Automatic driving vehicle longitudinal speed control system and method based on game theory

Abstract

The invention discloses an automatic driving vehicle longitudinal speed control system and method based on a game theory, and the system comprises a self-vehicle game strategy module which is used for constructing a first strategy set related to a self-vehicle longitudinal driving game, and calculating a first game income corresponding to a self-vehicle longitudinal driving game strategy; the manual driving vehicle game strategy module is used for constructing a second strategy set about the manual driving vehicle lane changing game and calculating a second game revenue corresponding to the manual driving vehicle lane changing game strategy; the game solving module is used for planning the optimal longitudinal driving track of the vehicle based on a master-slave game strategy according to the first strategy set, the second strategy set, the first game income and the second game income; according to the method, driver behavior characteristics, environmental constraints and multi-objective optimization can be comprehensively considered, game optimization between a self-driving vehicle and a manual driving vehicle is carried out, the decision robustness of a mixed driving environment is improved, unreasonable cut-in behaviors are effectively inhibited, and the collision risk is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle subsystem joint control, and in particular to a longitudinal speed control system and method for an autonomous driving vehicle based on game theory. Background Art

[0002] At present, with the rapid development of autonomous driving technology, autonomous driving vehicles have gradually been integrated into the transportation system, sharing road resources with manually driven vehicles, forming a mixed driving road environment; however, existing intelligent driving technology still has shortcomings in dealing with interactions with manually driven vehicles.

[0003] On the one hand, traditional intelligent driving decision-making methods often lack interactivity and are unable to dynamically adjust their own strategies based on the behavior of human-driven vehicles, which can easily lead to poor traffic flow or safety hazards. On the other hand, when faced with unreasonable behaviors of manually driven vehicles, such as sudden cut-ins or aggressive driving, the existing system lacks flexibility and judgment in responding. Sometimes it is too conservative, affecting driving efficiency, and sometimes it endangers driving safety due to insufficient response.

[0004] Therefore, a more advanced and intelligent solution is needed to address the decision-making issues of intelligent vehicles in mixed human-machine driving environments. Game theory, as a discipline that studies the games and interactions between different participants, provides new ideas for solving such problems due to its interactive nature. By adopting decision-making methods based on game theory, intelligent vehicles can more effectively cope with the complex behaviors of manually driven vehicles, achieve efficient and comfortable driving, and improve the operating efficiency and safety of the overall transportation system. Summary of the Invention

[0005] The purpose of the present invention is to provide a longitudinal speed control system and method for an autonomous driving vehicle based on game theory, thereby solving all or one of the above-mentioned problems existing in the prior art.

[0006] In order to solve the above technical problems, the specific technical solutions of the present invention are as follows: In one aspect, the present invention provides a longitudinal speed control system for an autonomous driving vehicle based on game theory, comprising: The vehicle game strategy module is configured to construct a first strategy set for the longitudinal driving game of the vehicle; based on the vehicle's driving state information, the neighboring vehicle's driving state information, and the first strategy set, and taking into account driving safety factors, driver and passenger riding comfort factors, and traffic efficiency factors, calculate a first game payoff corresponding to the vehicle's longitudinal driving game strategy; A manually driven vehicle game strategy module is configured to construct a second strategy set for the manually driven vehicle lane changing game; based on the manually driven vehicle's driving state information, the manually driven vehicle's neighboring vehicle's driving state information, and the second strategy set, and taking into account factors such as positional advantage, comfort, traffic efficiency, and the different driving styles of different drivers, the module calculates the second game payoff corresponding to the manually driven vehicle lane changing game strategy; a game solving module, configured to calculate an optimal strategy for the vehicle based on a master-slave game strategy according to the first strategy set, the second strategy set, the first game payoff, and the second game payoff; and plan an optimal longitudinal driving trajectory for the vehicle based on the optimal strategy for the vehicle; The environment perception module is used to cooperate with the self-vehicle game strategy module, the manually driven vehicle game strategy module and the game solving module to obtain the corresponding self-vehicle state information or neighboring vehicle state information.

[0007] As an improved solution, the vehicle is an autonomous driving vehicle; The self-driving vehicle game strategy module is specifically further used to use a quintic spline curve to establish a longitudinal driving model of the autonomous driving vehicle; based on the longitudinal driving model of the autonomous driving vehicle, the execution time and the corresponding target longitudinal position of the autonomous driving vehicle under different longitudinal driving game strategies are sampled at equal intervals, and the first strategy set is constructed based on several of the execution times and the corresponding target longitudinal positions.

