Collision control method, apparatus, recording medium, and electronic equipment for collaborative operation of man-machines

Abstract

The present invention belongs to the technical field of automatic driving, and particularly relates to a method, device, recording medium and electronic device for collision control by man-machine collaborative driving. The collision control method by man-machine collaborative driving includes the steps of: establishing a man-machine path tracking control game model corresponding to man-machine interaction behavior based on a driver's deterministic steering torque and a driver's random steering torque (S101); solving the man-machine path tracking control game model to obtain man-machine torque collision information (S102); and determining a shared control strategy based on the man-machine torque collision information, thereby controlling the vehicle based on the shared control strategy (S103). The collision control method by man-machine collaborative driving provided in the present invention can improve the accuracy of vehicle control by describing the mapping relationship between the difference in man-machine decision-making and the man-machine steering torque interaction.

Description

[Technical Field]

[0001] This invention claims priority to a Chinese patent application filed on April 14, 2022, with application number 202210414179.X, titled "Collision control method, apparatus, recording medium, and electronic device by human-machine cooperative operation," the entire contents of which are incorporated herein by reference.

[0002] The present invention belongs to the field of autonomous driving technology, and more particularly to a collision control method using human-machine collaborative operation, a collision control device using human-machine collaborative operation, a recording medium, and electronic equipment. [Background technology]

[0003] Both the autonomous driving system and the driver are agents that make judgments and decisions based on their own understanding of the scene. Therefore, in addition to the differences in human-machine steering collisions caused by differences in human-machine preview behavior at the control layer of the cooperative driving system, another major cause of human-machine collisions is differences at the human-machine decision-making layer, namely differences in the target trajectory planned by the driver and the autonomous driving system, which further leads to a collision of steering torque.

[0004] However, in modeling the human-machine interaction mechanism, it becomes difficult to directly measure the driver's decision-making objectives, and in particular, in the modeling process of human-machine interaction in extreme driving situations (e.g., collaborative emergency avoidance by human-machine), it becomes difficult to directly describe the human-machine interaction behavior using a linear dynamics model.

[0005] For example, many nonlinear methods, such as nonlinear prediction methods, local linearization methods, and piecewise affine methods, are all applied to deal with model mismatch problems under extreme vehicle driving conditions. However, nonlinear prediction methods often have poor real-time performance due to their high computational complexity. Local linearization or piecewise affine methods can ensure real-time performance of the algorithm, but these methods inevitably cause the control strategy to switch alternately within different linearization sections, resulting in non-smooth phenomena in the human-machine interaction results, and furthermore, a sliding mode phenomenon occurs where the switching alternates near linear segmentation points.

[0006] Furthermore, the information disclosed in the background art above is used solely to enhance understanding of the background of the present invention, and may include information that does not constitute prior art known to those skilled in the art. [Overview of the project]

[0007] According to one embodiment of the present invention, a collision control method by cooperative operation of a man-machine is provided, the method comprising: establishing a man-machine path tracking control game model corresponding to the interaction behavior of the man-machine based on the driver's deterministic steering torque and the driver's random steering torque; solving the man-machine path tracking control game model to obtain torque collision information of the man-machine; and determining a shared control strategy based on the torque collision information of the man-machine, thereby performing vehicle control based on the shared control strategy.

[0008] According to a second embodiment of the present invention, a collision control device for man-machine cooperative operation is provided, the device including: a modeling module for establishing a man-machine path tracking control game model corresponding to man-machine interaction behavior based on the driver's deterministic steering torque and the driver's random steering torque; a solving module for solving the man-machine path tracking control game model to obtain man-machine torque collision information; and an operation module for determining a shared control strategy based on the man-machine torque collision information and performing vehicle control based on the shared control strategy.

[0009] According to a third embodiment of the present invention, a computer-readable recording medium storing a computer program is provided, and when the program is executed by a processor, the collision control method by human-machine cooperative operation described in the above embodiment is realized.

[0010] According to a fourth embodiment of the present invention, an electronic device is provided, the electronic device comprising one or more processors and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the man-machine collaborative collision control method of the above embodiment.

[0011] The general descriptions above and the detailed descriptions below are merely illustrative and interpretive and do not limit the present invention. [Brief explanation of the drawing]

[0012] The drawings herein, incorporated into the specification, constitute part of this specification, illustrate suitable embodiments of the invention, and are intended to interpret the principles of the invention together with the specification. Note that the drawings in the following description represent only some embodiments of the invention, and those skilled in the art can obtain other drawings from these without requiring any creative work. [Figure 1]It is a schematic diagram schematically showing the flow of a collision control method by cooperative driving of a man-machine in an exemplary embodiment of the present invention. [Figure 2] It is a schematic diagram schematically showing the principle of steering interaction of a man-machine cooperative driving system in an exemplary embodiment of the present invention. [Figure 3] It is a schematic diagram schematically showing the principle of a non-cooperative game of a man-machine cooperative driving system in an exemplary embodiment of the present invention. [Figure 4] It is a diagram schematically showing the principle of a closed-loop dynamic game of a man-machine cooperative driving system in an exemplary embodiment of the present invention. [Figure 5] It is a schematic diagram schematically showing the principle of an open-loop dynamic game of a man-machine cooperative driving system in an exemplary embodiment of the present invention. [Figure 6] It is a schematic diagram schematically showing the flow of a method for constructing a closed-loop man-machine path tracking control game model in an exemplary embodiment of the present invention. [Figure 7] It is a schematic diagram schematically showing the principle of a multi-point preview mode in an exemplary embodiment of the present invention. [Figure 8] It is a schematic diagram schematically showing the flow of a method for constructing an open-loop man-machine path tracking control game model in an exemplary embodiment of the present invention. [Figure 9] It is a schematic diagram schematically showing the flow of a method for solving a closed-loop man-machine path tracking control game model in an exemplary embodiment of the present invention. [Figure 10] It is a schematic diagram schematically showing the flow of a method for solving another closed-loop man-machine path tracking control game model in an exemplary embodiment of the present invention. [Figure 11] It is a schematic diagram schematically showing the flow of a method for solving another open-loop man-machine path tracking control game model in an exemplary embodiment of the present invention. [Figure 12] It is a schematic diagram schematically showing the flow of a method for solving another open-loop man-machine path tracking control game model in an exemplary embodiment of the present invention. [Figure 13]This is a schematic diagram schematically showing the configuration of a collision control device by cooperative operation of a man-machine in an exemplary embodiment of the present invention. [Figure 14] This is a schematic diagram schematically showing a computer-readable recording medium in an exemplary embodiment of the present invention. [Figure 15] This is a schematic diagram schematically showing the structure of a computer system of an electronic device in an exemplary embodiment of the present invention.

Mode for Carrying Out the Invention

[0013] Hereinafter, exemplary embodiments will be more comprehensively described with reference to the drawings. However, the exemplary embodiments can be implemented in multiple types of forms and are not limited to the examples described in this specification. On the contrary, these embodiments are provided to make the present invention complete and comprehensive, and to fully convey the idea of the exemplary embodiments to those skilled in the art.

[0014] Note that the features, configurations or characteristics described can be combined with one or more embodiments in any suitable manner. In the following description, many specific details are provided to enable a complete understanding of the embodiments according to the present invention. However, what those skilled in the art should understand is that the technical solution according to the present invention can be realized even without one or more of these specific details, or other methods, members, devices, steps, etc. can be adopted. In other cases, well-known methods, devices, realizations or operations are not shown or described in detail to avoid obscuring the aspects of the present invention.

