicle driving on a first lane, and the second vehicle driving on a second lane;

[0006] 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, the first decision information including K first potential behaviors, and the second decision information including L second potential behaviors;

[0007] 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;

[0008] The first vehicle is controlled to perform a target behavior, the target behavior is determined from K first potential behaviors based on expected utility values corresponding to the K first potential behaviors respectively, the expected utility values corresponding to the K first potential behaviors are obtained based on an 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, and the target behavior includes a first target behavior representing that the first vehicle travels in a first lane, or a second target behavior representing that the first vehicle travels in a second lane.

[0009] In an optional implementation of the first aspect, the traffic environment information of the game participant is acquired, including:

[0010] A first instruction is received, the first instruction being an instruction triggered when sensor information acquired by a sensor of the first vehicle satisfies a preset lane-changing condition, the first instruction being used to instruct the first vehicle to perform a lane-changing action, the lane-changing action being an action capable of causing the first vehicle to switch from a first lane in which the first vehicle is currently traveling to a second lane;

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

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

[0013] Based on the first decision information of the first vehicle and the game result of each game strategy in the K*L game strategies, a utility function of the first vehicle is constructed;

[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 participant, a first probability distribution function is constructed, the first probability distribution function being used to represent a 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 possible decision behaviors of the second vehicle, a second probability distribution function is constructed, the second probability distribution function being used to represent a probability distribution of the second potential behavior of the second vehicle, the possible decision behaviors of the second vehicle being any one of the L second potential behaviors;

[0016] Based on the traffic environment information of the game participant, a third probability distribution function is constructed, the third probability distribution function being used to represent a probability distribution of the possible decision behaviors of the second vehicle;

[0017] construct a fourth probability distribution function based on the possible decision behavior of the first vehicle, the fourth probability distribution function being used to represent a probability distribution of the traffic environment information of the game participant, the possible decision behavior of the first vehicle being any one of the K first potential behaviors;

[0018] construct a corresponding expected utility function of 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.

[0019] In an optional implementation of the first aspect, the corresponding expected utility function of 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] wherein 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, and P A (θ|y A ) is the fourth probability distribution function;

[0022] a is the first decision information of the first vehicle, s includes a 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 participant, y M is the possible decision behavior of the second vehicle, and y A is the possible decision behavior of the first vehicle.

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

[0024] obtain a target utility function corresponding to the second vehicle, the target utility function corresponding to the second vehicle being determined based on the simulation random utility equation, the first random utility distribution function and the 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, obtain a plurality of groups of random values corresponding to the possible decision behavior of the second vehicle, 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 plurality of groups of random values, based on each group of random values, the target utility function corresponding to the second vehicle is solved to obtain an optimal solution of each group of random values, and a plurality of optimal solutions are obtained;

[0027] Based on the plurality of optimal solutions, a second probability distribution function is simulated.

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

[0029]

[0030] wherein, 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 result 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 participant, 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, the embodiments of the present application provide a vehicle control device, which comprises:

[0033] The obtaining module is configured to obtain traffic environment information of a game participant, the game participant including a first vehicle and a second vehicle, the first vehicle driving on a first lane, and the second vehicle driving on a second lane;

[0034] determining a first decision information of the first vehicle, a second decision information of the second vehicle, and a game result of each game strategy in the K*L game strategies based on the traffic environment information of the game participants, the first decision information comprising K first potential behaviors, and the second decision information comprising L second potential behaviors;

[0035] 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;

[0036] controlling the first vehicle to perform a target behavior, the target behavior being determined from the K first potential behaviors based on expected utility values respectively corresponding to the K first potential behaviors, the expected utility values respectively corresponding to the K first potential behaviors being obtained based on the expected utility function corresponding to the first vehicle, and the expected utility value of each first potential behavior being used to evaluate the feasibility of the first vehicle performing the first potential behavior, the target behavior comprising a first target behavior representing the first vehicle driving in the first lane, or a second target behavior representing the first vehicle driving in the second lane.

[0037] In a third aspect, an electronic device is provided, which includes a memory configured to store computer program instructions, and a processor configured to read and run the computer program instructions stored in the memory to execute the vehicle control method provided in any of the optional implementation manners of the first aspect.

[0038] In a fourth aspect, a computer storage medium is provided, which stores computer program instructions, and the computer program instructions are executed by a processor to implement the vehicle control method provided in any of the optional implementation manners of the first aspect.

[0039] In a fifth aspect, a computer program product is provided, which includes a computer program, and the computer program is executed by a processor to implement the vehicle control method provided in any of the optional implementation manners of the first aspect.

[0040] In the embodiment of the present application, the traffic environment information of the game participants, including the first vehicle and the second vehicle, can be obtained, and the first vehicle travels on the first lane and the second vehicle travels on the second lane. Based on this, 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 the K*L game strategies can be determined based on the traffic environment information of the game participants. 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 result of each game strategy in the K*L game strategies. In this way, the expected utility value corresponding to the K first potential behaviors can be obtained by solving the expected utility function of the first vehicle, so that the target behavior with a higher expected utility value can be executed by the first vehicle in the subsequent control. The target behavior can include a first target action representing the first vehicle traveling on the first lane, or a second target behavior representing the first vehicle traveling on the second lane. In this way, the potential risks and uncertainties in the vehicle driving process can be considered, that is, the opponent behavior change is considered, and the lane changing decision can be adjusted in real time based on the real-time environment information and opponent behavior, thereby improving the robustness and reliability of the vehicle lane changing decision, and further ensuring the safety of vehicle driving. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiments of the present application will be briefly introduced. Those skilled in the art can obtain other drawings according to these drawings without creating any creative labor.

