Vehicle control method, device and equipment and storage medium

Abstract

The embodiment of the invention provides a vehicle control method and device, equipment and a storage medium. The method comprises the steps of determining mutual state prediction of a target vehicle and an obstacle vehicle at a second moment at least based on a first decision behavior of the obstacle vehicle at a first moment and observation data of the target vehicle at the first moment; the observation data comprises mutual states of the target vehicle and the obstacle vehicle at a first moment and a second decision behavior of the target vehicle at a third moment, the second moment is after the first moment, and the third moment is before the first moment. And determining a fourth decision behavior of the obstacle vehicle at the second moment at least based on the mutual state prediction at the second moment and the second decision behavior. And determining at least one decision behavior of the target vehicle after the first moment at least based on the mutual state prediction at the second moment and the fourth decision behavior. And controlling the driving process of the target vehicle after the first moment through the at least one decision behavior. Therefore, the safety of the target vehicle can be improved.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to methods, devices, apparatuses, and storage media for vehicle control. Background Art

[0002] On complex urban roads, autonomous vehicles (target vehicles) inevitably interact with other traffic participants (e.g., other vehicles). In the process of interacting with other traffic participants, the autonomous vehicle and other traffic participants are two independent individuals, and there is no correlation between the two. Therefore, there are certain safety hazards in the process of controlling the autonomous vehicle. How to make the autonomous vehicle drive more safely and improve the safety performance of the vehicle is worthy of attention. Summary of the invention

[0003] In a first aspect of the present disclosure, a method for vehicle control is provided. The method may include: determining a prediction of a mutual state between a target vehicle and an obstacle vehicle at a second moment based at least on a first decision-making behavior of an obstacle vehicle at a first moment and observation data of a target vehicle at the first moment, the observation data including the mutual state between the target vehicle and the obstacle vehicle at the first moment and the second decision-making behavior of the target vehicle at a third moment, the second moment being after the first moment and the third moment being before the first moment. Determine a fourth decision-making behavior of the obstacle vehicle at the second moment based at least on the prediction of the mutual state at the second moment and the third decision-making behavior of the target vehicle at the first moment. Determine at least one decision-making behavior of the target vehicle after the first moment based at least on the prediction of the mutual state at the second moment and the fourth decision-making behavior. Control the driving process of the target vehicle after the first moment through at least one decision-making behavior.

[0004] In a second aspect of the present disclosure, a vehicle control device is provided. The device may include: a mutual state prediction module, which may be configured to determine the mutual state prediction of the target vehicle and the obstacle vehicle at the second moment based on at least the first decision-making behavior of the obstacle vehicle at the first moment and the observation data of the target vehicle at the first moment, the observation data including the mutual state of the target vehicle and the obstacle vehicle at the first moment and the second decision-making behavior of the target vehicle at the third moment, the second moment being after the first moment and the third moment being before the first moment. An obstacle vehicle decision-making behavior determination module, which may be configured to determine the fourth decision-making behavior of the obstacle vehicle at the second moment based on at least the mutual state prediction at the second moment and the third decision-making behavior of the target vehicle at the first moment. A target vehicle decision-making behavior determination module, which may be configured to determine at least one decision-making behavior of the target vehicle after the first moment based on at least the mutual state prediction at the second moment and the fourth decision-making behavior. A target vehicle control module, which may be configured to control the driving process of the target vehicle after the first moment through at least one decision-making behavior.

[0005] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit. When the instructions are executed by the at least one processing unit, the electronic device executes the method of the first aspect.

[0006] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect.

[0007] In a fifth aspect of the present disclosure, a computer program product is provided, which includes computer executable instructions, and when the computer executable instructions are executed by a processor, the method of the first aspect is implemented.

[0008] It should be understood that the content described in this section is not intended to limit the key features or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0010] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;

[0011] Figure 2 A flow chart showing a method of vehicle control according to some embodiments of the present disclosure;

[0012] Figure 3 An example diagram showing a mutual state prediction process according to some embodiments of the present disclosure;

[0013] Figure 4 A schematic structural block diagram of a vehicle control device according to some embodiments of the present disclosure is shown; and

[0014] Figure 5 A block diagram of an electronic device in which one or more embodiments of the present disclosure may be implemented is shown. DETAILED DESCRIPTION

[0015] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0016] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below.

[0017] Herein, unless explicitly stated, executing a step “in response to A” does not mean executing the step immediately after “A” but may include one or more intermediate steps.

[0018] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition, use, storage or deletion of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0019] It is understandable that before using the technical solutions disclosed in the various embodiments of the present disclosure, the types, scopes of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to relevant users and their authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations. The relevant users may include any type of right holders, such as individuals, enterprises, and groups.

[0020] For example, in response to receiving an active request from a user, a prompt message is sent to the relevant user to clearly prompt the relevant user that the operation requested to be performed will require obtaining and using the information of the relevant user, so that the relevant user can independently choose whether to provide information to software or hardware such as an electronic device, application, server or storage medium that executes the operation of the technical solution of the present disclosure based on the prompt message.

[0021] As an optional but non-limiting implementation, in response to receiving an active request from a relevant user, a prompt message is sent to the relevant user, for example, in the form of a pop-up window, in which the prompt message may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to select "agree" or "disagree" to provide information to the electronic device.

[0022] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0023] As used herein, the term "model" can learn the association between the corresponding input and output from the training data, so that after the training is completed, the corresponding output can be generated for a given input. The generation of the model can be based on machine learning technology. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs by using multi-layer processing units. A neural network model is an example of a model based on deep learning. In this article, "model" may also be referred to as "machine learning model", "learning model", "machine learning network" or "learning network", and these terms are used interchangeably in this article.

[0024] Figure 1 A schematic diagram of an environment 100 in which embodiments of the present disclosure can be implemented is shown. The environment 100 may include a target vehicle 110 and an obstacle vehicle 120. The target vehicle 110 refers to a vehicle of interest whose behavior is to be controlled, which may be a vehicle with an automatic driving function or an assisted driving function. The obstacle vehicle 120 refers to any vehicle that may hinder the normal driving of the vehicle or affect the safety of the vehicle's passage relative to the target vehicle 110. Figure 1 One obstacle vehicle 120 is shown in the figure, but in actual application there may be multiple obstacle vehicles. In such a case, the embodiments of the present disclosure can still be similarly applied.