[0008] As an improved solution, the autonomous vehicle game strategy module is further configured to calculate the driving safety benefit brought by the manually driven vehicle to the autonomous vehicle based on the multiple lane change options of the manually driven vehicle; The self-driving vehicle game strategy module is further configured to calculate the comfort benefit of the self-driving vehicle using the acceleration and jerk of the self-driving vehicle during a longitudinal lane change; The self-driving vehicle game strategy module is specifically further used to calculate the traffic efficiency benefit of the autonomous driving vehicle by using the difference between the real-time speed of the autonomous driving vehicle and the target speed of the autonomous driving vehicle during the longitudinal lane change of the autonomous driving vehicle.

[0009] As an improved solution, the self-vehicle game strategy module is further configured to use the sum of the driving safety benefit, the comfort benefit, and the traffic efficiency benefit as the first game benefit.

[0010] As an improved solution, the manually driven vehicle game strategy module is specifically further used to use a quintic spline curve to establish a lane changing model of the manually driven vehicle; based on the lane changing model of the manually driven vehicle, a number of lane changing times and corresponding target longitudinal positions of the manually driven vehicle are sampled at equal intervals, and the second strategy set is constructed according to the several lane changing times of the manually driven vehicle and the several target longitudinal positions of the manually driven vehicle.

[0011] As an improved solution, the manually driven vehicle game strategy module is further configured to calculate the positional advantage benefit of the manually driven vehicle based on the positional safety between the manually driven vehicle and the autonomous vehicle under different lane change selections at different driving positions of the manually driven vehicle; The manually driven vehicle game strategy module is further configured to calculate the comfort benefit of the manually driven vehicle using the jerk of the manually driven vehicle during the lane change game; The manually driven vehicle game strategy module is further configured to calculate the traffic efficiency benefit of the manually driven vehicle using the difference between the real-time speed of the manually driven vehicle and the target speed of the manually driven vehicle during the lane change game; The manually driven vehicle game strategy module is specifically used to set the manually driven vehicle aggressiveness coefficient according to the different driving styles of the drivers, and to take the weighted sum of the position advantage benefit, the comfort benefit and the traffic efficiency benefit with respect to the manually driven vehicle aggressiveness coefficient as the second game benefit.

[0012] As an improved solution, the lane change selection of the manually driven vehicle includes: Driving toward the autonomous vehicle; After driving towards the autonomous vehicle; Continue to follow the vehicle in front without changing lanes; The driving position corresponding to the lane change selection of the manually driven vehicle includes: First driving position: the manually driven vehicle is close to the autonomous vehicle and the vehicle preceding the autonomous vehicle, or the manually driven vehicle is close to the vehicle preceding the manually driven vehicle; Second driving position: the longitudinal position of the manually driven vehicle is between the autonomous vehicle and the vehicle preceding the autonomous vehicle, and the manually driven vehicle maintains a safe distance from the vehicle preceding the manually driven vehicle; A third driving position in addition to the first driving position and the second driving position.

[0013] As an improved solution, the manually driven vehicle game strategy module is specifically further used to set the real-time aggressiveness coefficient of the manually driven vehicle by adopting the master-slave non-cooperative game theory; when the aggressiveness coefficient of the manually driven vehicle approaches zero, the manually driven vehicle game strategy module judges that the manually driven vehicle is a conservative vehicle; when the aggressiveness coefficient of the manually driven vehicle approaches one, the manually driven vehicle game strategy module judges that the manually driven vehicle is an aggressive vehicle; when the aggressiveness coefficient of the manually driven vehicle is between zero and one, the manually driven vehicle game strategy module judges that the manually driven vehicle is an ordinary vehicle.

[0014] As an improved solution, the game solving module is further specifically used to: solve the optimal strategy of the self-vehicle according to the master-slave game strategy based on the first game payoff, the second game payoff, the first strategy set and the second strategy set; plan the optimal longitudinal driving trajectory of the self-vehicle according to the optimal strategy of the self-vehicle, and establish a multi-objective trajectory planning cost function; calculate the optimal target longitudinal trajectory corresponding to the optimal strategy of the self-vehicle and the optimal longitudinal vehicle speed corresponding to the optimal target longitudinal trajectory based on the multi-objective trajectory planning cost function; and control the longitudinal driving of the autonomous driving vehicle according to the optimal longitudinal vehicle speed.