[0042] Figure 1 is one of the flowcharts provided by the related art of the embodiments of the present application;

[0043] Figure 2 is another flowchart provided by the related art of the embodiments of the present application;

[0044] Figure 3 is an architecture diagram of a lane changing assistance system provided by the embodiments of the present application

[0045] Figure 4 is one of the flowcharts of a vehicle control method provided by the embodiments of the present application;

[0046] Figure 5 is another flowchart of a vehicle control method provided by the embodiments of the present application;

[0047] Figure 6 is a third flowchart of a vehicle control method provided by the embodiments of the present application;

[0048] Figure 7This is the fourth schematic flowchart of a vehicle control method provided in the embodiments of this application;

[0049] Figure 8 This is one of the scenario diagrams of a vehicle control method provided in the embodiments of this application;

[0050] Figure 9 (a) is a second scenario diagram of a vehicle control method provided in an embodiment of this application;

[0051] Figure 9 (b) is a third scenario diagram of a vehicle control method provided in the embodiments of this application;

[0052] Figure 10 This is a fourth scenario illustration of a vehicle control method provided in the embodiments of this application;

[0053] Figure 11 This is a schematic diagram of the structure of a vehicle control device provided in an embodiment of this application;

[0054] Figure 12 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0055] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0056] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0057] The term "and / or", as used herein, merely describes association between associated objects, indicates that there can be three cases, for example, A and / or B, which can represent: A exists alone, A and B exist together, and B exists alone.

[0058] In the prior art, when the original lane driving condition is poor and the lane changing action needs to be performed during vehicle driving, the lane changing process can be performed as shown in the prior art Figure 1 The lane changing process in the prior art can specifically include the following steps:

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

[0060] S102, collecting environmental information.

[0061] Specifically, after the lane changing assistance system receives the input for instructing the vehicle to perform a lane changing action, the environmental information around the vehicle can be collected by using an advanced driving assistance system (ADAS).

[0062] S103, determining whether the vehicle meets the lane changing condition based on the environmental information. If yes, S104 is performed, and if no, S107 is performed.

[0063] S104, deciding whether to perform a vehicle lane changing action. If yes, S105 is performed, and if no, S107 is performed.

[0064] S105, performing a 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 lane changing process shown in the above Figure 1 As shown in the lane changing process, for S104, if the automatic driving level of the vehicle is L2 level, i.e., the vehicle is a semi-automatic driving vehicle, the driver needs to manually input instructions to control the vehicle to perform or not to perform a lane changing action.

[0068] If the vehicle is a conditional autonomous vehicle, i.e. the vehicle is a L3 level autonomous vehicle, the lane changing decision is not controlled by human, so the lane changing assistant system can directly execute the lane changing action after determining that the vehicle meets the lane changing condition, i.e. the lane changing assistant system lacks the decision action of whether the vehicle executes the lane changing. If the basic game theory method is used, the information of the autonomous vehicle and the adjacent road vehicles needs to be common knowledge to meet the game theory condition, which must be realized by the vehicle-to-vehicle communication (V2V) function. However, the V2V is not applicable to most vehicles at present, so there is a great limitation.

[0069] In addition, during the execution of the lane changing action of the vehicle, if the traffic is abnormal, the environment changes, the driver intervenes, etc., the lane changing action of the vehicle may fail to be completed, the lane changing assistant system selects to return to the original lane according to the current lane changing condition, or prompts the driver to take over and exit. Thus, the reliability of the lane changing decision of the vehicle may be low.

[0070] In order to more accurately describe the overall process of the vehicle executing the lane changing action in the prior art, the overall process of the vehicle executing the lane changing action in the related art can be as follows Figure 2As shown, OFF indicates that the lane change assist system is in a deactivated state, meaning the system cannot perform a lane change maneuver. Inhibited indicates that the lane change assist system is in a suppressed state, meaning there are suppression conditions for the system, preventing it from performing a lane change maneuver. Enable indicates that the system is in a pending state where the enabling conditions are met. If there are no suppression conditions and no lane change command is received, the system must remain in this state, and it still cannot perform a lane change maneuver. It should be noted that both the enabling and suppression conditions can be determined based on the actual vehicle conditions and are not specifically limited here. Wait indicates that the lane change assist system is in a waiting state. Here, the system can wait for a preset duration to meet the pre-set lane change advance operation time. This preset duration can be set based on actual conditions or experience; for example, it could be 3 seconds. No specific limitation is made here. It should be noted that when the lane change assist system is in a waiting state, it can still control the vehicle to stay centered, but this requires a prerequisite: no other conditions besides the turn signal stalk being activated. Lane Changing: Indicates that the lane change assist system is in the process of changing lanes; its longitudinal control remains active, while lateral centering control is temporarily suppressed. Lane Changed: Indicates that the lane change assist system has successfully completed the lane change maneuver. The vehicle can now move to the center line of the target lane, and the system will automatically transition to the suppressed state. Cancel: Indicates that the lane change maneuver has been cancelled; the system no longer needs to perform the maneuver. In this case, the system can warn the driver to take over immediately via the human-machine interface, and the system will automatically transition to the suppressed state. Retreated: Indicates that the lane change maneuver has been cancelled; the system no longer needs to perform the maneuver. In this way, the vehicle can exit the center line of the original lane. At this point, the lane change assist system will automatically switch from the current state to the suppressed state. Failure: This indicates that when a system malfunction, steering lever malfunction, or turn signal malfunction occurs, the lane change assist system will automatically switch from the current state to the lane change failure state.