[0025] The target vehicle 110 can rely on the vehicle control device 130 to drive automatically. The vehicle control device 130 can be the vehicle computer of the target vehicle, or it can be a server-side device. The server-side device can be an independent physical server, or it can be a server cluster or distributed system composed of multiple physical servers, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks, and big data and artificial intelligence platforms. The server-side device can include, for example, a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, and the like.

[0026] The vehicle control device 130 relies on external data to determine the decision-making behavior of the target vehicle 110. The external data may include sensing results from the target vehicle 110 and / or an external data source. The target vehicle 110 is usually equipped with a collection device for capturing elements in the physical environment, a sensing device for sensing objects in the physical environment, etc. (not shown in the figure). For example, the collection device or the sensing device may include an optical camera that can capture images in the physical environment, a laser radar that captures point cloud data, etc. The external data source may be embodied as a device for collecting sensing data in the environment in which the vehicle is located, for example, a roadside camera, a roadside laser radar, and other sensors.

[0027] It should be understood that the structure and function of the various elements in the environment 100 are described for exemplary purposes only and do not imply any limitation on the scope of the present disclosure.

[0028] For the control of autonomous vehicles, it is usually necessary to use the current speed of the obstacle vehicle to linearly predict the movement trend of the obstacle vehicle in the next few seconds to obtain the predicted trajectory of the obstacle vehicle. The predicted trajectory is used to determine whether there is a risk of collision between the target vehicle (self-vehicle) and the obstacle vehicle in the future. Once the predicted trajectory of the obstacle vehicle intersects with the driving trajectory of the target vehicle, the braking control of the target vehicle will be triggered.

[0029] In the above control process, the target vehicle and the obstacle vehicle are usually regarded as two independent individuals with no correlation with each other. However, in actual scenarios, the target vehicle and the obstacle vehicle change dynamically during the interaction process as the states of the two vehicles and the environmental interference change. Therefore, treating the target vehicle and the obstacle vehicle as two independent individuals cannot reflect the actual interaction process, which may lead to misjudgment of the target vehicle. For example, if the target vehicle adopts an overly conservative strategy, it will cause more sudden braking and rear-end collision problems, which will also reduce the overall driving efficiency of the target vehicle.

[0030] In an embodiment of the present disclosure, an improved scheme for target vehicle control is proposed. The scheme points out that: based on at least the first decision-making behavior of the obstacle vehicle at the first moment and the observation data of the target vehicle at the first moment, the mutual state prediction of the target vehicle and the obstacle vehicle at the second moment is determined; the observation data includes the mutual state of the target vehicle and the obstacle vehicle at the first moment and the second decision-making behavior of the target vehicle at the third moment, the second moment is after the first moment, and the third moment is before the first moment. Based on at least the mutual state prediction at the second moment and the third decision-making behavior of the target vehicle at the first moment, the fourth decision-making behavior of the obstacle vehicle at the second moment is determined. Based on at least the mutual state prediction at the second moment and the fourth decision-making behavior, at least one decision-making behavior of the target vehicle after the first moment is determined. The driving process of the target vehicle after the first moment is controlled by at least one decision-making behavior.

[0031] Through the above process, the target vehicle and the obstacle vehicle are regarded as a whole. Based on the prediction of the mutual state between the target vehicle and the obstacle vehicle, the future dynamic relationship between the two can be foreseen in advance, thereby obtaining a random optimal control model for the interactive decision of the two vehicles. Based on this prediction, the vehicle control device can optimize the control strategy of the target vehicle so that it can more accurately respond to possible dangerous situations during the subsequent driving process. Therefore, through the prediction of the mutual state, the target vehicle can more effectively avoid the obstacle vehicle, thereby improving the overall driving safety and the rationality of the decision.

[0032] Figure 2 An example process 200 of a method of vehicle control according to some embodiments of the present disclosure is shown. For ease of discussion, reference will be made to Figure 1 In the application environment 110 , the vehicle control device 130 may be used to control the target vehicle.

[0033] In box 201, the vehicle control device 130 determines the prediction of the mutual state of the target vehicle and the obstacle vehicle at the second moment based at least on the first decision-making behavior of the obstacle vehicle at the first moment and the observation data of the target vehicle at the first moment; the observation data includes the mutual state of the target vehicle and the obstacle vehicle at the first moment and the second decision-making behavior of the target vehicle at the third moment, the second moment is after the first moment, and the third moment is before the first moment.

[0034] The vehicle control device 130 regards the target vehicle 110 and the obstacle vehicle 120 as a whole. The control strategy for the target vehicle 110 is determined by comprehensively considering the mutual influence between the decision-making behaviors of the target vehicle 110 and the obstacle vehicle 120, as well as the random interference caused by factors such as sensor errors, network delays, and environmental interference.

[0035] The first decision behavior of the obstacle vehicle 120 may correspond to the control instruction of the obstacle vehicle 120. The vehicle control device 130 cannot obtain the first decision behavior of the obstacle vehicle 120, but needs to be determined by using the observation data and the kinematic model of the obstacle vehicle. Taking the current moment as the first moment as an example, the observation data of the first moment can be expressed as H k .

[0036] The first moment observation data H k The mutual state of the target vehicle 110 and the obstacle vehicle 120 at the first moment can be represented by x k The mutual state x at the first moment k is based on the first state of the target vehicle 110 and the second state of the obstacle vehicle 120 Determined, mutual state x k It can be expressed as Can be represented as a vector dimension.

[0037] First state of target vehicle 110 and the second state of the obstacle vehicle 120 The dimensions are the same. In the first state For example, the first state It can indicate the position, speed, direction and other dimensions of the target vehicle 110. Correspondingly, the mutual state x between the target vehicle 110 and the obstacle vehicle 120 at the first moment k The relative position, relative speed, relative direction, etc. of the target vehicle 110 and the obstacle vehicle 120 can also be indicated.