[0015] On the other hand, the present invention also provides a method for controlling the longitudinal speed of an autonomous driving vehicle based on game theory, comprising the following steps: The calculation steps of the longitudinal driving game profit of the vehicle are as follows: Constructing a first strategy set for the longitudinal driving game of the own vehicle; calculating a first game payoff corresponding to the longitudinal driving game strategy of the own vehicle based on the driving state information of the own vehicle, the driving state information of the neighboring vehicle, and the first strategy set, and taking into account driving safety factors, driver and passenger riding comfort factors, and traffic efficiency factors; Steps to calculate the benefits of the lane-changing game for manually driven vehicles: Constructing a second strategy set for the lane-changing game of manually driven vehicles; calculating the second game payoff corresponding to the lane-changing game strategy of the manually driven vehicle based on the driving state information of the manually driven vehicle, the driving state information of neighboring vehicles of the manually driven vehicle, and the second strategy set, and taking into account factors such as position advantage, comfort, traffic efficiency, and different driving styles of different drivers; Comprehensive game solution steps: According to the first strategy set, the second strategy set, the first game payoff, and the second game payoff, an optimal strategy of the vehicle is calculated based on a master-slave game strategy; and an optimal longitudinal driving trajectory of the vehicle is planned according to the optimal strategy of the vehicle.

[0016] The beneficial effects of the technical solution of the present invention are: 1. The game-theory-based longitudinal velocity control system for autonomous vehicles described in this invention can establish a multidimensional game strategy model for both manually driven and autonomous vehicles through the interaction of system modules. This model comprehensively considers driver behavior, environmental constraints, and multi-objective optimization, improving decision-making robustness in mixed-driving environments. The system dynamically evaluates positional advantages and strategic benefits, effectively suppressing unreasonable cut-in behavior and reducing collision risk while balancing comfort and traffic efficiency. Real-time strategy optimization is achieved based on a master-slave game approach, ensuring rapid response in complex interactive scenarios and significantly enhancing environmental adaptability. Ultimately, this system achieves the goal of safe, efficient, and comfortable driving for autonomous vehicles, significantly outperforming traditional static decision-making schemes.

[0017] 2. The game theory-based longitudinal speed control method for an autonomous driving vehicle described in the present invention can orderly call system modules, thereby realizing the system logic of the game theory-based longitudinal speed control system for an autonomous driving vehicle described in the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 Schematic diagram of the principle architecture of the autonomous driving vehicle longitudinal speed control system based on game theory according to Example 1 of the present invention; Figure 2 The lane changing time of the manually driven vehicle in the longitudinal speed control system of the automatic driving vehicle based on game theory in Example 1 of the present invention is t i Schematic diagram of the strategy set when ; Figure 3 Schematic diagram of the vehicle's driving trajectory during the simulation of the game theory-based longitudinal speed control system for an autonomous driving vehicle according to Example 1 of the present invention; Figure 4 2. This is a schematic diagram of the estimation results of vehicle speed and driving style during the simulation of the longitudinal speed control system of the autonomous driving vehicle based on game theory according to Example 1 of the present invention; Figure 5 This is a flow chart of the method for controlling the longitudinal speed of an autonomous driving vehicle based on game theory according to Example 2 of the present invention. DETAILED DESCRIPTION

[0020] The preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby making a clearer and more precise definition of the protection scope of the present invention.

[0021] In the description of the present invention, it should be noted that the embodiments described in the present invention are only part of the embodiments of the present invention, rather than all of the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative work are within the scope of protection of the present invention.

[0022] The terms "first," "second," and the like in the specification and claims herein and in the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate so that the embodiments of the present invention described herein can be implemented in orders other than those illustrated or described herein. In addition, the terms "including" and "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or device comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such process, method, product, or device.