[0015] The block diagrams shown in the drawings are only functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be realized in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0016] The flowcharts shown in the diagrams are illustrative only and do not necessarily have to include all content and operations / steps, nor do they necessarily have to be performed in the order they are shown. For example, some operations / steps may be broken down, while others may be merged or partially merged, so the actual order in which they are performed may change depending on the actual situation.

[0017] In a human-machine dual-agent system, the driver and the autonomous driving system can simultaneously operate actuators and change the vehicle's state to achieve their respective goals. However, this input redundancy inevitably leads to human-machine collision interactions, which have serious consequences for vehicle safety, comfort, power, and fuel economy.

[0018] Game theory is an effective means of describing and understanding interaction collisions in multi-agent systems, and provides effective theoretical methods for quantitative modeling of human-machine interactions, resolving human-machine collisions, and estimating the true intentions of drivers.

[0019] Regarding the problem of collaborative trajectory tracking control between human-machine vehicles, both the autonomous driving system and the driver are agents that make judgments and decisions based on their own understanding of the scene. Therefore, in addition to steering collisions between human-machine vehicles due to differences in the preview actions of the human-machine vehicle in the control layer of the collaborative driving system, another major cause of human-machine collisions is differences in the decision-making layers of the human-machine vehicle, namely differences in the target trajectories planned by the driver and the autonomous driving system, which further leads to collisions in steering torque.

[0020] On the other hand, in modeling human-machine interaction mechanisms, particularly in the process of modeling human-machine interaction under extreme vehicle driving conditions (e.g., collaborative emergency avoidance by human-machine systems), it becomes difficult to directly describe human-machine interaction behavior using linear dynamics models. For example, many nonlinear methods such as nonlinear prediction methods, local linearization methods, and piecewise affine methods are all applied to deal with the problem of model inconsistency under extreme vehicle driving conditions, and nonlinear prediction methods often have poor real-time performance due to their high computational complexity. While local linearization or piecewise affine methods can ensure real-time performance of the algorithm, these methods inevitably cause the control strategy to switch alternately within different linearization sections, resulting in non-smooth phenomena in the human-machine interaction results, and furthermore, a sliding mode phenomenon appears where the switching alternates near linear segmentation points. On the other hand, while dynamic non-cooperative game theory can be applied to multi-agent dynamic systems, current research in game theory for cooperative operating systems is mainly limited to the design of shared control strategies, and there is still no complete theoretical description of the mapping relationship between differences in human-machine decision-making and collision control.

[0021] To solve this troublesome problem, the present invention studies the human-machine interaction mechanism of collision control from the perspective of differences in decision-making. In a dynamic steering system with human-machine interaction, two types of disturbances exist simultaneously: deterministic steering resistance torque and the driver's uncertain steering torque. Therefore, the present invention proposes a new theoretical framework for random games that considers deterministic and random steering torques and completely describes this mapping relationship with Nash equilibrium and Stackelberg equilibrium in different information modes. By doing so, the present invention designs a theoretical bridge connecting differences in human-machine decision-making with collision control, overcoming the confusion problem of human-machine decision-making present in cooperative driving systems, and further providing a theoretical basis for designing shared control strategies.

[0022] The details of the implementation of the technical proposal of the embodiment of the present invention will be described in detail below.

[0023] Figure 1 is a schematic diagram illustrating the flow of a collision control method using man-machine cooperative operation in an exemplary embodiment of the present invention. As shown in Figure 1, this collision control method using man-machine cooperative operation includes steps S101 to S103.

[0024] In step S101, a man-machine path-following control game model is established that corresponds to man-machine interaction behavior, based on the driver's deterministic steering torque and the driver's random steering torque.

[0025] In step S102, the path tracking control game model of the man-machine is solved to obtain torque collision information of the man-machine.

[0026] In step S103, a shared control strategy is determined based on the torque collision information of the man-machine, and vehicle control is performed based on the shared control strategy.

[0027] In the technical solutions provided in some embodiments of the present invention, the present invention establishes a man-machine path tracking control game model corresponding to man-machine interaction behavior based on the driver's deterministic steering torque and the driver's random steering torque, and obtains man-machine torque collision information by solving the man-machine path tracking control game model, which is then used for vehicle control. The driver's uncertain behavior can be incorporated into the man-machine path tracking control, making it more aligned with the demands of actual scenes and allowing for more accurate control effects. At the same time, the man-machine torque collision information obtained by solving the game model accurately describes the man-machine interaction behavior in collision control from the differences in decision-making in the man-machine cooperative driving model, overcoming the confusion problem of man-machine decision-making that exists in cooperative driving systems, and further providing a theoretical basis for designing shared control strategies and further optimizing the results of vehicle control.

[0028] The following describes in more detail each step of the collision control method using man-machine cooperative operation in this exemplary embodiment, with reference to the drawings and examples.

[0029] In step S101, a man-machine path-following control game model is established that corresponds to man-machine interaction behavior, based on the driver's deterministic steering torque and the driver's random steering torque.

[0030] In one embodiment of the present invention, first, a man-machine path-following control game model is established for solving man-machine interaction behavior, and this man-machine path-following control game model can utilize the theoretical framework of non-cooperative games.

[0031] Figure 2 is a schematic diagram illustrating the principle of steering interaction in a man-machine cooperative driving system in an exemplary embodiment of the present invention. As shown in Figure 2, both the driver and the automated driving system (hereinafter simply referred to as the driving system) generate corresponding steering actions based on their respective target trajectories, and simultaneously, both can sense each other's decision-making through the motion state of the steering system and the entire vehicle. Therefore, for the driver, in order to achieve their own decision-making goals, their steering actions include a response to the steering actions of the driving system. For this reason, when designing the controller of the driving system, the driver's steering control input should also be given due consideration. For this reason, when modeling man-machine steering collisions in a man-machine cooperative driving system, the interaction of man-machine steering actions must be considered. In particular, under conditions where the decision-making goals of the man and machine differ, the driver's steering actions are not only based on their own decision-making goals but also actively compensate for the steering actions of the automated driving system, which is a significant difference from pure manual driving.

[0032] In a collaborative driving process, both the driver's and the automated driving system's steering actions aim to minimize tracking errors for each trajectory. Since each steering action is generated based on lane system state feedback and the other's steering actions, it is inevitable that the target trajectories of the decision-making layers of the human-machine system will differ. Under these conditions, the human-machine interaction process can be described in terms of a non-cooperative game.

[0033] Figure 3 is a schematic diagram illustrating the principle of a non-cooperative game of a man-machine cooperative driving system in an exemplary embodiment of the present invention. As shown in Figure 3, the driver and the driving system are considered game participants, and both aim to maximize their respective interests by integrating state information of the game process and the actions of the other party to generate their respective actions.

[0034] When studying the problem of human-machine cooperative operation using game theory, the trajectory tracking actions of the driver and the autonomous driving system are described using an optimal control strategy based on a cost function. The sum of the cost functions of both is non-zero, and the optimal trajectory tracking control is usually described by the predictive horizontal and the control time domain. Therefore, the problem of trajectory tracking by human-machine cooperative operation can be abstracted as a non-zero-sum multi-stage dynamic game problem. For non-zero-sum multi-stage dynamic games, the game problem can be divided into two types based on the game's information mode: closed-loop memoryless dynamic game problems and open-loop dynamic game problems.