[0038] The first moment observation data H k It may also include a second decision-making behavior of the target vehicle 110 at a third moment, where the third moment is a moment before the first moment. The second decision-making behavior can be expressed as According to the observation data H at the first moment k , the second decision behavior of the target vehicle 110 at the third moment And the observation data history H k-1 , we can get the first decision behavior of the obstacle vehicle 120 at the first moment It can be expressed as a vector dimension. In summary, the observation data H at the first moment k It can be expressed as

[0039] At least based on the first decision-making behavior of the obstacle vehicle 120 at the first moment and the observation data H of the target vehicle 110 at the first moment k , and the decision behavior of the target vehicle 110 at the first moment The mutual state prediction of the target vehicle 110 and the obstacle vehicle 120 at the second moment can be determined. The mutual state prediction at the second moment can be expressed as x k+1 The first decision-making behavior of the obstacle vehicle 120 at the first moment It can be determined during the calculation process at the second moment.

[0040] The mutual state prediction at the second moment may include the state prediction of the target vehicle 110 and the state prediction of the obstacle vehicle 120, and thus, the mutual state prediction can be obtained based on the state prediction of the target vehicle 110 and the state prediction of the obstacle vehicle 120. The specific prediction process of the mutual state prediction at the second moment will be described in detail later. Through the above process, the target vehicle 110 and the obstacle vehicle 120 are taken as a whole, and the states of the two vehicles at the current moment jointly affect the states of the two vehicles at the next moment.

[0041] In block 202 , the vehicle control device 130 determines a fourth decision behavior of the obstacle vehicle 120 at the second moment based on at least the mutual state prediction at the second moment and the third decision behavior of the target vehicle at the first moment.

[0042] The vehicle control device 130 uses the mutual state prediction of the target vehicle 110 and the obstacle vehicle 120 at the second moment and the third decision behavior of the target vehicle 110 at the first moment. Combined with the previous observation data, the prediction of the behavior of the obstacle vehicle 120 can be updated through the Bayesian method. Specifically, this process involves the update process of the probability distribution of the behavior parameters of the obstacle vehicle 120 in different behavior modes.

[0043] By predicting the behavior of the obstructing vehicle 120, the possibility of different behavior modes can be determined. That is, when the behavior mode and parameters of the obstructing vehicle 120 are known, the probability distribution of the decision-making behavior of the obstructing vehicle 120 is updated. Based on the updated behavior mode and behavior parameters of the obstructing vehicle 120, the fourth decision-making behavior of the obstructing vehicle 120 at the second moment is calculated. The fourth decision-making behavior is obtained by evaluating the probability distribution of the possible behaviors of the obstructing vehicle 120, and is used to predict the future actions of the obstructing vehicle 120, so that the target vehicle 110 can make an appropriate response when making a decision.

[0044] The above process combines the observation data of the target vehicle 110, the current and predicted states of the obstacle vehicle 120, and the control decision of the target vehicle 110, thereby gradually deducing the possible behavior of the obstacle vehicle 120 at future moments.

[0045] In block 203 , the vehicle control device 130 determines at least one decision behavior of the target vehicle 110 after the first moment based on at least the mutual state prediction at the second moment and the fourth decision behavior.

[0046] The vehicle control device 130 can determine the cost of each possible decision behavior of the target vehicle 110 based on the current state prediction and the decision behavior of the obstacle vehicle 120 at the third moment. This includes the direct cost of making different decisions for the target vehicle 110 in the current state (such as the cost in terms of safety, efficiency, etc.) and the expected cost that may be generated in the future.

[0047] By evaluating the cost of each possible decision behavior, a decision behavior sequence that minimizes the overall cost is selected. The overall cost here includes the direct cost at the current moment and the expected cost at the future moment. The expected cost is calculated based on the current state and the cost of the predicted future behavior of the obstacle vehicle 120, taking into account possible state changes and corresponding costs in the future.

[0048] The optimal decision behavior sequence that the target vehicle 110 should take in the entire decision-making process is determined by a dynamic programming method. This process considers the cost of each possible decision behavior and selects the decision sequence that minimizes the total cost, thereby optimizing the control strategy of the target vehicle 110.

[0049] In box 204, the vehicle control device 130 can control the driving of the target vehicle 110 after the first moment through at least one decision-making behavior. In the process of controlling the target vehicle 110, the vehicle control device 130 adopts a prediction method that regards the target vehicle 110 and the obstacle vehicle 120 as a whole. First, by analyzing the observation data and historical data of the target vehicle 110 and the obstacle vehicle 120 at a certain moment, the vehicle control device 130 predicts the behavior of the obstacle vehicle 120 at a future moment based on these data. This prediction involves the decision-making behavior of the obstacle vehicle 120 at different time nodes, thereby providing a targeted control strategy for the target vehicle 110.

[0050] The following is a detailed description of the process of predicting the mutual state of the target vehicle 110 and the obstacle vehicle 120 at the second moment. The vehicle control device 130 determines the state change trend between the target vehicle 110 and the obstacle vehicle 120 based on the mutual state of the target vehicle 110 and the obstacle vehicle 120 at the first moment. Determine the first influence degree of the first decision behavior on the mutual state. Determine the second influence degree of the third decision behavior on the mutual state. Determine the mutual state prediction of the target vehicle 110 and the obstacle vehicle 120 at the second moment based on at least the state change trend, the first influence degree and the second influence degree.

[0051] The mutual state prediction of the target vehicle 110 and the obstacle vehicle 120 at the second moment can be expressed as follows:

[0052]

[0053] Figure 3 An example process 300 of mutual state prediction according to some embodiments of the present disclosure is shown. k The relative state of the target vehicle 110 and the obstacle vehicle 120 at the first moment may be indicated. k+1 The mutual state prediction of the target vehicle 110 and the obstacle vehicle 120 at the second time may be indicated. The second time is after the first time.