[0023] Example 1: This example provides a longitudinal speed control system for an autonomous driving vehicle based on game theory. Figures 1 to 4 Shown, including: (1) Environmental perception module, used to obtain the driving status information of the vehicle and neighboring vehicles; Specifically, the ego vehicle state information includes: the vehicle position and speed of the ego vehicle (EV); wherein the ego vehicle is an autonomous vehicle; Specifically, the neighboring vehicle status information includes the vehicle positions and speeds corresponding to the manually driven vehicle (HV) that is about to change lanes, the preceding vehicle (TP) in the lane where the ego vehicle is located, and the preceding vehicle (PV) in the lane where the manually driven vehicle is located.

[0024] (2) The self-vehicle game strategy module is used to calculate the self-vehicle game payoff based on its own vehicle driving status information and the neighboring vehicle driving status information; Specifically, the self-driving car game strategy module establishes the self-driving car longitudinal driving model; based on the self-driving car longitudinal driving model, the game strategy execution time and target longitudinal position of EVs within a certain range are sampled to construct a two-dimensional strategy set S EV ; Based on the two-dimensional strategy set S EV , and taking into account driving safety, driver and passenger comfort and traffic efficiency factors, calculate the game benefits corresponding to each strategy and the final total game benefits; Specifically, the above process performed by the self-driving game strategy module includes: (2.1) The self-driving car game strategy module uses a quintic spline curve to establish the longitudinal model of the autonomous vehicle, where the longitudinal position, velocity, and acceleration of the vehicle are expressed as follows: ; ; ; Among them, c i are polynomial coefficients, c0 is the longitudinal position of the vehicle at t0, c1 is the speed of the vehicle at t0, 2c2 is the acceleration of the vehicle at t0, 、 and are the coefficients to be determined in the quintic spline curve.

[0025] (2.2) Self-driving car game strategy module, collects the execution time t of different game strategies of autonomous driving vehicles f , and the corresponding target longitudinal position x f As the first strategy set of the autonomous vehicle; the first strategy set is used to characterize the response of EV to HV lane changing behavior, denoted as S EV ;S EV The number of strategies in is N EV1 ×N EV2 , S EV It is expressed as follows: .

[0026] (2.3) The self-driving game strategy module calculates the game payoff of the corresponding strategy and the final total game payoff, as follows: (2.3.1) For the autonomous vehicle EV, the human-driven vehicle HV has two different options when changing lanes, including: driving in front of the autonomous vehicle EV and driving behind the autonomous vehicle EV. These two different options will bring different driving safety benefits to the autonomous vehicle EV. The self-driving vehicle game strategy module uses the headway time T h Measuring the driving safety benefits between EVs and HVs , the specific calculation formula is as follows: ; ; Among them, w safe1 is the weight coefficient, x HV is the vertical position of HV after the game decision is completed, v HV is the speed of HV after the game decision is completed, x EV is the vertical position of EV for game decision making, v EVThe speed of the EV making the game decision; (2.3.2) Since there may be a preceding vehicle TP in the lane where the EV is located, the self-vehicle game strategy module calculates the driving safety benefit between the EV and the TP. , specifically expressed as follows: ; Among them, w safe2 is the weight coefficient, x TP is the vertical position of TP after the EV game decision is completed; (2.3.3) The self-driving game strategy module uses the acceleration and jerk during the EV's longitudinal strategy execution to represent the EV's comfort benefit. 、 , as follows: ; Among them, w comi is the weight coefficient; is the acceleration with respect to time t The calculation function of is the acceleration with respect to time t Calculation function.

[0027] (2.3.4) The self-driving game strategy module uses the difference between the EV's real-time speed and the target speed during the EV's longitudinal strategy execution to represent the corresponding traffic efficiency gain. , as follows: ; Among them, w eff is the weight coefficient, v d,EV is the target speed of the EV; (2.3.5) The self-driving car game strategy module adds the driving safety benefits, comfort benefits, and traffic efficiency benefits to obtain the total game benefits of the autonomous driving vehicle EV. (i.e. the first game payoff), specifically as follows: .