[0035] Figure 4 schematically illustrates the principle of a closed-loop dynamic game of a man-machine cooperative operation system in an exemplary embodiment of the present invention. As shown in Figure 4, in this information model, the participants' acceptable strategy sets are mapped by the initial state and the state of each stage, but "no memory" means that when participants make decisions at each stage, they only know the initial and current states of the system and have no memory of the remaining states of each stage, so the participant's action at the i-th stage is, JPEG0007880437000001.jpg514, JPEG0007880437000002.jpg514, i∈{0,1,…,n u It may also be expressed as}.

[0036] A closed-loop memoryless dynamic game corresponds to an open-loop dynamic game. Figure 5 is a schematic diagram illustrating the principle of an open-loop dynamic game in a man-machine cooperative operation system in an exemplary embodiment of the present invention. As shown in Figure 5, the entire game process takes a total of n u It is divided into individual stages, and the state vector of each stage system is x k Since the acceptable strategy set for each participant at each stage is only relevant to the initial state, and given the initial state x0, the strategy set is a constant function, so the behavior of the participant at the i-th stage is also constant. JPEG0007880437000003.jpg54, JPEG0007880437000004.jpg54, i∈{0,1,…, n u It becomes}.

[0037] Therefore, in step S101, two different information modes, a closed-loop and an open-loop, can be established for the man-machine path tracking control game model.

[0038] (1) Closed-loop human-machine path tracking control game model Figure 6 is a schematic diagram illustrating the flow of a method for constructing a closed-loop man-machine path-following control game model in an exemplary embodiment of the present invention. Specifically, the steering actions of the driver and the driving system are described by an optimal multi-point preview linear quadratic regulator (LQR) method. As shown in Figure 6, this method for constructing a man-machine path-following control game model includes the following steps. In step S601, a first discrete state update equation for the vehicle's dynamic system is established based on the driver's deterministic steering torque and the driver's random steering torque, resulting from the cooperative operation of the man-machine in a closed-loop information mode. In step S602, the first discrete state update equation is extended by the dynamic process of the human-machine preview to obtain a path-tracking extension system that includes the human-machine preview state. In step S603, a driver trajectory cost function and a driving system trajectory cost function are constructed based on the path tracking extension system to obtain the man-machine path tracking control game model.

[0039] Specifically, this section focuses on the modeling problem of human-machine interaction, so it can be assumed that the target trajectories of the human-machine all have small tangential angles, and under the condition of small heading angles, the state vector in the model is: It may be simplified to JPEG0007880437000005.jpg532, and here, JPEG0007880437000006.jpg46 is the rotation angle of the steering wheel. JPEG0007880437000007.jpg56 is related to time This is the result of calculating the derivative of JPEG0007880437000008.jpg46, where Y is the global vertical coordinate of the vehicle's center of gravity. JPEG0007880437000009.jpg43 is the vehicle's heading angle, JPEG0007880437000010.jpg53 is related to time This is the result of calculating the derivative of JPEG0007880437000011.jpg43.

[0040] In step S601, a first discrete state update equation for the vehicle's dynamic system is established based on the driver's deterministic steering torque and the driver's random steering torque, resulting from the cooperative operation of the man-machine in a closed-loop information mode.

[0041] Driver's definite steering torque The random steering torque is set to JPEG0007880437000012.jpg54. The filename is JPEG0007880437000013.jpg57, and the steering torque of the driving system is set to Let's call it JPEG0007880437000014.jpg55. State vector Based on JPEG0007880437000015.jpg44, the driver's deterministic steering torque is as shown in equation (1). JPEG0007880437000016.jpg54 and driver random steering torque The continuous state-space equation is established using JPEG0007880437000017.jpg57. JPEG0007880437000018.jpg1069(1) During the ceremony, JPEG0007880437000019.jpg47 is steering torque related to distance. JPEG0007880437000020.jpg44, JPEG0007880437000021.jpg44, JPEG0007880437000022.jpg45, JPEG0007880437000023.jpg44 and JPEG0007880437000024.jpg44 is a parameter matrix in the model, as shown below. JPEG0007880437000025.jpg50170

[0042] To describe the problem of human-machine cooperative operation as a multi-stage game, we define the discrete time T of the system. s By discretizing the continuous system of the above equation, the dynamic system of a man-machine shared vehicle may be transformed into the form of the following difference equation, i.e., the first discrete state update equation, as shown in equation (2). JPEG0007880437000026.jpg1087(2) During the ceremony,

number

[0043] In step S602, the first discrete state update equation is extended by the dynamic process of the man-machine preview, and a path tracking extended system including the man-machine preview state is obtained.

[0044] FIG. 7 is a schematic diagram schematically showing the principle of the multi-point preview mode in an exemplary embodiment of the present invention. While modeling the path tracking control system by the LQR method and considering the predictive behavior of the man-machine on vehicle dynamics, first, the preview behavior of the man-machine is modeled as a multi-point preview mode as shown in FIG. 7. Referring to FIG. 7, the driver and the driving system preview a part of the area on their target trajectory based on their own decision-making at each time point, and this area can be described as n p preview points, and the preview distance is determined by the driver's preview time t p and t p = n p ×T s is. This dynamic process may be represented by a shift register as shown in Equation (3). JPEG0007880437000032.jpg538(3) Here,

Equation

[0045] In the dynamic process of the man-machine preview JPEG0007880437000034.jpg538 extends the dynamic system of a shared man-machine vehicle, and a path-tracking extension system including a preview state of the man-machine can be obtained, as shown in equation (4). JPEG0007880437000035.jpg1079(4) Here,

number

[0046] In step S603, a driver trajectory cost function and a driving system trajectory cost function are constructed based on the path tracking extension system to obtain the man-machine path tracking control game model.

[0047] Specifically, in a path tracking augmentation system where human-machine decision-making differs, both the prediction time domain and the control time domain are n u By designing the driver trajectory cost function J1 and the driving system trajectory cost function J2 as steps, we obtain a man-machine path tracking control game model that can be described as shown in equation (6). JPEG0007880437000042.jpg1179 JPEG0007880437000043.jpg1166(6) Here,

number

[0048] Based on this, equation (6) is obtained by a linear quadratic method n u We construct a multi-stage man-machine path-following control game model, where both cost functions include the steering control input of the other party, thereby representing the interaction characteristics of the man-machine.

[0049] (2) Open-loop man-machine path tracking control game model Figure 8 is a schematic diagram illustrating the flow of a method for constructing an open-loop man-machine path-following control game model in an exemplary embodiment of the present invention. Specifically, a Distributed Model Predictive Control (DMPC) strategy is used to describe the mapping relationship between differences in man-machine decision-making in the open-loop information mode and steering torque collisions. As shown in Figure 8, this method for constructing a man-machine path-following control game model includes the following steps. In step S801, a second discrete state update equation for the vehicle's dynamic system under man-machine cooperative operation in open-loop information mode is established based on the driver's deterministic steering torque and the driver's random steering torque. In step S802, the predicted output vector in the prediction time domain is determined based on the second discrete state update equation, and the driver reference trajectory vector and the driving system reference trajectory vector are determined. In step S803, the driver trajectory cost function and the driving system trajectory cost function are constructed using the predicted output vector, the driver reference trajectory vector, and the driving system reference trajectory vector, respectively, to obtain the man-machine path tracking control game model.