[0071] Thus, based on Figure 2 As shown, the Standby Enable State indicates that the conditions for lane changing are met, but the lane change assist system has not received a lane change decision / instruction. Therefore, step 5 in the diagram, transitioning from the Enabled state to the Wait state, represents the decision-making process of the decision-making unit. In autonomous driving below Level 2, this involves manual operation by the driver; in Level 3 and above, the vehicle needs to make its own judgments and take control.

[0072] In order to accurately describe the overall process of the vehicle performing the lane changing action in the related art, it needs to be explained first that the figure can accurately describe the overall process of the vehicle performing the lane changing action in the prior art, which can be specifically as shown in Figure 2 As shown in the figure, when the lane changing assistance system in the vehicle is in the off state (i.e., the lane changing assistance system in the vehicle cannot currently perform the lane changing action), if the lane changing assistance system receives a switching signal sent by the switching module, such as an automated-driving control unit (ACU), through the bus, the lane changing assistance system can switch the current state from the off state to the on state, and can feed back the current state of the lane changing assistance system to the ACU through the bus.

[0073] Based on this, in order to solve the above 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, the game participants including a first vehicle and a second vehicle, and the first vehicle driving on a first lane and the second vehicle driving on 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 result of each game strategy in KxL game strategies can be determined based on the traffic environment information of the game participants. 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 result of each game strategy in KxL game strategies. In this way, the expected utility value corresponding to K first potential behaviors can be obtained by solving the expected utility function corresponding to the first vehicle, so that the first vehicle can be controlled to perform a target behavior with a higher expected utility value in the subsequent process. The target behavior can include a first target action representing the first vehicle driving on the first lane, or a second target behavior representing the first vehicle driving on the second lane. In this way, the potential risks and uncertainties in the vehicle driving process can be considered, i.e., the opponent behavior change is considered, and the lane changing decision can be adjusted in a timely manner based on real-time environmental information and opponent behavior, thereby improving the robustness and reliability of the vehicle lane changing decision, and further ensuring the safety of the vehicle driving.

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

[0075] Figure 3 is an architecture diagram of a lane changing assistance system provided by the embodiments of the present application.

[0076] As Figure 3As shown, the lane change assistance system includes a condition judgment module, a mode management module, and a vehicle control module. The condition judgment module is connected to a vision system level chip, a sensor, and the mode management module. The mode management module is connected to the vehicle control module, a human-machine interface, and a turn signal control device. The vehicle control module is connected to an electric power steering device.

[0077] Based on Figure 3 As shown in the architecture diagram, the system function components of the lane change assistance system (i.e., the condition judgment module, the mode management module, and the vehicle control module) can determine whether the vehicle meets the lane change condition based on the information detected by the vision system level chip and the sensor, input the information to the mode management module for management decision, determine the current vehicle mode, and output the current vehicle mode to the human-machine interface and the turn signal controller. If the vehicle needs to change lanes or cancel the lane change, the vehicle control module needs to be input to determine whether the electric power steering is needed.

[0078] It should be noted that the information detected by the vision system level chip and the sensor can include the distance between the vehicle and surrounding vehicles or other objects. Accordingly, the lane change condition can be set with a safety distance threshold, and it can be determined 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 as a front safety distance threshold, a rear safety distance threshold, and left and right safety distance thresholds according to actual conditions, which are not limited here.

[0079] Based on this, based on the above Figure 3 As shown in the architecture diagram of the lane change assistance system, the vehicle control method provided in the embodiments of the present application is described in detail in combination with the following drawings.

[0080] As shown in the architecture diagram of the lane change assistance system, the vehicle control method provided in the embodiments of the present application is described in detail in combination with the following drawings. Figure 4 As shown, the execution subject of the vehicle control method can be a lane change assistance system, which can be a lane change assist (LCA) system, an indicated lane change (ILC) system, or other systems for controlling vehicle lane change driving, which are not limited here. Based on this, the vehicle control method can specifically include the following steps:

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

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

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

[0084] S420, based on the traffic environment information of the game participants, determining 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 the K*L game strategies.

[0085] The first decision information of the first vehicle can include relevant decision information that the first vehicle can perform, which can include K first potential behaviors. For example, the K first potential behaviors can include lane changing behavior and non-lane changing behavior, and in addition, the K first potential behaviors can include other decision behaviors that the first vehicle can perform, which are not limited herein.

[0086] Similarly, the second decision information of the second vehicle can include relevant decision information that the second vehicle can perform, which can include L second potential behaviors. For example, the L second potential behaviors can include yielding behavior and non-yielding behavior, and in addition, the L second potential behaviors can also include other decision behaviors that the second vehicle can perform, which are not limited herein. K and L are both positive integers, and the application embodiments do not limit the values of K and L.

[0087] Specifically, the lane changing 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 changing assistance system can also determine the game result of each game strategy in 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, 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, constructing the expected utility function corresponding to the first vehicle.

[0089] Specifically, the lane changing 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 result of each game strategy in the K*L game strategies after determining 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 the K*L game strategies.