[0054] Combination Figure 3 As shown, the mutual state prediction 301 at the second moment is represented by x k+1 The time interval 305 between the first moment and the second moment can be expressed as 1 / z. The mutual state prediction x at the second moment k+1 After a time interval of 1 / z, the mutual state at the previous moment will return. By calculating the mutual state at the previous moment, a state change trend 306 can be obtained. Thus, the state change trend 306 between the target vehicle 110 and the obstacle vehicle 120 can be continuously updated in an iterative manner.

[0055] The state change trend 306 can be expressed as The state change trend can be determined by the joint kinematics model of the target vehicle 110 and the obstacle vehicle 120. The determination process of the joint kinematics model will be described in detail later.

[0056] The decision behavior of the target vehicle 110 at the first moment can be indicated. The decision behavior of the target vehicle 110 at the first moment can be determined by the kinematic model of the target vehicle 110. The kinematic model of the target vehicle 110 can adopt a bicycle model. The bicycle model can be linearly expressed as Can be used to represent the dimensions of matrices and vectors.

[0057] By using the control input matrix 302 of the obstacle vehicle 120 , a first degree of influence of the first decision-making behavior on the mutual state can be obtained. It can be indicated that the decision behavior of the vehicle 120 at the obstacle is In the case of , the second degree of influence on the mutual state. Figure 3 As shown, the control input matrix 302 of the obstacle vehicle 120 can be expressed as B o (.), Its parameters are all time-varying, and their magnitudes depend on their mutual states. Can represent the dimensions of a matrix.

[0058] Using the control input matrix 303 of the target vehicle 110 , the first degree of influence of the third decision-making behavior on the mutual state can be obtained. The third decision behavior of the target vehicle 110 may be indicated as The first degree of influence on the mutual state in the case of Figure 3 As shown, the control input matrix 303 of the target vehicle 110 can be expressed as B e (.), Its parameters are all time-varying, and their magnitudes depend on their mutual states. Can represent the dimensions of a matrix.

[0059] In addition, random interference 304 is included. Figure 3 As shown, random interference 304 can be expressed as d k , random interference 304 can be represented as random interference caused by factors such as sensor error, network delay, environmental interference, model error, etc. Here, it is assumed that the random interference d k It obeys Gaussian distribution, with mean 0 and variance ∑ d , the parameters of random interference are estimated through statistical numbers.

[0060] Through the above process, it is possible to capture the complex dynamic interaction between the target vehicle 110 and the obstacle vehicle 120. Through this prediction, the decision-making behavior of the vehicle can be updated and adjusted in real time during the vehicle's driving process, ensuring that the target vehicle 110 can make a reasonable response and avoid potential dangers.

[0061] The following is a detailed description of the process of determining the state change trend between the target vehicle 110 and the obstacle vehicle 120. The vehicle control device 130 determines the first state change trend corresponding to the target vehicle 110 based on the first state of the target vehicle 110 at the first moment and using the target vehicle decision behavior model corresponding to the target vehicle 110, wherein the first state is a part of the mutual state. Based on the second state of the obstacle vehicle 120 at the first moment and using the obstacle vehicle decision behavior model corresponding to the obstacle vehicle, the second state change trend corresponding to the obstacle vehicle 120 is determined, wherein the second state is a part of the mutual state. Based on the first state change trend and the second state change trend, the state change trend between the target vehicle 110 and the obstacle vehicle 120 is determined.

[0062] As mentioned above, the target vehicle decision behavior model corresponding to the target vehicle 110 can be a bicycle model, which can be linearly expressed as In the target vehicle decision behavior model, A e It can correspond to the kinematic model matrix. Based on the first state of the target vehicle 110 at the first moment By using the target vehicle decision behavior model, a first state change trend corresponding to the target vehicle 110 may be determined.

[0063] The kinematic model of the obstacle vehicle can be expressed as The kinematic model is usually a nonlinear function obtained by fitting a neural network based on sensor data (such as lidar or visual data). By using the obstacle vehicle decision behavior model, the second state change trend corresponding to the obstacle vehicle 120 can be determined.

[0064] The state change trend between the target vehicle 110 and the obstacle vehicle 120 corresponds to the first state of the target vehicle 110 at the first moment. and the second state of the obstacle vehicle 120 at the first moment The decision behavior models of the target vehicle 110 and the obstacle vehicle 120 are used to determine their respective state updates, and then the updated results are integrated into a unified expression f(x k ), the state change trend between the target vehicle 110 and the obstacle vehicle 120 can be obtained.

[0065] By integrating the decision-making behavior models of the target vehicle 110 and the obstacle vehicle 120, the dynamic behaviors of the two and their mutual influence can be more comprehensively described. This unified dynamic modeling method makes predictions and decisions more accurate and consistent, can better reflect the interactive relationship between the two during actual driving, and provides a solid foundation for formulating more accurate control strategies.

[0066] The following is a detailed description of the process of determining the fourth decision behavior corresponding to the obstacle vehicle 120 at the second moment. The fourth decision behavior at the second moment is completed on the basis of the first decision behavior of the obstacle vehicle 120 at the first moment and the mutual state prediction of the target vehicle 110 and the obstacle vehicle 120 at the second moment. In other words, the entire determination of the decision behavior of the obstacle vehicle 120 is an iterative process. The principle of each iteration is the same. Taking the fourth decision behavior at the second moment as an example, the entire iterative process is explained. The vehicle control device 130 determines the probability of at least one behavior parameter of the obstacle vehicle 120 based on the observation data at the first moment and the mutual state prediction. Based on the observation data at the first moment and the third decision behavior of the target vehicle 110, the probability of at least one behavior pattern of the obstacle vehicle 120 is determined. Based on the probability of at least one behavior parameter and the probability of at least one behavior pattern, the fourth decision behavior of the obstacle vehicle 120 at the second moment is determined.