[0050] Specifically, under the framework of model predictive control, both the driver and the driving system are predicted in the time domain n. p Within the system, the vehicle's trajectory is estimated, and the control time domain n uBy performing steering control within the system to minimize the discrepancy between the vehicle trajectory and each decision, model predictive control more intuitively reflects the target trajectory planned by the driver and the decision-making layer of the autonomous driving system in the final interaction model compared to linear quadratic regulator methods. At the same time, as can be seen from the model predictive control algorithm, the state prediction vector in its cost function is always related to the current state of the system and the control time domain n u Since it is established based on the internal control input, the control law is also related only to the current initial state and coincides precisely with the definition of the open-loop information mode.

[0051] In step S801, a second discrete state update equation for the vehicle's dynamic system under man-machine cooperative operation in open-loop information mode is established based on the driver's deterministic steering torque and the driver's random steering torque.

[0052] For the dynamic system of a man-machine cooperative vehicle, when the driver's uncertain actions are incorporated into the system's disturbances, a second discrete state update equation is obtained, as shown in equation (7). JPEG0007880437000061.jpg1083(7) Here,

number

[0053] Based on the second discrete state update equation described above, the disturbance input in the prediction time domain is... Assuming that JPEG0007880437000068.jpg56 is maintained at a constant level, the next n of the man-machine cooperative operation system p The model output for each step may also be expressed as follows: JPEG0007880437000069.jpg76168

[0054] In step S802, the predicted output vector in the prediction time domain is determined based on the second discrete state update equation, and the driver reference trajectory vector and the driving system reference trajectory vector are determined.

[0055] The prediction time domain and control time domain of the model prediction algorithm for a human-machine cooperative operation system are both n u Assuming this is the case, at time k, the model predicted output vector in the prediction time domain is as shown in equation (8). Defined as JPEG0007880437000070.jpg55, the control input vector of the human-machine is as shown in equations (9) and (10). JPEG0007880437000071.jpg46 and Each file is defined as JPEG0007880437000072.jpg47. JPEG0007880437000073.jpg761(8) JPEG0007880437000074.jpg644(9) JPEG0007880437000075.jpg645(10)

[0056] Based on the second discrete state update equation (Equation 7), the following n of the man-machine cooperative operation system p The step model output, i.e., the predicted output vector, may be expressed as shown in equation (11). JPEG0007880437000076.jpg556(11) Here, JPEG0007880437000077.jpg649, JPEG0007880437000078.jpg676, JPEG0007880437000079.jpg2279, The filename is JPEG0007880437000080.jpg2279.

[0057] At each time step k, the reference trajectory vectors of the driver and the autonomous driving system may be expressed as shown in equation (12). JPEG0007880437000081.jpg654 JPEG0007880437000082.jpg657(12)

[0058] In step S803, the driver trajectory cost function and the driving system trajectory cost function are constructed using the predicted output vector, the driver reference trajectory vector, and the driving system reference trajectory vector, respectively, to obtain the man-machine path tracking control game model.

[0059] In a human-machine path-tracking control game model, the parameters are the predicted output vector. JPEG0007880437000083.jpg55 and reference locus vector JPEG0007880437000084.jpg46, Represented by JPEG0007880437000085.jpg47, the driver trajectory cost function and the driving system trajectory cost function are obtained as shown in equation (13). JPEG0007880437000086.jpg652 JPEG0007880437000087.jpg554(13) During the ceremony, JPEG0007880437000088.jpg55, JPEG0007880437000089.jpg45 are all weight matrices for path tracking control, where x∈{1, 2}, JPEG0007880437000090.jpg670, The filename is JPEG0007880437000091.jpg658.

[0060] In step S102, the path tracking control game model of the man-machine is solved to obtain torque collision information of the man-machine.

[0061] In step S101, two different man-machine path-following control game models are constructed for closed-loop and open-loop information modes, and the solution methods for these two game models are also different.

[0062] Furthermore, regarding the problem of non-cooperative games, in a human-machine cooperative driving system, the controller of the autonomous driving system is usually designed using a mirror-symmetric anthropomorphic strategy to improve the consistency between the human and machine. Thus, the driver and the autonomous driving system have an equal relationship in the game process, and when the game participants are in a symmetric or equal relationship, the Nash equilibrium provides a rational theoretical solution to non-cooperative games. In this equilibrium state, neither party occupies a dominant position in the decision-making process, and neither can unilaterally adjust their own decision-making to lower the value of their trajectory tracking cost function.

[0063] Another problem in non-cooperative games is the master-slave game in dual-agent systems. In this problem, the leader makes their decision first, based on the followers' reactions to their own decisions, while the followers make their decisions after observing the leader's decisions. The result of such hierarchical games is called a Stackelberg equilibrium.

[0064] Nash equilibrium and Stackelberg equilibrium theoretically model the decision-making and control mechanisms of cooperative human-machine systems, and for each game model, two solutions corresponding to this model—a Nash equilibrium and a Stackelberg equilibrium—can be obtained. Therefore, we will then use quantitative models based on the theory of four non-cooperative games to explore the optimal modeling scheme and method for human-machine interaction mechanisms by deeply analyzing the mapping relationship between the differences in human-machine decision-making in Nash equilibrium and Stackelberg equilibrium and steering torque collisions, based on two information modes: open-loop and closed-loop.

[0065] (1) Nash equilibrium solutions for human-machine decision-making and control in closed-loop information mode In one embodiment of the present invention, the problem of solving a Nash equilibrium in closed-loop information mode can be described as a constrained optimization problem of a Hamiltonian function as shown in equation (14). JPEG0007880437000092.jpg43134 During the ceremony, JPEG0007880437000093.jpg54 is a covariant vector.

[0066] The above equation is a closed-form solution to the constraint optimization problem. JPEG0007880437000094.jpg552 represents a closed-loop Nash equilibrium solution.

[0067] The Nash equilibrium solution in open-loop mode is an open-loop Nash equilibrium solution because it relates only to the initial state and not to the current state at each stage. JPEG0007880437000095.jpg543 also satisfies the closed-loop Nash equilibrium condition (14), but it is clear that the solution to the closed-loop Nash equilibrium problem is not limited to the open-loop Nash equilibrium solution, and this non-uniqueness of information leads to the problem that there are multiple Nash equilibrium solutions in the closed-loop information structure. In this specification, when modeling a system, the parameter of the driver random steering torque is Considering JPEG0007880437000096.jpg44, the non-uniqueness of information in the game process is just resolved, and the feedback Nash equilibrium avoids the problem of multiple solutions existing. The optimal solution at each stage of the feedback Nash equilibrium satisfies the following conditions. JPEG0007880437000097.jpg71167

[0068] The feedback Nash equilibrium condition under closed-loop conditions is consistent with the Bellman optimality principle, and the Stochastic Dynamic Programming (SDP) algorithm can be used to find the closed-loop Nash equilibrium solution (also called the feedback Nash equilibrium solution) of a path-following control system under conditions where human-machine decision-making differs.