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

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

[0092] In addition, the target behavior can include a first target behavior indicating that the first vehicle drives along the first lane, i.e., the first vehicle does not perform a lane changing action, or a second target behavior indicating that the first vehicle drives along the second lane, i.e., the second vehicle performs a lane changing action. It should be noted that the first target behavior can include a plurality of behaviors that can enable the first vehicle to drive along the first lane, and the second target behavior can include a plurality of behaviors that can enable the first vehicle to drive along the second lane.

[0093] Specifically, after the expected utility function corresponding to the first vehicle is constructed, the expected utility function corresponding to the first vehicle can be solved to obtain an expected utility value corresponding to each of the K first potential behaviors, and then the target behavior can be determined from the K first potential behaviors based on the expected utility value corresponding to each of the K first potential behaviors, and then the first vehicle can be controlled to perform the target behavior.

[0094] In order to more accurately determine the target behavior, in an embodiment, before the first vehicle is controlled to perform the target behavior, the vehicle control method can further include the following steps:

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

[0096] Specifically, since each expected utility value of the first potential behaviors is used to evaluate the feasibility of the first vehicle performing the first potential behavior, after the expected utility function corresponding to the first vehicle is solved to obtain an expected utility value corresponding to each of the K first potential behaviors, the first potential behavior with the maximum expected utility value can be determined as the target behavior from the K first potential behaviors based on the expected utility values corresponding to the K first potential behaviors respectively.

[0097] In this embodiment, the first potential behavior with the maximum expected utility value can be determined based on the expected utility values of the K first potential behaviors before the first vehicle is controlled to perform the target behavior, so that the target behavior can be accurately determined, and the reliability of the vehicle decision behavior is improved.

[0098] In the embodiments of the present application, the traffic environment information of the game participants, including the first vehicle and the second vehicle, can be obtained, and the first vehicle travels on the first lane and the second vehicle travels on the second lane. Based on this, 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 the K*L game strategies can be determined based on the traffic environment information of the game participants. 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 result of each game strategy in the K*L game strategies. In this way, the expected utility values of the K first potential behaviors can be obtained by solving the expected utility function corresponding to the first vehicle, so that the first vehicle can be controlled to perform a target behavior with a higher expected utility value in the future. The target behavior can include a first target action representing the first vehicle traveling on the first lane, or a second target behavior representing the first vehicle traveling on the second lane. In this way, potential risks and uncertainties in the vehicle driving process can be considered, i.e., the opponent's behavior change is considered, and the lane changing decision can be adjusted in a timely manner based on real-time environmental information and opponent behavior, improving the robustness and reliability of the vehicle lane changing decision, and thus ensuring the safety of vehicle driving.

[0099] To more accurately describe the vehicle control method provided by the embodiments of the present application, in one embodiment, as shown in Figure 5 The S410 described above can 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, which is an action that can cause the first vehicle to switch from the first lane currently traveled to the second lane.

[0102] The first instruction is used to instruct the first vehicle to perform a lane changing action. The lane changing action can be an action that can cause the first vehicle to switch from the first lane currently traveled to the second lane.

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

[0104] In addition to the above, the first instruction can also be sent by a target system to the lane changing assistance system. The target system can be a system capable of instructing the vehicle to perform a lane changing action. For example, the target system can be a navigation system, or the target system can be a system capable of detecting that a congestion, regulation, or other situation exists in front of the current lane of the vehicle that is not suitable for the vehicle to pass through, and the like, which is not limited herein.

[0105] S520, in response to the first instruction, obtaining the traffic environment information of the game participant.

[0106] Specifically, the lane changing assistance system can receive the first instruction, and since the first instruction is used to instruct the first vehicle to perform a lane changing action, which is an action that can cause the first vehicle to switch from the first lane in which it is currently driving to the second lane, the lane changing assistance system can obtain the traffic environment information of the game participant in response to the first instruction.

[0107] In this embodiment, by receiving the first instruction for instructing the first vehicle to perform a lane changing action, and obtaining the traffic environment information of the game participant in response to the first instruction, the target behavior can be accurately determined by taking into account the changes in the surrounding environment and the behavior of the opponent, and the reliability of the vehicle lane changing decision can be improved.

[0108] In order to more accurately describe the vehicle control method provided by the embodiments of the present application, in one embodiment, as shown in Figure 6 The S430 described above can 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 KxL game strategies.

[0110] S620, constructing 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 participant.

[0111] The first probability distribution function described above can be used to represent the probability distribution of the game result of each game strategy in the KxL game strategies.

[0112] S630, 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.

[0113] The second probability distribution function described above can be used to represent 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.

[0114] S640, constructing a third probability distribution function for representing a distribution of possible decision behaviors of the second vehicle based on the traffic environment information of the game participant.

[0115] wherein the third probability distribution function can be used to represent a probability distribution of the possible decision behaviors of the second vehicle.

[0116] S650, constructing a fourth probability distribution function based on the possible decision behaviors of the first vehicle.

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

[0118] S660, constructing a corresponding expected utility function of 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 the utility function of the first vehicle based on the first decision information of the first vehicle and the game results of each game strategy of the KxL game strategies; and can construct the 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 participant; can also construct the second probability distribution function based on the first decision information of the first vehicle and the possible decision behaviors of the second vehicle; and can construct the third probability distribution function for representing a distribution of possible decision behaviors of the second vehicle based on the traffic environment information of the game participant; and can also construct the fourth probability distribution function based on the possible decision behaviors of the first vehicle, so that after obtaining the corresponding utility function of the first vehicle, the second probability distribution function for representing a probability distribution of the second potential behavior of the second vehicle, the third probability distribution function for representing a probability distribution of the possible decision behaviors of the second vehicle, and the fourth probability distribution function for representing a probability distribution of the traffic environment information of the game participant, the corresponding expected utility function of the first vehicle is constructed based on the above-mentioned 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.