[0067] The vehicle control device 130 is based on the observation data H at the first moment. k And historical observation data H k-1, the first behavior parameter θ and the first behavior mode M of the obstacle vehicle 120 can be determined by using the prior distribution. The prior distribution can indicate the behavior parameter θ of the obstacle vehicle 120 under the behavior mode M based on the observed data. M , it can be inferred that the first decision-making behavior of the obstacle vehicle 120 at the first moment

[0068] With the observation data H k The update of the mutual state prediction of the target vehicle 110 and the obstacle vehicle 120 at the second moment and the update of the decision-making behavior of the target vehicle 110, and the observation data will also be updated to H k+1 , that is, the observed data H k+1 It can be expressed as

[0069] Based on the updated observation data, the probability of at least one behavior parameter of the obstructing vehicle 120 and the probability of at least one behavior pattern of the obstructing vehicle 120 may be determined. Exemplarily, the behavior pattern may include a conservative behavior pattern, a normal behavior pattern, an adventurous behavior pattern, etc. The behavior parameter may include turning left, turning right, accelerating, decelerating, changing lanes, etc.

[0070] Based on the above process, the fourth decision behavior of the obstructing vehicle 120 may be determined based on the probability of at least one behavior parameter of the obstructing vehicle 120 and the probability of at least one behavior pattern of the obstructing vehicle 120 .

[0071] The following describes the determination process of the probability of at least one behavior parameter and the probability of at least one behavior pattern in turn. First, the determination process of the probability of the behavior parameter is described. The first decision behavior of the obstacle vehicle 120 at the first moment is determined based on the first behavior parameter and the first behavior pattern of the obstacle vehicle 120. The obstacle vehicle 120 may correspond to multiple behavior parameters, and the determination process of the probability of each behavior parameter in the multiple behavior parameters is the same. The following takes the determination process of the probability of a given behavior parameter in the multiple behavior parameters as an example. The vehicle control device 130 determines the first probability of the predicted mutual state between the target vehicle 110 and the obstacle vehicle 120 at the second moment based on the first behavior parameter, the first behavior pattern, the observation data at the first moment, and the third decision behavior. Obtain the prior probability of the first behavior parameter of the obstacle vehicle 120. Based on the first behavior parameter, the first behavior pattern, and the observation data at the first moment, determine the second probability of the predicted mutual state between the target vehicle 110 and the obstacle vehicle 120 at the second moment. Based on the first probability, the prior probability of the first behavior parameter, and the second probability, determine the probability of the given behavior parameter at the second moment.

[0072] The probability of a given behavior parameter can be expressed as follows:

[0073]

[0074] p(θ M′ |H k+1 ; M) can be expressed as the updated obstacle vehicle 120 corresponding to the given behavior parameter θ M′ That is, based on the new observation data H k+1 and the first behavior mode M, determining that the obstacle vehicle 120 has a given behavior parameter θ M′ probability.

[0075] It can be expressed as the first behavior parameter θ of the obstacle vehicle 120 M , the first behavior pattern M, the first moment observation data H k and the third decision behavior of the target vehicle 110 In the case of k+1 The first probability.

[0076] p(θ M |H k ; M) can be expressed as the observation data H based on the first moment k In the case of the first behavior mode M, the first behavior parameter θ of the obstacle vehicle 120 is determined M The prior probability of .

[0077] is a normalization factor, which can be expressed as: and the first moment observation data H k In the case of k+1 The normalization factor usually integrates all possible behavior parameters.

[0078] Through the first probability, the first behavior parameter θ M The prior probability and the second probability can be used to obtain the updated given behavior parameter θ M′ probability.

[0079] The following will continue to introduce the process of determining the probability of the behavior pattern. The obstacle vehicle 120 can correspond to multiple behavior patterns, and the process of determining the probability of each behavior pattern is the same. The following takes the process of determining the probability of a given behavior pattern among multiple behavior patterns as an example. The vehicle control device 130 determines the third probability of the predicted mutual state between the target vehicle 110 and the obstacle vehicle 120 at the second moment based on the third decision behavior, the first behavior pattern and the observation data at the first moment. Obtain the prior probability of the first behavior pattern of the obstacle vehicle 120. Based on the third decision behavior of the target vehicle 110 and the observation data at the first moment, determine the fourth probability of the predicted mutual state between the target vehicle 110 and the obstacle vehicle 120 at the second moment. Based on the third probability, the prior probability of the first behavior pattern and the fourth probability, determine the probability of the given behavior pattern at the second moment.

[0080] The probability of a given behavior pattern can be expressed as follows:

[0081]

[0082] p(M′|H k+1 ) can represent the behavior pattern M' of the obstacle vehicle 120 in the new observation data H k+1 That is, based on the new observation data H k+1 , determine the probability that the obstacle vehicle 120 has a given behavior pattern M′.

[0083] It can be expressed based on the observation data H at the first moment k , the first behavior mode M and the third decision behavior of the target vehicle 110 In the case of k+1 This represents the change in the state of the obstacle vehicle 120 that may be caused by the behavior of the target vehicle 110 under the first behavior mode M.

[0084] p(M|H k ) can be expressed based on the observation data H at the first moment k , the prior probability that the obstacle vehicle 120 is in the first behavior mode M.

[0085] is a normalization factor, which can be expressed as the observed data H based on the first moment k and the third decision behavior of the target vehicle 110 Determine the new observation data x k+1 The fourth probability.

[0086] The updated probability of the given behavior pattern M′ can be obtained through the third probability, the prior probability of the first behavior pattern M and the fourth probability.

[0087] After determining the probability of at least one behavior parameter and the probability of at least one behavior pattern, the vehicle control device 130 may determine the probability distribution of at least one behavior parameter and at least one behavior pattern based on the probability of at least one behavior parameter and at least one behavior pattern. Based on the probability distribution, the vehicle control device 130 may determine the fourth decision behavior of the obstacle vehicle 120.

[0088] Based on the probability of at least one behavior parameter and the probability of at least one behavior pattern, the joint distribution of a given behavior parameter and a given behavior pattern can be obtained. The joint distribution can be expressed as follows:

[0089] F k ' +1 = p(θ M′ |H k+1 ;M)p(M′|H k+1 ) (4)

[0090] After updating the probability of a given behavior pattern and a given behavior parameter of the obstacle vehicle 120, it can be obtained that the obstacle vehicle 120 at the second moment based on the observation data H k+1 , given behavior parameter θ under given behavior mode M' M′ This probability reflects the probability that the obstacle vehicle 120 takes a given behavior θ under a given behavior mode M'. M′ possibility.