[0069] Figure 9 is a schematic diagram illustrating the flow of a method for solving a closed-loop man-machine path-following control game model in an exemplary embodiment of the present invention. As shown in Figure 9, this method for solving a man-machine path-following control game model includes the following steps. In step S901, a random dynamic programming algorithm determines the recursive relationship of the steering control value functions corresponding to the driver and the driving system, respectively, under the Nash equilibrium conditions. In step S902, based on the first discrete state update equation and the recursive relation, closed-loop Nash equilibrium solutions corresponding to the driver and the driving system, respectively, are calculated as torque collision information for the man-machine.

[0070] Specifically, at any time step k, the unmodeled disturbance in the man-machine cooperative operation system JPEG0007880437000098.jpg44 is n u Assuming that it is maintained constant throughout the dynamic game of the entire stage, Gauss random distribution Using JPEG0007880437000099.jpg419, the parameters related to driver random steering torque are described, and in the formula, JPEG0007880437000100.jpg42, JPEG0007880437000101.jpg43 represents the mean and standard deviation of a Gaussian distribution, respectively.

[0071] It is a disturbance vector. JPEG0007880437000102.jpg44, The presence of JPEG0007880437000103.jpg44 makes the solution of the man-machine game problem based on steering torque interaction an affine quadratic problem. Therefore, in the solution process based on dynamic programming, the steering control value functions of the driver and the driving system take the form of an affine quadratic, as shown in equation (15). JPEG0007880437000104.jpg1279 JPEG0007880437000105.jpg1169(15)

[0072] In equation (15) above, the steering control value function is obtained from the jth to the nth stage of the cost functions of the driver and the driving system, respectively. u The values ​​of the value function in the game process up to step (k+j) are represented, and the steering control value function for step (k+j+1) satisfies the recursive relation as shown in equation (16). JPEG0007880437000106.jpg871 JPEG0007880437000107.jpg771(16) In the equation, the superscript "N" represents the value function under the Nash equilibrium condition, and the one-step cost function g() at each stage may be expressed as shown in equation (17). JPEG0007880437000108.jpg1179 JPEG0007880437000109.jpg1178(17)

[0073] The first discrete state update equation By substituting JPEG0007880437000110.jpg555 (Equation 4) into the steering control value function (Equation 15), the torque of a man-machine that satisfies the closed-loop Nash equilibrium relationship satisfies the relationship shown in Equation (18). JPEG0007880437000111.jpg1079 JPEG0007880437000112.jpg1071(18)

[0074] (2) Stackelberg equilibrium solution for human-machine decision-making and control in closed-loop information mode Figure 10 is a schematic diagram illustrating the flow of a method for solving another closed-loop man-machine path-following control game model in an exemplary embodiment of the present invention. As shown in Figure 10, this method for solving the man-machine path-following control game model includes the following steps: In step S1001, a random dynamic programming algorithm is used to determine the recursive relationship of the steering control value functions corresponding to the driver and the driving system, respectively, under the Stackelberg equilibrium condition. In step S1002, the driver's response function is determined based on the recursive relationship of the steering control value function corresponding to the driving system. In step S1003, the open-loop Stackelberg equilibrium solution corresponding to the driving system is calculated based on the recursive relationship between the first discrete state update equation, the driver response function, and the steering control value function corresponding to the driving system. In step S1004, an open-loop Stackelberg equilibrium solution corresponding to the driver is calculated based on the open-loop Stackelberg equilibrium solution corresponding to the driving system, and this is used as the torque collision information for the man-machine.

[0075] Specifically, unlike the Nash equilibrium, the Stackelberg equilibrium involves a master-slave relationship between the driver and the autonomous driving system. In each stage of the game, the driving system, being the leader, takes the steering control input first, and the driver observes this action and responds accordingly.

[0076] Therefore, the closed-loop Stackelberg equilibrium solution can be solved by backward induction. Based on the random dynamic programming method, the recursive relationship of the driver steering control value function JPEG0007880437000113.jpg57 is This is the same as JPEG0007880437000114.jpg57 (see Equation 16).

[0077] The recursive relationship of the driving system steering control value function in the closed-loop Stackelberg equilibrium solution (also called the feedback Stackelberg equilibrium solution) in closed-loop information mode satisfies the conditions shown in equation (19). JPEG0007880437000115.jpg1379(19) In the equation, the superscript "S" represents the value function under the Stackelberg equilibrium condition, where, The filename is JPEG0007880437000116.jpg15166.

[0078] The first discrete state update equation JPEG0007880437000117.jpg555 (Equation 4) and the recursive relationship of the driver steering control value function By substituting JPEG0007880437000118.jpg57 into the recursive relation of the driving system steering control value function (Equation 19), the driver response function to the driving system steering torque can be obtained as shown in Equation (20). JPEG0007880437000119.jpg1179(20)

[0079] By substituting the first discrete state update equation (Equation 4) and the driver response function (Equation 20) into the recursive relation of the steering control value function of the driving system (Equation 19), we obtain the open-loop Stackelberg equilibrium solution of the driving system in the Stackelberg equilibrium strategy, as shown in Equation (21). JPEG0007880437000120.jpg1079JPEG0007880437000121.jpg577JPEG0007880437000122.jpg1079(21) During the ceremony, JPEG0007880437000123.jpg647, JPEG0007880437000124.jpg539, JPEG0007880437000125.jpg539, The filename is JPEG0007880437000126.jpg560.

[0080] Since the driving system is the leader and the driver is the follower, the closed-form solution to the constrained optimization problem of the Hamiltonian function corresponding to the driver can be obtained as the driver's open-loop Stackelberg equilibrium solution from the driving system's open-loop Stackelberg equilibrium solution.

[0081] (3) Nash equilibrium solutions for human-machine decision-making and control in open-loop information mode Figure 11 is a schematic diagram illustrating the flow of a method for solving another open-loop man-machine path-following control game model in an exemplary embodiment of the present invention. As shown in Figure 11, this method for solving the man-machine path-following control game model includes the following steps: In step S1101, a closed-form solution is obtained for the model corresponding to the path tracking control game model of the man-machine, thereby obtaining a relational expression between the steering control of the man-machine and the target trajectory based on the closed-form solution of the model. In step S1102, the open-loop Nash equilibrium solutions corresponding to the driver and the driving system are obtained as torque collision information for the man-machine by solving the relational expression using a convex iterative algorithm.

[0082] Specifically, based on the definition of an open-loop Nash equilibrium, a convex iterative algorithm is used to find the Nash equilibrium solution of the system in open-loop information mode.