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

[0121] Based on this, in some embodiments, the expected utility function corresponding to the first vehicle involved above can 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] Wherein, 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, and P A (θ|y A ) is the fourth probability distribution function.

[0124] a is the first decision information of the first vehicle, s includes the game result 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 participant, y M is the possible decision behavior of the second vehicle, and y A is the possible decision behavior of the first vehicle.

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

[0126]

[0127] In this embodiment, the expected utility value of each first potential behavior can be accurately calculated according to the above formula, and then the target behavior to be executed by the first vehicle can be accurately determined based on the expected utility value of each first potential behavior, thereby improving the accuracy of vehicle decision-making.

[0128] Therefore, 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 All of these can be solved using standard decision analysis methods, except for the aforementioned P. A (m|a,y M It is necessary to predict the distribution of decision-making behavior of vehicle M. Therefore, the lane-changing control method provided in this application can analyze vehicle M's decision-making behavior from the perspective of vehicle M. To simulate P A (m|a,y M Then, the overall utility expectation equation is solved to obtain the optimal solution. The specific process is as follows:

[0129] First, based on the expected utility model of vehicle A, we can similarly obtain the optimal decision solution for vehicle M from the perspective of vehicle M, as shown in the following formula (3):

[0130]

[0131] In this solution, the state controls and utility expressions involved in the optimal solution for vehicle M are the same as above, indicating that the perspective is that of vehicle M. However, since the specific utility of vehicle M cannot be known definitively or the probability distribution of its related behaviors cannot be determined, a simulation stochastic utility equation u is used to simulate the preference behavior of vehicle A towards vehicle M. M (m,s) and the random utility distribution equation Π M () is used to approximate the optimal solution for vehicle M. The solution can be transformed into the following formula (4):

[0132]

[0133] Among them, U M (m,s) represents the simulated stochastic 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 represents the first vehicle's initial decision information, s includes the game outcome of each of the K×L game strategies, m represents the second vehicle's initial decision information, θ represents the traffic environment information of the game participants, and y represents the second vehicle's initial decision information. M For the possible decision-making behavior of the second vehicle, y A The possible decision-making behavior of the first vehicle.

[0135] In this way, the lane change assistance system can know a, y M For each combination of a, y M known, a plurality of sets of random values can be obtained, each set of random values can include a first random value corresponding to the simulation of 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, and the plurality of sets of random values can be obtained based on sampling. In this way, for each set of random values, the above formula (4) is brought into, and based on the calculation result of bringing the above formula (4) into, the formula (3) is backstepped, and the optimal solution corresponding to each set of random values, that is, the optimal behavior of the second vehicle at present, can be obtained. Further, the above second probability distribution function can be determined by the following formula (5), as shown below:

[0136]

[0137] Wherein, N is the number of sets of random values, I is the optimal solution corresponding to each set of random values, m *.i is the utility value of the optimal solution corresponding to each set of random values.

[0138] In this way, the optimal decision sample distribution of M*(a, y M ) can be obtained by repeatedly simulating the expected maximum utility value of M, so as to obtain the approximation value of P A (m|a, y M ). The more the simulation times, the more accurate the approximation value.

[0139] Based on the above, in an embodiment, as Figure 7 shown, the above S630 can specifically include the following steps:

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

[0141] In some embodiments, the above-mentioned target utility function corresponding to the second vehicle 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, a plurality of sets of random values corresponding to the possible decision behavior of the second vehicle are obtained.

[0143] Each set of random values can include a first random value corresponding to the simulation of 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.

[0144] S730, for each set of random values, based on each set of random values, the target utility function corresponding to the second vehicle is solved, and the optimal solution of each set of random values is obtained, and a plurality of optimal solutions are obtained.

[0145] S740, based on the plurality of optimal solutions, a second probability distribution function is simulated.

[0146] Specifically, the lane change assistance system can obtain the target utility function corresponding to the second vehicle, and 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 sets of random values corresponding to the possible decision behavior of the second vehicle are obtained, and then for each set of random values, based on each set of random values, the target utility function corresponding to the second vehicle is solved, and the optimal solution of each set of random values is obtained, and a plurality of optimal solutions are obtained, and finally, based on the plurality of optimal solutions, a second probability distribution function is simulated.

[0147] In this embodiment, the expected maximum utility value of the random simulation M can be obtained by repeating a plurality of times, so that an approximate value of P A (m|a,y M ) is obtained. Then it is convenient to accurately construct the expected utility function corresponding to the first vehicle.