[0028] (3) A game strategy module for manually driven vehicles, which is used to calculate the game benefits of manually driven vehicles based on their own vehicle’s driving status information and the driving status information of neighboring vehicles; Specifically, the manual vehicle game strategy module establishes a manual vehicle lane-changing model. Based on the manual vehicle lane-changing model, the lane-changing time and the target longitudinal position of the HV within a certain range are sampled at equal intervals to construct the corresponding two-dimensional strategy set S HV ; Based on S HV, and taking into account the factors of position advantage, comfort, traffic efficiency and the different driving styles of different drivers, calculate the game benefits corresponding to each strategy and the final total game benefits; Specifically, the above process performed by the manually driven vehicle game strategy module includes: (3.1) The game strategy module for manually driven vehicles uses a quintic spline curve to establish a lane-changing model for manually driven vehicles. This model describes the longitudinal and lateral motion of the manually driven vehicle, as shown in the following expression: ; Where x is the longitudinal coordinate of the manually driven vehicle HV, y is the transverse coordinate of the manually driven vehicle HV, and a i (i=0,1,2,…5),b j (j=0,1,2,…5) are the polynomial coefficients of the lane-changing trajectory.

[0029] (3.2) The game strategy module for manually driven vehicles performs equally spaced sampling of the lane change time and the corresponding target longitudinal position of the manually driven vehicle HV within a certain range, and constructs the second strategy set S HV , as follows: (3.2.1) The driving time range corresponding to the lane change process is expressed as follows: ; Among them, T min is the minimum lane change time acceptable to human drivers, T max is the maximum lane changing time acceptable to human drivers, t0 is the starting time of the lane changing process, and t f is the end time of the lane changing process; (3.2.2) In T min and T max The lane changing time is sampled at equal intervals between the two times, which is expressed as follows: ; Where ΔT is the sampling time interval, N HV1 is the sampling number of lane-changing time, t m is the lane changing time of the mth sample, and the trajectory can be optimized based on different lane changing times; (3.2.3) The target lateral position of the HV for lane change is set as the target lane centerline. Considering factors such as safety and efficiency, the target longitudinal position of the HV is set as x f The value range of is as follows: ; Among them, x TP is the longitudinal position of TP after lane change, x PVis the longitudinal position of PV after lane change, x0 is the longitudinal position of HV at the current moment, and X safe For safe distance, X safe =v f *T h,min , v f is the EV speed at the end of lane change, T h,min To ensure the minimum headway for safety; (3.2.4) For x f Perform equal-interval sampling, the number of samples is N HV2， The specific expressions are as follows: ; (3.2.5) If Figure 2 , Figure 2 The horizontal axis is the different lane changing time t f , the vertical coordinate is the target longitudinal position x corresponding to different lane changing times f Based on this, considering the importance of lane changing time and target longitudinal position in the lane changing process, the game strategy module of the manually driven vehicle selects different lane changing times t f and its corresponding target longitudinal position x f As the second strategy set of the human-driven vehicle HV, it is denoted as S HV , using S HV Characterizes the response of different driver styles to the vehicle behavior, S HV The number of strategies is N HV1 ×N HV2 , S HV The specific expressions are as follows: .

[0030] (3.3) The manual driving vehicle game strategy module calculates the game payoff corresponding to each strategy and the final total game payoff, as follows: (3.3.1) When a manually driven HV changes lanes, the lane change options include: A. Before driving to the autonomous EV; B. After driving towards the autonomous EV; C. Continue to follow the vehicle PV in front without changing lanes.

[0031] (3.3.2) According to the driver's intention, lane change is usually selected in the following situations: A. When the HV is too close to the EV and TP or too close to the PV, the HV chooses to continue following the vehicle; B. When the HV's longitudinal position is between the EV and the TP, and it maintains a safe distance from other vehicles, the HV chooses to merge in front of the EV; C. In other cases, the HV chooses to merge behind the EV; The regions corresponding to the above different lane change decisions are as follows: ; Among them, x TP is the longitudinal position of the TP vehicle at the end of the lane change of the manually driven vehicle; x EV is the longitudinal position of the EV when the manually driven vehicle completes the lane change; x PV is the longitudinal position of the PV at the end of the lane change of the manually driven vehicle; x HV It is the longitudinal position of the HV when the manually driven vehicle completes the lane change.

[0032] (3.3.3) When the longitudinal position of the HV is in different regions, different lane change options are made: A. When the longitudinal position of the HV is in Region 1 and Region 2, the HV continues to follow the vehicle; B. When the longitudinal position of the HV is in Region 3, the HV will cut in front of the EV; C. When the longitudinal position of the HV is in Region 4, the HV will cut in behind the EV.