[0083] For an unconstrained problem like equation (13), the path-following control law of a man-machine has the following closed-form solution, as shown in equation (22).

number

number

[0084] As can be seen from equation (23), there is an interaction relationship between the two control laws, that is, one's own control actions are not only related to their respective decision-making goals, system states, and disturbances, but are also closely related to the other's control strategy. For this reason, in order to resolve the interaction from equation (23), we solve it using a convex iterative algorithm and obtain the update equation as shown in equation (24). JPEG0007880437000132.jpg553 JPEG0007880437000133.jpg456(24)

[0085] The process of solving a convex iterative algorithm can be summarized as follows. First, the initial iteration value is JPEG0007880437000134.jpg59, After confirming JPEG0007880437000135.jpg510, substitute it into the relational equation (Equation 23) to obtain the current optimal value. JPEG0007880437000136.jpg59, We obtain JPEG0007880437000137.jpg510, and then substitute it into the update formula (Equation 24) in the next step. JPEG0007880437000138.jpg59, Update JPEG0007880437000139.jpg510 and repeat in this manner. When i approaches infinity, the update formula (Equation 24) becomes as follows. JPEG0007880437000140.jpg554 JPEG0007880437000141.jpg457(25) Therefore, the relational equation (Equation 23) is as follows: JPEG0007880437000142.jpg20129 For this reason, the expression for the Nash equilibrium solution of human-machine decision-making and control in open-loop information mode is as shown in equation (27). JPEG0007880437000143.jpg2079(27)

[0086] In the actual modeling process, the values ​​from the first stage of the game are taken as the result of the man-machine interaction in the open-loop Nash equilibrium at time k, i.e., as the torque collision information of the man-machine. JPEG0007880437000144.jpg546 JPEG0007880437000145.jpg547(28)

[0087] (4) Stackelberg equilibrium solution for human-machine decision-making and control in open-loop information mode Figure 12 is a schematic diagram illustrating the flow of a method for solving another open-loop man-machine path-following control game model in an exemplary embodiment of the present invention. As shown in Figure 12, this method for solving the man-machine path-following control game model includes the following steps: In step S1201, the driving system trajectory cost function is converted into a driving system trajectory optimization function that takes into account the driver's reaction function. In step S1202, the open-loop Stackelberg equilibrium solution corresponding to the operating system is obtained by solving the operating system trajectory optimization function. In step S1203, the open-loop Stackelberg equilibrium solution corresponding to the driver is calculated based on the open-loop Stackelberg equilibrium solution and the driver trajectory cost function, and this is used as the torque collision information for the man-machine.

[0088] Specifically, the open-loop Stackelberg equilibrium solution is realized by a backward induction method similar to that used to solve the closed-loop Stackelberg equilibrium. Predicted output vector Substituting JPEG0007880437000146.jpg55 (Equation 11) into the game model (Equation 13) yields the following equation. JPEG0007880437000147.jpg656 JPEG0007880437000148.jpg560(29) During the ceremony, JPEG0007880437000149.jpg553, The filename is JPEG0007880437000150.jpg554.

[0089] Unlike solving open-loop Nash equilibrium, in the master-slave game, the autonomous driving system acts first as the leader at each stage of the game, and the driver observes the autonomous driving system's actions before responding accordingly.

[0090] Therefore, as shown in equation (30), We obtain JPEG0007880437000151.jpg43 to get the driver's response function to the driving system. JPEG0007880437000152.jpg1379(30)

[0091] When a control strategy is adopted, the driving system obtains a new driving system trajectory cost function by considering the driver response function to it in its cost function, as shown in equation (31). JPEG0007880437000153.jpg1179(31)

[0092] Therefore, finding the Stackelberg equilibrium solution for steering torque control of the driving system in open-loop information mode is equivalent to solving an unconstrained optimization problem as shown in equation (32). JPEG0007880437000154.jpg10104(32)

[0093] By solving the above optimization problem, we can obtain the open-loop Stackelberg equilibrium solution corresponding to the operating system, as shown in equation (33). JPEG0007880437000155.jpg569(33) During the ceremony, JPEG0007880437000156.jpg528, JPEG0007880437000157.jpg526, JPEG0007880437000158.jpg517, JPEG0007880437000159.jpg531, The filename is JPEG0007880437000160.jpg1034.

[0094] This is the Stackelberg equilibrium solution for the steering control of the driving system. Based on JPEG0007880437000161.jpg57, the optimal driver response to the steering control of the automated driving system can be obtained by solving an optimization problem like equation (34). JPEG0007880437000162.jpg1086(34)

[0095] From the above equation, as shown in equation (35), the Stackelberg equilibrium solution for driver steering control in open-loop information mode can be obtained. JPEG0007880437000163.jpg570(35) During the ceremony, JPEG0007880437000164.jpg527, JPEG0007880437000165.jpg518, JPEG0007880437000166.jpg531, JPEG0007880437000167.jpg529, The filename is JPEG0007880437000168.jpg930.

[0096] Similarly, as shown in equation (36), we take the open-loop Stackelberg equilibrium solution for the first stage of the game and describe the interaction result of the man-machine steering torque at time k. JPEG0007880437000169.jpg545 JPEG0007880437000170.jpg547(36)

[0097] Unlike the open-loop Nash equilibrium, the open-loop Stackelberg equilibrium is solved by backward induction. Therefore, when solving the control law for the automated driving system (Equation 34), constraints can be added to ensure the controller satisfies the expected performance, turning it into a constraint optimization problem. Thus, the significance of the open-loop Stackelberg equilibrium strategy proposed herein lies not only in proposing a theoretical model of the interaction of steering torque between the man and the machine, but also in enabling the flexible design of an interactive steering assist controller that satisfies kinematic and dynamic safety constraints using this algorithm.

[0098] In step S103, a shared control strategy is determined based on the torque collision information of the man-machine, and vehicle control is performed based on the shared control strategy.

[0099] Specifically, the man-machine torque collision information obtained in step S102 establishes a theoretical basis between differences in man-machine decision-making and collision control. Based on this theoretical basis, a shared control strategy under emergency lane change situations can be better designed, thereby guiding vehicle control.

[0100] This invention models the mapping relationship between differences in human-machine decision-making and the interaction of human-machine steering torque in four types of dynamic non-cooperative games, in order to establish a theoretical relationship between differences in human-machine decision-making and collision control.

[0101] On the other hand, the dynamic model of the cooperative operation system is extended using the target trajectory of the man-machine, and then the man-machine interaction behavior in feedback information mode is modeled using a linear secondary regulator method.

[0102] The model establishes a mapping relationship between differences in human-machine decision-making and the interaction with steering torque. Therefore, solving the problem of discrepancies in human-machine decision-making due to the presence of steering resistance torque and driver uncertainty torque becomes an affine quadratic game problem. This specification proposes an algorithm for an affine quadratic game based on random dynamic programming to find feedback-Nash equilibrium solutions and feedback-Stackelberg equilibrium solutions that describe the interaction relationship between human-machine decision-making and steering torque.

[0103] On the other hand, the problem of multi-target path tracking control for humans and vehicles in an open loop is described using a distributed model predictive control method. To solve the human-machine decision-making and control model in the open-loop information mode, the open-loop Nash equilibrium solution and the open-loop Stackelberg equilibrium solution, which describe the mapping relationship between human-machine decision-making and control, are obtained using the model predictive control method.

[0104] Figure 13 is a schematic diagram illustrating the configuration of a collision control device using man-machine collaborative operation in an exemplary embodiment of the present invention. As shown in Figure 13, this collision control device 1300 using man-machine collaborative operation may include a modeling module 1301, a solution module 1302, and an operation module 1303. The modeling module 1301 is configured to establish a man-machine path-following control game model corresponding to man-machine interaction behavior, based on the driver's deterministic steering torque and the driver's random steering torque. The solution module 1302 is configured to solve the path tracking control game model of the man-machine to obtain torque collision information of the man-machine. The operation module 1303 is configured to determine a shared control strategy based on the torque collision information of the man-machine, and to perform vehicle control based on the shared control strategy.