[0148] In this way, based on the vehicle control method provided in the embodiments of the present application, in one embodiment, as shown in Figure 8 , vehicle A drives on the first lane, vehicle M drives on the second lane, when there is vehicle B in front of vehicle A affecting 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 currently driving to the second lane, and because there is vehicle M driving on the second lane. Therefore, the lane change assistance system in vehicle A needs to judge whether vehicle A can successfully change lanes in combination with the current driving environment, that is, whether vehicle M will cause vehicle A to fail to change lanes in the process of 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 embodiments of the present application, the decision model of vehicle A can be established in turn from the perspective of vehicle A, and the decision model of vehicle M can be established from the perspective of vehicle M. Specifically, as shown in Figure 9 , wherein, Figure 9 (a) is a schematic diagram of the decision model of vehicle A, Figure 9(b) is a schematic diagram of the decision model of the above-mentioned vehicle M. In this way, based on the decision model of the above-mentioned vehicle A, the self-utility of the vehicle A is considered from the perspective of the vehicle A, the behavior of the vehicle M is observed or inferred, and the vehicle A is controlled to make a selection that maximizes the self-utility of the vehicle A. The selection can be simply understood as two options, i.e., performing a lane-changing action and not performing a lane-changing action (i.e., continuing to travel in the first lane). Similarly, based on the decision model of the above-mentioned vehicle M, the self-utility of the vehicle M and the self-utility of the vehicle A are considered from the perspective of the vehicle M, and the selection of the vehicle M is determined. The selection of the vehicle M can be simply understood as two options, i.e., accelerating and not giving way and decelerating to give way. It should be noted that, as a whole, the modeling of the vehicle M is a prediction model for the decision center of the vehicle A.

[0150] Specifically, as shown in Figure 9 (a) and Figure 9 (b), θ∈Θ can refer to current environmental information, which can also be understood as all relevant information of the current objective environment, which is not limited here. A Y is the first environmental information perceived by the vehicle A through various sensors, i.e., the environmental information from the perspective of the vehicle A. M Y is the second environmental information perceived by the vehicle M through various sensors, i.e., the environmental information from the perspective of the vehicle M. A can be the decision behavior of the vehicle A, which can include two decision behaviors, i.e., performing a lane-changing action and not performing a lane-changing action. M can be the decision behavior of the vehicle M, which can include two decision behaviors, i.e., performing an accelerating action (i.e., the vehicle M does not give way to the vehicle A) and performing a decelerating action (i.e., the vehicle M gives way to the vehicle A). S can be a game result obtained by game between the decision behavior of the vehicle A and the decision behavior of the vehicle M, which can be a probability distribution s∈S. This result distribution produces utility values for the vehicle A and the vehicle M from different perspectives, i.e., the utility value u A of the vehicle A, which is used to evaluate the feasibility of the decision behavior of the vehicle A, and the utility value u M of the vehicle M, which is used to evaluate the probability of occurrence of the decision behavior of the vehicle M.

[0151] Based on this, the game perspectives of the vehicle A and the vehicle M are combined, and a schematic diagram of a decision model combined from the game perspectives of the two is shown in Figure 10 Based on this, the vehicle lane-changing method provided in the embodiments of the present application can start to build a decision model based on the content shown in Figure 10 Specifically, according to the Bayesian theory, the probability distribution of the probability of a specific event in the respective state space can be obtained to calculate the expected utility functions of the vehicle A in the four state spaces Θ, y M , M and S. It should be noted that, when building the expected utility function of the vehicle A, 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, and then the target behavior can be accurately determined for subsequent corresponding control of vehicle A.

[0152] Based on the same inventive concept, the embodiments of the present application also provide a vehicle control device, which can be applied to a lane changing assistance system. Specifically, the embodiments of the present application are described in detail in combination with Figure 11 The vehicle control device provided by the embodiments of the present application is described in detail.

[0153] Figure 11 is a structural schematic diagram of a vehicle control device provided by the embodiments of the present application.

[0154] As shown in Figure 11 , the vehicle control device 1100 can include:

[0155] The acquisition module 1110 is configured to acquire traffic environment information of game participants, the game participants including a first vehicle and a second vehicle, the first vehicle driving on a first lane, and the second vehicle driving on a second lane.

[0156] The determination module 1120 is 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, the first decision information including K first potential behaviors, and the second decision information including L second potential behaviors.

[0157] The construction module 1130 is configured to construct, 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, an expected utility function corresponding to the first vehicle.

[0158] The control module 1140 is configured to control the first vehicle to perform a target behavior, the target behavior being determined from the K first potential behaviors based on expected utility values respectively corresponding to the K first potential behaviors, the expected utility values respectively corresponding to the K first potential behaviors being obtained based on the expected utility function corresponding to the first vehicle, the expected utility value of each first potential behavior being used to evaluate the feasibility of the first vehicle performing the first potential behavior, and the target behavior including a first target behavior representing the first vehicle driving on the first lane or a second target behavior representing the first vehicle driving on the second lane.

[0159] In one embodiment, the acquisition module is specifically configured to:

[0160] receive a first instruction, the first instruction being an instruction triggered when sensor information acquired by a sensor of the first vehicle satisfies a preset lane-changing condition, the first instruction being used to instruct the first vehicle to perform a lane-changing action, the lane-changing action being an action capable of causing the first vehicle to switch from a first lane in which the first vehicle is currently traveling to a second lane;

[0161] In response to the first instruction, obtain traffic environment information of the game participant.

[0162] In one embodiment, the above-mentioned construction module is specifically used for:

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

[0164] 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 participant, the first probability distribution function being used to represent a probability distribution of the game result of each game strategy in the K×L game strategies;

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

[0166] construct a third probability distribution function based on the traffic environment information of the game participant, the third probability distribution function being used to represent a probability distribution of the possible decision behaviors of the second vehicle;

[0167] construct a fourth probability distribution function based on possible decision behaviors of the first vehicle, the fourth probability distribution function being used to represent a probability distribution of the traffic environment information of the game participant, the possible decision behaviors of the first vehicle being any one of the K first potential behaviors;

[0168] construct 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.