[0033] (3.3.4) Under different lane change choices, the corresponding position advantage benefits are different. When the HV chooses to drive in front of the EV, the HV will prefer to drive to the middle position between the TP and the EV and keep a safe distance from the PV. When the HV chooses to drive behind the EV, the HV will prefer to keep a safe distance from the EV and the PV. Based on this, the artificial driving vehicle game strategy module calculates the position advantage benefits of the HV as follows: ; Among them, W safe is the position benefit weight coefficient, W is the set constant; among them, hour, ; hour, ; hour, .

[0034] (3.3.5) The manual driving vehicle game strategy module uses the acceleration during the HV game to represent the comfort benefit of the HV. , as follows: ; Among them, W com is the comfort benefit weight coefficient.

[0035] (3.3.6) The manual vehicle game strategy module uses the difference between the real-time vehicle speed and the target vehicle speed during the HV game to represent the traffic efficiency gain. , as follows: ; Among them, W eff is the comfort benefit weight coefficient, v d,HV is the HV target vehicle speed.

[0036] (3.3.7) The game strategy module for manually driven vehicles takes into account the different driving styles of different drivers and converts the total game payoff function of HV into (i.e., the second game payoff) is expressed as: ; Where ρ is the aggressiveness coefficient of the manually driven vehicle; When ρ approaches 0 (e.g., ρ is within the first interval [0.01–0.3], which is set based on actual conditions), HVs are conservative vehicles. Conservative vehicles prioritize driving safety and tend to slow down to merge into the target lane, maintaining a larger safety gap between them and the vehicles in front and behind them. When ρ approaches 1 (for example, ρ is in the second interval (0.7-0.99), which is set based on actual conditions), HVs are aggressive vehicles. Aggressive vehicles tend to accelerate and merge into the target lane to gain a greater position advantage and traffic efficiency. When ρ is between 0 and 1 (for example, ρ is in the third interval [0.3-0.7], which is set according to actual conditions), the HV is an ordinary vehicle, which is between conservative vehicles and aggressive vehicles and prefers driving comfort.

[0037] (3.3.8) The game strategy module for manually driven vehicles sets up an online driving style identification method based on the master-slave non-cooperative game theory, namely, a real-time update algorithm for ρ, as follows: ; in, represents the estimated driving style of the human driver; s EV The game strategy adopted by EV; HV,observe The game strategy adopted by the human driver is obtained by the EV through sensors or vehicle-to-vehicle communication; represents the game strategy adopted by the human driver predicted by the EV at the previous moment; the human-driven vehicle game strategy module solves the above inequality in real time to obtain the estimated aggressive driving style coefficient ρ of the human-driven vehicle; it should be noted that at the initial moment, the driving style coefficient is set to ρ = 0.5 by default; at each subsequent time step, the human-driven vehicle game strategy module solves the inequality in real time based on the actual behavior of the observed HV to achieve real-time update of ρ.

[0038] (4) A game solving module is used to solve the optimal strategy of the ego vehicle based on the master-slave game strategy according to the first strategy set of the EV, the second strategy set of the HV, the first game payoff of the EV, and the second game payoff of the HV; the longitudinal planning of the ego vehicle is performed according to the solved optimal strategy of the ego vehicle, and the corresponding speed of the ego vehicle within the planned execution time is solved as follows: (4.1) Game solving module, based on the first game payoff, the second game payoff, S EV and S HV , according to the master-slave game strategy, the optimal strategy of the car is solved as follows: (4.1.1) Since TP and PV are both manually driven vehicles, it is assumed that TP and PV will not participate in the game with the vehicles behind them and TP and PV are considered as moving obstacles. Finally, considering the interaction between EV and HV, the game solving module will calculate the leader's game payoff. Described as: ; Among them, s EV EV strategy; HV is the strategy of HV; J(s EV , s HV ) indicates that EV and HV take s EV and s HV Under the strategy, the leader EV can obtain the maximum game benefit; J EV is the first game payoff; Among them, HV selects s HV When the strategy is used, the future driving trajectory of the HV is predicted in real time based on the current position and speed of the HV using the spline curve method; the EV selects s EV When choosing a strategy, the longitudinal position, speed and acceleration of the EV are calculated by combining spline curves and linear quadratic programming methods. Based on the future driving trajectory of the HV, the longitudinal position, speed and acceleration of the EV, the maximum game payoff J(s) corresponding to the selected strategy set is calculated. EV , s HV ).