[0105] According to an exemplary embodiment of the present invention, the modeling module 1301 is configured to include a first modeling unit that establishes a first discrete state update equation for the vehicle's dynamic system by man-machine cooperative operation in a closed-loop information mode based on the driver's deterministic steering torque and the driver's random steering torque, extends the first discrete state update equation by a dynamic process of man-machine preview, obtains a path-following extension system including the man-machine preview state, and constructs a driver trajectory cost function and a driving system trajectory cost function based on the path-following extension system to obtain a man-machine path-following control game model.

[0106] According to an exemplary embodiment of the present invention, the modeling module 1301 is configured to include a second modeling unit that establishes a second discrete state update equation for the vehicle's dynamic system under man-machine cooperative operation in open-loop information mode based on the driver's deterministic steering torque and the driver's random steering torque, determines a predicted output vector in the predicted time domain based on the second discrete state update equation, determines a driver reference trajectory vector and a driving system reference trajectory vector, and constructs a driver trajectory cost function and a driving system trajectory cost function, respectively, using the predicted output vector, the driver reference trajectory vector and the driving system reference trajectory vector, thereby obtaining a man-machine path-following control game model.

[0107] According to an exemplary embodiment of the present invention, the solution module 1302 includes a first solution unit configured to determine the recursive relationship of steering control value functions corresponding to the driver and the driving system, respectively, under Nash equilibrium conditions using a random dynamic programming algorithm, and to calculate the closed-loop Nash equilibrium solutions corresponding to the driver and the driving system, respectively, as torque collision information for the man-machine, based on the first discrete state update equation and the recursive relationship.

[0108] According to an exemplary embodiment of the present invention, the solution module 1302 includes a second solution unit configured to use a random dynamic programming algorithm to determine the recursive relationship of the steering control value functions corresponding to the driver and the driving system, respectively, under the Stackelberg equilibrium conditions, determine the driver response function based on the recursive relationship of the steering control value functions corresponding to the driving system, calculate the open-loop Stackelberg equilibrium solution corresponding to the driving system based on the first discrete state update equation, the driver response function, and the recursive relationship of the steering control value functions corresponding to the driving system, and calculate the open-loop Stackelberg equilibrium solution corresponding to the driver based on the open-loop Stackelberg equilibrium solution corresponding to the driving system, thereby obtaining the torque collision information for the man-machine.

[0109] According to an exemplary embodiment of the present invention, the solution module 1302 includes a third solution unit configured to obtain a closed-form solution of a model corresponding to the man-machine path tracking control game model, thereby obtaining a relational expression between the steering control of the man-machine and the target trajectory based on the closed-form solution of the model, and to obtain an open-loop Nash equilibrium solution corresponding to the driver and the driving system, respectively, as torque collision information for the man-machine by solving the relational expression using a convex iterative algorithm.

[0110] According to an exemplary embodiment of the present invention, the solving module 1302 includes a fourth solving unit which converts the driving system trajectory cost function into a driving system trajectory optimization function that takes into account the driver response function, solves the driving system trajectory optimization function to obtain an open-loop Stackelberg equilibrium solution corresponding to the driving system, calculates an open-loop Stackelberg equilibrium solution corresponding to the driver based on the open-loop Stackelberg equilibrium solution and the driver trajectory cost function, and is configured to obtain the torque collision information of the man-machine.

[0111] The specific details of each module in the above-mentioned man-machine collaborative collision control device 1300 are described in detail in the corresponding man-machine collaborative collision control method, so the explanation is omitted here.

[0112] While the above detailed description has described several modules and units of the equipment for performing the operation, such classifications are not mandatory. In practice, according to embodiments of the present invention, the features and functions of two or more modules and units described above may be embodied in a single module and unit. Conversely, the features and functions of one module and unit described above may be further embodied by multiple modules and units.

[0113] In exemplary embodiments of the present invention, a recording medium capable of implementing the above method is further provided. Figure 14 is a schematic diagram illustrating a computer-readable recording medium in an exemplary embodiment of the present invention. As shown in Figure 14, a program product 1400 for carrying out the above method according to an embodiment of the present invention is shown, which can use a portable compact disk read-on memory (CD-ROM), contains program code, and can be executed on a terminal device such as a mobile phone. However, the program product of the present invention is not limited thereto, and in this specification, a readable recording medium can be any tangible medium that contains or stores a program that can be used by or with an instruction execution system, apparatus, or device.

[0114] In exemplary embodiments of the present invention, an electronic device capable of realizing the above method is further provided. Figure 15 is a schematic diagram illustrating the structure of a computer system of an electronic device in exemplary embodiments of the present invention.

[0115] The computer system 1500 of the electronic device shown in Figure 15 is merely an example and does not impose any limitations on the functions and scope of use of the embodiments of the present invention.

[0116] As shown in Figure 15, the computer system 1500 includes a central processing unit (CPU) 1501 and can perform various appropriate operations and processes based on programs stored in read-only memory (ROM) 1502 or programs loaded from storage unit 1508 into random access memory (RAM) 1503. RAM 1503 further stores various programs and data necessary for the operation of the system. The CPU 1501, ROM 1502, and RAM 1503 are interconnected via a bus 1504. An input / output (I / O) interface 1505 is also connected to the bus 1504.

[0117] The I / O interface 1505 is connected to an input unit 1506, including a keyboard and mouse; an output unit 1507, including devices such as a cathode ray tube (CRT), liquid crystal display (LCD), and speaker; a storage unit 1508, including a hard disk; and a communication unit 1509, including a network interface card such as a LAN (Local Area Network) card or modem. The communication unit 1509 performs communication processing via a network, such as the Internet. A driver 1510 is also connected to the I / O interface 1505 as needed. Removable media 1511, such as magnetic disks, optical disks, magneto-optical disks, and semiconductor memory, are installed in the driver 1510 as needed, and computer programs read from them are installed in the storage unit 1508 as needed.

[0118] In particular, according to embodiments of the present invention, the process described below with reference to the flowchart may be implemented as a computer software program. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for performing the method shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via a communication unit 1509 and / or installed from a removable medium 1511. When the computer program is executed by a central processing unit (CPU) 1501, it performs various functions limited to the system of the present invention.

[0119] The computer-readable medium in the embodiments of the present invention may be a computer-readable signal medium, a computer-readable recording medium, or any combination thereof. The computer-readable recording medium may be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable recording media may include, but are not limited to, an electrical connection having one or more wires, a portable computer magnetic disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the present invention, the computer-readable recording medium may be any tangible medium containing or storing a program, the program may be used by an instruction execution system, apparatus, or device, or used in conjunction with them. In the present invention, the computer-readable signal medium may include data signals propagated in the baseband or as part of a carrier wave, wherein computer-readable program code is carried therein. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium may also be any computer-readable medium other than a computer-readable recording medium that can transmit, propagate, or transmit programs for use by or in connection with instruction execution systems, apparatus, or devices. The program code contained in the computer-readable medium may be transmitted by any suitable medium, including but not limited to wireless, wires, or any suitable combination thereof.

[0120] The flowcharts and block diagrams in the drawings illustrate the feasible architectures, functions, and operations of systems, methods, and computer program products in various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or portion of code, and such module, program segment, or portion of code may contain executable instructions for implementing one or more predetermined logical functions. It should also be noted that in some alternative embodiments, the functions described in a block may be executed in an order different from that shown in the drawings. For example, two consecutively shown blocks may actually be executed substantially in parallel, or in reverse order depending on the related functions. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented in a dedicated hardware-based system for performing predetermined functions or operations, or in a combination of dedicated hardware and computer instructions.