[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, 0)dP A (m|a, y M )dP A (y M |0)dP A (0|y A )

[0171] wherein, u s (a, s) is a utility function of the first vehicle, P A (s|m, a, 0) is a first probability distribution function, P A (m|a, y M ) is a second probability distribution function, P A (y M |0) is a third probability distribution function, P A (0|y A ) is a fourth probability distribution function;

[0172] a is first decision information of the first vehicle, s includes a game result of each game strategy in K*L game strategies, m is second decision information of the second vehicle, 0 is traffic environment information of a game participant, y M is a possible decision behavior of the second vehicle, y A is a possible decision behavior of the first vehicle.

[0173] In one embodiment, the above-mentioned construction module is specifically used for:

[0174] obtaining a target utility function corresponding to the second vehicle, the target utility function corresponding to the second vehicle being 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, obtaining a plurality of groups of random values corresponding to the possible decision behavior of the second vehicle, 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 plurality of groups of random values, based on each group of random values, solving the target utility function corresponding to the second vehicle to obtain an optimal solution of each group of random values, and obtaining a plurality of optimal solutions;

[0177] based on the plurality of optimal solutions, simulating to obtain the second probability distribution function.

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

[0179]

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

[0181] a is first decision information of the first vehicle, s includes a game result of each game strategy in KxL game strategies, m is second decision information of the second vehicle, θ is traffic environment information of a game participant, y M is a possible decision behavior of the second vehicle, y A is a possible decision behavior of the first vehicle.

[0182] In the embodiment of the application, the traffic environment information of the game participant including the first vehicle and the second vehicle can be obtained, and the first vehicle travels in the first lane and the second vehicle travels in the second lane. Based on this, 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 KxL game strategies can be determined based on the traffic environment information of the game participant. Then, the expected utility function corresponding to the first vehicle can be constructed based on the traffic environment information of the game participant, the first decision information, the second decision information and the game result of each game strategy in KxL game strategies. In this way, the expected utility value corresponding to K first potential behaviors can be obtained by solving the expected utility function corresponding to the first vehicle, so that the first vehicle can be controlled to perform a target behavior with a higher expected utility value in the subsequent. The target behavior can include a first target action representing that the first vehicle travels in the first lane, or a second target behavior representing that the first vehicle travels in the second lane. In this way, the potential risks and uncertainties in the vehicle driving process can be considered, that is, the opponent behavior change is considered, and the lane changing decision can be adjusted in time based on real-time environment information and opponent behavior, thereby improving the robustness and reliability of the vehicle lane changing decision, and further ensuring the safety of vehicle driving.

[0183] The various modules in the vehicle control device provided in the embodiments of the application can implement the method steps of any of the embodiments shown in the embodiments of the application and achieve the corresponding technical effects. For brevity, they will not be described here. Figures 4 to 7

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

[0185] The electronic device can include a processor 1201 and a memory 1202 having computer program instructions stored therein.

[0186] ​In particular, the processor 1201 can include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or can be configured to implement one or more integrated circuits that embody the embodiments of the present application.

[0187] The memory 1202 can include mass storage for data or instructions. As an example and not by way of limitation, the memory 1202 can include a hard disk drive (HDD), a floppy disk drive, flash memory, an optical disc (e.g., a compact disc (CD) or a digital versatile disc (DVD)), a solid-state drive (SSD), a USB drive, or a combination of two or more of these. Where appropriate, the memory 1202 can include removable or non-removable (or fixed) media, where appropriate. The memory 1202 can be internal or external to the integrated gateway disaster recovery device. In particular embodiments, the memory 1202 is non-volatile, solid-state memory.

[0188] The memory can include read-only memory (ROM), random-access memory (RAM), magnetic disk storage mediums, optical storage mediums, flash memory devices, electrical, optical, or other physical / tangible memory storage devices. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software that, when executed (by one or more processors), is operable to perform operations described with reference to the methods 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 can further include a communication interface 1203 and a bus 1210. As shown, the processor 1201, the memory 1202, and the communication interface 1203 are connected by the bus 1210 and complete communication with each other. Figure 12

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

[0192] ​Bus 1210 includes a hardware, software, or both that couples components of the online data traffic metering device to each other. As an example without limitation, a bus can include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand (IB) interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or another suitable bus or a combination of two or more of these. Where appropriate, bus 1210 can include one or more buses. Although the example embodiments described and illustrated herein include a particular bus, the application contemplates any suitable bus or interconnect.

[0193] In addition, in combination with the vehicle control method in the above-mentioned embodiments, the embodiments of the present application can provide a computer storage medium for implementation. The computer storage medium has computer program instructions stored thereon; the computer program instructions are executed by a processor to implement the vehicle control method provided by the embodiments of the present application.

[0194] The embodiments of the present application also provide 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 by the embodiments of the present application.

[0195] The functional blocks shown in the above structural 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 functional card, and the like. When implemented in software, the elements of the present application are program or code segments used to perform the required tasks. The program or code segments can be stored in a machine-readable medium or transmitted through a data signal carried in a carrier wave in a transmission medium or communication link. The "machine-readable medium" can include any medium capable of storing or transmitting information. Examples of the machine-readable medium 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, and the like. The code segments can be downloaded via a computer network such as the Internet, an intranet, and the like.