[0091] Taking into account the given behavior mode M', all behavior parameters of the obstacle vehicle 120 can be expressed as follows:

[0092] F k+1 ={F k ' +1 (θ M′ ,M′)|θ M′ ∈θ M ,M′∈M} (5)

[0093] By combining all possible behavior patterns and behavior parameters, a complete probability distribution can be constructed. The probability distribution describes all possible behaviors of the obstacle vehicle 120 under different behavior patterns and behavior parameters. This means that the vehicle control device 130 has obtained a comprehensive behavior prediction distribution through all possible behavior patterns and behavior parameters of the obstacle vehicle 120.

[0094] Based on the complete probability distribution, the fourth decision behavior of the obstacle vehicle 120 can be obtained. The determination of the fourth decision behavior can be expressed as follows:

[0095]

[0096] It can represent the behavior corresponding to the ith behavior parameter under the behavior mode M. can represent the probability of the behavior. That is, It can be the behavior with the highest behavior parameter probability determined based on the expression (5) when the behavior pattern probability is the highest.

[0097] After determining the fourth decision behavior of the obstacle vehicle 120 at the second moment, the vehicle control device 130 may determine the first cost based on the mutual state of the target vehicle 110 and the obstacle vehicle 120 at the first moment and the third decision behavior of the target vehicle 110. Determine the second cost based on the prediction of the mutual state of the target vehicle 110 and the obstacle vehicle 120 at the second moment and the fourth decision behavior. Determine at least one decision behavior of the target vehicle 110 after the first moment based on the first cost and the second cost. The at least one decision behavior may be expressed as follows:

[0098]

[0099] Based on the initial state According to the mutual state x between the target vehicle 110 and the obstacle vehicle 120 at the first moment k And the probability distribution F obtained by calculating formula (6) k+1 And the probability distribution F determined in the past k . Combined with the cost function The first price The second cost E[V k+1 (x k+1 ,F k+1 )], and the final state x N The termination cost R T (x N ), we can get every possible decision behavior The cost of the known terminal state is: V N (x N ,F N )=R T (x N ). That is, when the final state x is reached N When the cost is directly derived from the objective function R T (x N ) is determined by the final state x N That is, the mutual state of the target vehicle 110 and the obstacle vehicle 120 at the end time, F N In the final state x N , the behavior pattern of the obstacle vehicle 120 and the probability distribution of the behavior parameters.

[0100] By minimizing the cost function, the vehicle control device 130 can determine the optimal decision behavior sequence that minimizes the overall decision cost. The optimal decision behavior sequence can be expressed as:

[0101]

[0102] The first cost and the second cost can be determined based on multiple factors, for example, they can be related to the distance between the target vehicle 110 and the obstacle vehicle 120, the road boundary, the dangerous area, etc. The closer the distance, the higher the cost. In addition, it can also be related to the continuity and smoothness of the path and speed. If the path is discontinuous or the speed changes dramatically, the efficiency cost will increase.

[0103] The first cost can indicate the decision-making behavior in the current state. The contemporary value The second cost may indicate the mutual state prediction x based on the second time instant. k+1 The probability distribution F is determined by calculating formula (6) k+1 The expected future cost under the current situation is a comprehensive consideration of all possible future states, including the expected cost of future safety, efficiency and other factors. By considering the expected future cost, it can ensure that the current decision not only minimizes the immediate cost, but also optimizes the overall cost in the future.

[0104] Through the above process, based on the prediction of the mutual state of the target vehicle 110 and the obstacle vehicle 120, the behavior pattern of the obstacle vehicle 120 and the joint probability distribution of the behavior parameters, the vehicle control device 130 can predict the future costs that may be generated under different decision behavior sequences. By minimizing the expected future costs, the vehicle control device 130 can select an optimal decision behavior sequence, thereby realizing intelligent control of the target vehicle 110 in a dynamic and complex driving environment. This decision-making mechanism helps to improve the safety of the target vehicle 110 and the rationality of decision-making, especially when facing complex traffic scenes, it can more effectively avoid potential risks.

[0105] Figure 4 A schematic structural block diagram of a vehicle control apparatus 400 according to some embodiments of the present disclosure is shown. The apparatus 400 may be implemented in or included in the vehicle control device 130, for example. Each module / component in the apparatus 400 may be implemented by hardware, software, firmware, or any combination thereof.

[0106] As shown in the figure, the device 400 includes a mutual state prediction module 401, which is configured to determine the mutual state prediction of the target vehicle and the obstacle vehicle at the second moment based on at least the first decision-making behavior of the obstacle vehicle at the first moment and the observation data of the target vehicle 110 at the first moment, the observation data including the mutual state of the target vehicle and the obstacle vehicle at the first moment and the second decision-making behavior of the target vehicle at the third moment, the second moment is after the first moment, and the third moment is before the first moment. The obstacle vehicle decision-making behavior determination module 402 is configured to determine the fourth decision-making behavior of the obstacle vehicle at the second moment based on at least the mutual state prediction at the second moment and the third decision-making behavior of the target vehicle at the first moment. The target vehicle decision-making behavior determination module 403 is configured to determine at least one decision-making behavior of the target vehicle after the first moment based on at least the mutual state prediction at the second moment and the fourth decision-making behavior. The target vehicle control module 404 is configured to control the driving process of the target vehicle after the first moment through at least one decision-making behavior.

[0107] In some embodiments of the present disclosure, the mutual state prediction module 401 may be specifically configured to: determine a state change trend between the target vehicle and the obstacle vehicle based on the mutual state of the target vehicle and the obstacle vehicle at the first moment; determine a first degree of influence of the first decision behavior on the mutual state; determine a second degree of influence of the third decision behavior on the mutual state; and determine a mutual state prediction of the target vehicle and the obstacle vehicle at the second moment based at least on the state change trend, the first degree of influence, and the second degree of influence.