[0121] The units according to embodiments of the present invention may be implemented in software or in hardware, and the described units may be provided in a processor. Herein, the names of these units do not limit the units themselves in some cases.

[0122] In another embodiment, the present invention further provides a computer-readable medium. The computer-readable medium may be included in the electronic device according to the above embodiment, or it may exist independently but not incorporated into the electronic device. One or more programs are placed on the computer-readable medium, and when the one or more programs are executed by the electronic device, the electronic device implements the method according to the above embodiment.

[0123] While the above detailed description has described several modules and units of the equipment for performing the operation, such classifications are not mandatory. In practice, according to embodiments of the present invention, the features and functions of two or more modules and units described above may be embodied in a single module and unit. Conversely, the features and functions of one module and unit described above may be further embodied by multiple modules and units.

[0124] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented in hardware or by combining software with the necessary hardware. For this reason, the technical solutions according to the embodiments of the present invention may be expressed in the form of a software product, which can be stored on a non-volatile storage medium (such as a CD-ROM, USB flash memory, or mobile hard disk) or on a network, and which includes several commands for causing a computer device (such as a personal computer, server, touch terminal, or network device) to perform the method described in the embodiments of the present invention.

[0125] Those skilled in the art will readily conceive of other embodiments of the present invention by considering this specification and implementing the contents disclosed herein. The present invention includes any modifications, uses, or adaptive variations to the present invention, such modifications, uses, or adaptive variations including prior art or conventional technical means of the art not disclosed herein, in accordance with the general principles of the present invention.

[0126] The present invention is not limited to the specific configurations described above and illustrated in the drawings, and various modifications and changes may be made without departing from its scope. The scope of the present invention is limited only to the appended claims.

Claims

1. A collision control method by human-machine cooperative operation, which is performed by a collision control device by human-machine cooperative operation, The steps include establishing a man-machine path tracking control game model that corresponds to man-machine interaction behavior based on the driver's deterministic steering torque and the driver's random steering torque, The steps include solving the path tracking control game model of the aforementioned man-machine to obtain torque collision information for the man-machine, The step of determining a shared control strategy based on the torque collision information of the man-machine, and then performing vehicle control based on the shared control strategy, is included. A collision control method using collaborative operation between man and machine.

2. If the man-machine path tracking control game model is a closed-loop game model, the step of establishing a man-machine path tracking control game model corresponding to the man-machine interaction behavior based on the driver's deterministic steering torque and the driver's random steering torque is: The steps include establishing a first discrete state update equation for the vehicle's dynamic system under man-machine cooperative operation in a closed-loop information mode, based on the driver's deterministic steering torque and the driver's random steering torque, The steps include extending the first discrete state update equation through a dynamic process of human-machine preview to obtain a path-tracking extension system that includes the human-machine preview state, The step of obtaining a man-machine path-tracking control game model by constructing a driver trajectory cost function and a driving system trajectory cost function based on the aforementioned path-tracking extension system. Collision control method by cooperative operation of a man-machine as described in claim 1.

3. If the man-machine path tracking control game model is an open-loop game model, the step of establishing a man-machine path tracking control game model corresponding to the man-machine interaction behavior based on the driver's deterministic steering torque and the driver's random steering torque is: The steps include establishing a second discrete state update equation for the vehicle's dynamic system under man-machine cooperative operation in open-loop information mode, based on the driver's deterministic steering torque and the driver's random steering torque, The steps include determining the predicted output vector in the prediction time domain based on the second discrete state update equation, and determining the driver reference trajectory vector and the driving system reference trajectory vector, The step of obtaining the man-machine path tracking control game model by constructing a driver trajectory cost function and a driving system trajectory cost function, respectively, using the predicted output vector, the driver reference trajectory vector, and the driving system reference trajectory vector. Collision control method by cooperative operation of a man-machine as described in claim 1.

4. The step of solving the man-machine path tracking control game model to obtain man-machine torque collision information is: The steps involve determining the recursive relationship of the steering control value functions corresponding to the driver and the driving system under Nash equilibrium conditions using a random dynamic programming algorithm, The process includes the step of calculating closed-loop Nash equilibrium solutions corresponding to the driver and the driving system, respectively, as torque collision information for the man-machine, based on the first discrete state update equation and the recursive relation. Collision control method by cooperative operation of a man-machine as described in claim 2.

5. The step of solving the man-machine path tracking control game model to obtain man-machine torque collision information is: The steps involve using a random dynamic programming algorithm to determine the recursive relationship between the steering control value functions corresponding to the driver and the driving system, respectively, under the Stackelberg equilibrium conditions, and The steps include determining the driver response function based on the recursive relationship of the steering control value function corresponding to the driving system, The steps include calculating the open-loop Stackelberg equilibrium solution corresponding to the driving system based on the recursive relationship between the first discrete state update equation, the driver response function, and the steering control value function corresponding to the driving system, The step includes calculating an open-loop Stackelberg equilibrium solution corresponding to the driver based on the open-loop Stackelberg equilibrium solution corresponding to the driving system, and using this as torque collision information for the man-machine. Collision control method by cooperative operation of a man-machine as described in claim 2.

6. The step of solving the man-machine path tracking control game model to obtain man-machine torque collision information is: The steps include obtaining a closed-form solution to the model corresponding to the man-machine path tracking control game model, thereby obtaining a relational expression between the man-machine steering control and the target trajectory based on the closed-form solution of the model, The process includes the step of solving the relational expression using a convex iterative algorithm to obtain open-loop Nash equilibrium solutions corresponding to the driver and the driving system, respectively, as torque collision information for the man-machine. Collision control method by cooperative operation of a man-machine as described in claim 3.

7. The step of solving the man-machine path tracking control game model to obtain man-machine torque collision information is: The steps include: converting the aforementioned driving system trajectory cost function into a driving system trajectory optimization function that takes into account the driver's response function; The steps include: obtaining an open-loop Stackelberg equilibrium solution corresponding to the operating system by solving the aforementioned operating system trajectory optimization function; The step includes calculating an open-loop Stackelberg equilibrium solution corresponding to the driver based on the open-loop Stackelberg equilibrium solution and the driver trajectory cost function, and using this as torque collision information for the man-machine. Collision control method by cooperative operation of a man-machine as described in claim 3.

8. A modeling module for establishing a man-machine path tracking control game model that corresponds to man-machine interaction behavior based on the driver's deterministic steering torque and the driver's random steering torque, A solution module for solving the aforementioned man-machine path tracking control game model and obtaining man-machine torque collision information, The operation module includes, by determining a shared control strategy based on the torque collision information of the man-machine, an operation module for performing vehicle control based on the shared control strategy. Collision control system using collaborative operation between man and machine.

9. A computer-readable recording medium storing a computer program, wherein when the computer program is executed by a processor, the collision control method by human-machine cooperative operation described in any one of claims 1 to 7 is realized. A computer-readable recording medium.

10. One or more processors, A memory device for storing one or more programs, When the one or more programs are executed by the one or more processors, the collision control method by cooperative operation of a man-machine as described in any one of claims 1 to 7 is implemented by the one or more processors. electronic equipment.

Images