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

[0197] The above is merely specific implementation of the present application, and those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the foregoing method embodiments, which will not be described herein again. It should be understood that the protection scope of the present application is not limited to this, and any person skilled in the art can easily think of various equivalent modifications or replacements within the technical range disclosed in the present application, and these modifications or replacements should be covered within the protection scope of the present application.

Claims

1. A vehicle control method, characterized in that, The method includes: Obtain traffic environment information of the game participants, including a first vehicle and a second vehicle, wherein the first vehicle is traveling in the first lane and the second vehicle is traveling in the second lane. Based on the traffic environment information of the game participants, 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 are determined. The first decision information includes K first potential behaviors, and the second decision information includes L second potential behaviors. 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, construct the expected utility function corresponding to the first vehicle; The first vehicle is controlled to perform a target behavior, which is 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 are obtained by solving 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 driving in a first lane, or a second target behavior that characterizes the first vehicle driving in a second lane. The expected utility function corresponding to the first vehicle satisfies the following formula: = in, Let be the utility function of the first vehicle. Let be the first probability distribution function. This is the second probability distribution function. The third probability distribution function, It is the fourth probability distribution function; This is the first decision information for the first vehicle. Including the game outcome of each of the K×L game strategies, This is the second decision information for the second vehicle. , which is the traffic environment information of the game participants. The possible decision-making behaviors of the second vehicle. The possible decision-making behaviors of the first vehicle.

2. The method according to claim 1, characterized in that, The acquisition of traffic environment information of game participants includes: Receive a first instruction, which is an instruction triggered when the sensor information obtained by the sensors of the first vehicle meets the preset lane-changing conditions. The first instruction is used to instruct the first vehicle to perform a lane-changing action, which is an action that enables the first vehicle to switch from the currently traveling first lane to the 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, 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, the expected utility function corresponding to the first vehicle is constructed, including: Based on the first decision information of the first vehicle and the game results of each of the K×L game strategies, the utility function of the first vehicle is constructed. 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. The first probability distribution function is used to characterize the probability distribution of the game outcome of each game strategy in the K×L game strategies. Based on the first decision information of the first vehicle and the possible decision behaviors of the second vehicle, a second probability distribution function is constructed. The second probability distribution function is used to characterize the probability distribution of the second potential behavior of the second vehicle. The possible decision behaviors of the second vehicle are any one of the L second potential behaviors. Based on the traffic environment information of the game participants, a third probability distribution function is constructed, which is used to characterize the probability distribution of the possible decision-making behavior of the second vehicle. Based on the possible decision behaviors of the first vehicle, a fourth probability distribution function is constructed. The fourth probability distribution function is used to characterize the probability distribution of traffic environment information of the game participants. The possible decision behaviors of the first vehicle are 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, the expected utility function corresponding to the first vehicle is constructed.

4. The method according to claim 3, characterized in that, The construction of a second probability distribution function based on the first decision information of the first vehicle and the possible decision behaviors of the second vehicle includes: Obtain the target utility function corresponding to the second vehicle. The target utility function corresponding to the second vehicle is determined based on the simulation stochastic utility equation, the first stochastic utility distribution function, and the second stochastic 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, multiple sets of random values ​​corresponding to the possible decision behavior of the second vehicle are obtained. Each set of random values ​​includes a first random value corresponding to the simulation random utility equation, 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 set of random values ​​in a plurality of sets of random values, the objective utility function corresponding to the second vehicle is solved based on each set of random values ​​to obtain the optimal solution for each set of random values, thereby obtaining multiple optimal solutions; The second probability distribution function is obtained through simulation based on the multiple optimal solutions.

5. The method according to claim 4, characterized in that, The objective utility function corresponding to the second vehicle satisfies the following formula: in, The simulated stochastic utility equation is as follows: Let be the first random utility distribution function. This is the second random utility distribution function; This is the first decision information for the first vehicle. Including the game outcome of each of the K×L game strategies, This is the second decision information for the second vehicle. The traffic environment information of the game participants. The possible decision-making behaviors of the second vehicle. The possible decision-making behaviors of the first vehicle.

6. A vehicle control device, characterized in that, The device includes: The acquisition module is used to acquire traffic environment information of the game participants, including a first vehicle and a second vehicle, wherein the first vehicle is traveling in the first lane and the second vehicle is traveling in the second lane. The determination module is used to determine the first decision information of the first vehicle, the second decision information of the second vehicle, and the game result of each of the K×L game strategies based on the traffic environment information of the game participants. The first decision information includes K first potential behaviors, and the second decision information includes L second potential behaviors. The construction module is used to 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 result of each game strategy in the K×L game strategies; A control module is used to control the first vehicle to perform a target behavior. The target behavior is 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 are obtained by solving 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 represents the first vehicle driving in a first lane, or a second target behavior that represents the first vehicle driving in a second lane. The expected utility function corresponding to the first vehicle satisfies the following formula: = in, Let be the utility function of the first vehicle. Let be the first probability distribution function. This is the second probability distribution function. The third probability distribution function, It is the fourth probability distribution function; This is the first decision information for the first vehicle. Including the game outcome of each of the K×L game strategies, This is the second decision information for the second vehicle. , which is the traffic environment information of the game participants. The possible decision-making behaviors of the second vehicle. The possible decision-making behaviors of the first vehicle.

7. An electronic device, characterized in that, The electronic device includes: 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 1-5.

8. 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 1-5.

9. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the vehicle control method according to any one of claims 1-5.

Images