[0108] In some embodiments of the present disclosure, the mutual state prediction module 401 may also be specifically configured as follows: based on the first state of the target vehicle at the first moment, using the target vehicle decision behavior model corresponding to the target vehicle, determine the first state change trend corresponding to the target vehicle, the first state is part of the mutual state. Based on the second state of the obstacle vehicle at the first moment, using the obstacle vehicle decision behavior model corresponding to the obstacle vehicle, determine the second state change trend corresponding to the obstacle vehicle, the second state is part of the mutual state. Based on the first state change trend and the second state change trend, determine the state change trend between the target vehicle and the obstacle vehicle.

[0109] In some embodiments of the present disclosure, the obstructing vehicle decision behavior determination module 402 may be configured to: determine the probability of at least one behavior parameter of the obstructing vehicle based on the observation data at the first moment and the mutual state prediction at the second moment. Determine the probability of at least one behavior pattern of the obstructing vehicle based on the observation data at the first moment and the third decision behavior of the target vehicle. Determine the fourth decision behavior of the obstructing vehicle at the second moment based on the probability of at least one behavior parameter and the probability of at least one behavior pattern.

[0110] In some embodiments of the present disclosure, the first decision behavior of the obstructing vehicle is determined based on the first behavior parameter and the first behavior pattern of the obstructing vehicle, and based on this, the obstructing vehicle decision behavior determination module 402 can also be configured to: for a given behavior parameter in at least one behavior parameter, based on the first behavior parameter, the first behavior pattern, the observation data at the first moment, and the third decision behavior, determine the first probability of the predicted mutual state between the target vehicle and the obstructing vehicle at the second moment. Obtain the prior probability of the first behavior parameter of the obstructing vehicle. Based on the first behavior parameter, the first behavior pattern, and the observation data at the first moment, determine the second probability of the predicted mutual state between the target vehicle and the obstructing vehicle at the second moment. Based on the first probability, the prior probability of the first behavior parameter, and the second probability, determine the probability of the given behavior parameter at the second moment.

[0111] In some embodiments of the present disclosure, the first decision behavior of the obstructing vehicle is determined based on the first behavior parameter and the first behavior pattern of the obstructing vehicle, and based on this, the obstructing vehicle decision behavior determination module 402 can also be configured to: for a given behavior pattern in at least one behavior pattern, determine a third probability of the predicted mutual state between the target vehicle and the obstructing vehicle at the second moment based on the third decision behavior, the first behavior pattern and the observation data at the first moment. Obtain the prior probability of the first behavior pattern of the obstructing vehicle. Determine the fourth probability of the predicted mutual state between the target vehicle and the obstructing vehicle at the second moment based on the third decision behavior of the target vehicle and the observation data at the first moment. Determine the probability of the given behavior pattern at the second moment based on the third probability, the prior probability of the first behavior pattern and the fourth probability.

[0112] In some embodiments of the present disclosure, the obstructing vehicle decision behavior determination module 402 may also be configured to: determine the probability distribution of at least one behavior parameter and at least one behavior pattern based on the probability of at least one behavior parameter and the probability of at least one behavior pattern, and determine the fourth decision behavior of the obstructing vehicle based on the probability distribution.

[0113] In some embodiments of the present disclosure, the fourth decision behavior of the obstacle vehicle is determined based on the probability of at least one behavior parameter corresponding to the obstacle vehicle and the probability of at least one behavior pattern, and based on this, the target vehicle decision behavior determination module 403 can be configured to: determine the first cost based on the mutual state of the target vehicle and the obstacle vehicle at the first moment and the third decision behavior of the target vehicle. Determine the second cost based on the prediction of the mutual state of the target vehicle and the obstacle vehicle at the second moment, the probability of at least one behavior parameter corresponding to the obstacle vehicle and the probability of at least one behavior pattern. Determine at least one decision behavior of the target vehicle after the first moment based on the first cost and the second cost.

[0114] Figure 51 shows a block diagram of an electronic device 500 in which one or more embodiments of the present disclosure may be implemented. It should be understood that Figure 5 The electronic device 500 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. Figure 5 The electronic device 500 shown may include or be implemented as Figure 1 The vehicle control device 130, or Figure 4 Device 400.

[0115] like Figure 5 As shown, the electronic device 500 is in the form of a general electronic device. The components of the electronic device 500 may include, but are not limited to, one or more processors or processing units 510, a memory 520, a storage device 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560. The processing unit 510 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 520. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 500.

[0116] The electronic device 500 typically includes a plurality of computer storage media. Such media may be any accessible media that is accessible to the electronic device 500, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 520 may be a volatile memory (e.g., registers, caches, random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 530 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data and may be accessed within the electronic device 500.

[0117] The electronic device 500 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 5 As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. The memory 520 may include a computer program product 525 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.

[0118] The communication unit 540 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 500 can be implemented in a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 500 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0119] The input device 550 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 560 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 500 may also communicate with one or more external devices (not shown) through the communication unit 540 as needed, such as a storage device, a display device, etc., communicate with one or more devices that allow a user to interact with the electronic device 500, or communicate with any device that allows the electronic device 500 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0120] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0121] According to an exemplary implementation of the present disclosure, a computer program product or a computer program is provided, the computer program product or the computer program including computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes Figure 2 The methods provided in the various optional methods are therefore not described in detail here.

[0122] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0123] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0124] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0125] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0126] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.

Claims

1. A method for controlling a vehicle, comprising: Determine a prediction of a mutual state between the target vehicle and the obstacle vehicle at a second moment based at least on a first decision-making behavior of the obstacle vehicle at a first moment and observation data of the target vehicle at the first moment; the observation data includes the mutual state between the target vehicle and the obstacle vehicle at the first moment and a second decision-making behavior of the target vehicle at a third moment, the second moment being after the first moment and the third moment being before the first moment; Determining a fourth decision-making behavior of the obstacle vehicle at the second moment based at least on the mutual state prediction at the second moment and the third decision-making behavior of the target vehicle at the first moment; Determining at least one decision-making behavior of the target vehicle after the first moment based at least on the mutual state prediction at the second moment and the fourth decision-making behavior; as well as The driving process of the target vehicle after the first time is controlled by the at least one decision-making action.

2. The method according to claim 1, wherein determining the mutual state prediction of the target vehicle and the obstacle vehicle at the second moment comprises: Determining a state change trend between the target vehicle and the obstacle vehicle based on the mutual state between the target vehicle and the obstacle vehicle at the first moment; determining a first degree of influence of the first decision-making behavior on the mutual state; determining a second degree of influence of the third decision-making behavior on the mutual state; as well as Based at least on the state change trend, the first influence degree and the second influence degree, a mutual state prediction of the target vehicle and the obstacle vehicle at the second moment is determined.

3. The method according to claim 2, wherein determining the state change trend between the target vehicle and the obstacle vehicle comprises: Based on a first state of the target vehicle at the first moment, using a target vehicle decision behavior model corresponding to the target vehicle, determining a first state change trend corresponding to the target vehicle, the first state being a part of the mutual state; Based on the second state of the obstacle vehicle at the first moment, using the obstacle vehicle decision behavior model corresponding to the obstacle vehicle, determining a second state change trend corresponding to the obstacle vehicle, wherein the second state is a part of the mutual state; as well as Based on the first state change trend and the second state change trend, a state change trend between the target vehicle and the obstacle vehicle is determined.

4. The method according to claim 1, wherein determining the fourth decision behavior of the obstacle vehicle at the second moment comprises: determining a probability of at least one behavior parameter of the obstructing vehicle based on the observation data at the first moment and the mutual state prediction at the second moment; Determining a probability of at least one behavior pattern of the obstacle vehicle based on the observation data at the first moment and the third decision-making behavior; as well as Based on the probability of the at least one behavior parameter and the probability of the at least one behavior pattern, a fourth decision-making behavior of the obstacle vehicle at the second moment is determined.

5. The method according to claim 4, wherein the first decision behavior of the obstacle vehicle is determined based on a first behavior parameter and a first behavior pattern of the obstacle vehicle, and determining the probability of the at least one behavior parameter of the obstacle vehicle comprises: For a given behavior parameter of the at least one behavior parameter, Determine a first probability of a predicted mutual state between the target vehicle and the obstacle vehicle at a second moment based on the first behavior parameter, the first behavior mode, the observation data at the first moment, and the third decision behavior; Obtaining a priori probability of the first behavior parameter of the obstacle vehicle; Determine, based on the first behavior parameter, the first behavior pattern, and the observation data at the first moment, a second probability of occurrence of a predicted mutual state between the target vehicle and the obstacle vehicle at a second moment; as well as Based on the first probability, the prior probability of the first behavior parameter and the second probability, the probability of the given behavior parameter at the second moment is determined.

6. The method according to claim 4, wherein the first decision behavior of the obstacle vehicle is determined based on the first behavior parameter and the first behavior pattern of the obstacle vehicle, and determining the probability of at least one behavior pattern of the obstacle vehicle comprises: For a given behavior pattern in the at least one behavior pattern, Determine, based on the third decision-making behavior, the first behavior pattern, and the observation data at the first moment, a third probability of occurrence of a predicted mutual state between the target vehicle and the obstacle vehicle at the second moment; Obtaining a priori probability of a first behavior mode of the obstacle vehicle; Determining, based on the third decision-making behavior and the observation data at the first moment, a fourth probability of occurrence of a predicted mutual state between the target vehicle and the obstacle vehicle at the second moment; and Based on the third probability, the prior probability of the first behavior pattern and the fourth probability, the probability of the given behavior pattern at the second moment is determined.

7. The method according to claim 4, wherein determining the fourth decision behavior of the obstacle vehicle at the second moment based on the probability of the at least one behavior parameter and the probability of the at least one behavior pattern comprises: determining a probability distribution of the at least one behavior parameter and the at least one behavior pattern based on the probability of the at least one behavior parameter and the probability of the at least one behavior pattern; as well as Based on the probability distribution, a fourth decision behavior of the obstacle vehicle is determined.

8. The method according to claim 1, wherein the fourth decision behavior of the obstacle vehicle is determined based on the probability of at least one behavior parameter and the probability of at least one behavior pattern corresponding to the obstacle vehicle, and determining at least one decision behavior of the target vehicle after the first moment comprises: Determining a first cost based on the mutual state of the target vehicle and the obstacle vehicle at the first moment and the third decision-making behavior; Determining a second cost based on the prediction of the mutual state of the target vehicle and the obstacle vehicle at the second moment, the probability of the at least one behavior parameter corresponding to the obstacle vehicle, and the probability of the at least one behavior pattern; as well as At least one decision-making behavior of the target vehicle after the first moment is determined based on the first cost and the second cost.

9. A vehicle control device, characterized in that: include: a mutual state prediction module, configured to determine a mutual state prediction between the target vehicle and the obstacle vehicle at a second moment based at least on a first decision-making behavior of the obstacle vehicle at a first moment and observation data of the target vehicle at the first moment; the observation data includes the mutual state between the target vehicle and the obstacle vehicle at the first moment and the second decision-making behavior of the target vehicle at a third moment, the second moment being after the first moment and the third moment being before the first moment; an obstacle vehicle decision behavior determination module, configured to determine a fourth decision behavior of the obstacle vehicle at the second moment based at least on the mutual state prediction at the second moment and the third decision behavior of the target vehicle at the first moment; a target vehicle decision behavior determination module, configured to determine at least one decision behavior of the target vehicle after the first moment based at least on the mutual state prediction at the second moment and the fourth decision behavior; as well as The target vehicle control module is configured to control the driving process of the target vehicle after the first moment through the at least one decision-making behavior.

10. An electronic device, characterized in that: include: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 8 when executed by the at least one processing unit.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: The computer program is executable by a processor to implement the method according to any one of claims 1 to 8.

12. A computer program product comprising computer executable instructions, characterized in that: The computer executable instructions implement the method according to any one of claims 1 to 8 when executed by a processor.

Images