[0039] (4.1.2) Considering the interaction between EV and HV, based on the master-slave game strategy and J(s EV , s HV ) The optimal strategy for calculating EV is as follows: ; ; in, is the optimal strategy of HV, is the optimal strategy for EV, i.e., the equilibrium solution; is the optimal strategy set of HV.

[0040] (4.2) Game solving module, which performs longitudinal planning of the ego vehicle based on the optimal strategy obtained, and solves the optimal speed of the ego vehicle within the execution time of the game strategy; Specifically, the game solving module establishes a multi-objective trajectory planning cost function based on the trajectory model of the quintic spline curve, and solves the optimal target longitudinal trajectory corresponding to the current game strategy execution time t based on the multi-objective trajectory planning cost function; Specifically, in the quintic spline curve, the polynomial coefficient c i The specific trajectory of the vehicle is determined. c0, c1, and 2c2 are the known state parameters of the vehicle at time t0 (same as 2.1). c3, c4, and c5 are unknown quantities and coefficients to be solved. They need to be solved by establishing an objective function. When planning the longitudinal trajectory of an EV, it is necessary to construct a longitudinal trajectory planning objective function based on comfort, efficiency, and location requirements. The specific calculation process is as follows: (4.2.1) The game solving module uses the acceleration and jerk of the EV during the execution of the longitudinal strategy to represent the comfort benefit of the EV. ,as follows: ; Among them, w coi is the comfort benefit weight coefficient.

[0041] (4.2.2) The game solving module uses the difference between the EV’s real-time speed and the target speed during the longitudinal strategy execution, as well as the difference between the EV’s speed and the target speed at the end of the longitudinal plan, to represent the traffic efficiency gain. ,as follows: ; Among them, w efi is the traffic efficiency weight coefficient, v d,EV is the target speed.

[0042] (4.2.3) The game solving module considers whether the longitudinal position of the EV at the planning end point can maintain a safe distance from the HV and TP, and expresses the position benefit based on this safe distance factor. ,as follows: ; Among them, w posi is the weight coefficient, x TP is the vertical position of TP at the end of the game, x HV is the vertical position of HV at the end of the game.

[0043] (4.2.4) The game solving module combines the above-mentioned benefit function and considers the position, velocity and acceleration constraints to obtain the multi-objective trajectory planning cost function ,as follows: ; .

[0044] (4.2.5) The game solving module uses the multi-objective trajectory planning cost function to take the longitudinal position, velocity, and acceleration of the longitudinal planning endpoint as the optimization quantity, and solves it through the QP algorithm to obtain the optimal x(t f )、v(t f )、a(t f ); Based on the following transformation, the longitudinal trajectory polynomial coefficient c is obtained i , and then based on c i Get the current t f The corresponding optimal target longitudinal trajectory, the formula is transformed as follows: .

[0045] It should be noted that this system ultimately controls the vehicle based on the solved optimal target longitudinal trajectory's longitudinal speed, and controls the above modules to operate cyclically in a logical order, continuously updating the vehicle status information and the longitudinal speed of the optimal target longitudinal trajectory to achieve continuous vehicle control until the vehicle is in a stopped state.

[0046] As a preferred embodiment of the present application, in order to verify whether the present application can improve the ability of the autonomous driving vehicle to respond to the unreasonable cutting behavior of the manually driven vehicle, a Matlab simulation program was built to conduct simulation tests as follows: (i) The driving conditions are set as follows: Simulated vehicles: the front vehicle in the left lane is a manually driven front vehicle TP and the autonomous rear vehicle EV, and the front vehicle in the right lane is a manually driven lane-changing vehicle HV; Initial longitudinal positions: TP is 100 m, PV is 140 m, EV is 40 m, and HV is 50 m. During the test, the TP and PV travel in their respective lanes at constant speeds of 12 m / s and 15 m / s, respectively. At the start of the simulation, the EV is in follow mode, following the TP at a target speed of 15 m / s. The HV travels in the right lane and, due to the slower speed of the PV, prepares to merge into the left lane. The HV's driving style is set to medium.

[0047] (ii) The final simulation results are as follows Figure 3 and Figure 4 ( Figure 3The middle horizontal axis represents the vehicle's longitudinal position, the horizontal axis represents the vehicle's lateral position, the dotted line in the middle represents the lane line dividing the left and right lanes, and the continuously curved line represents the driving trajectory of the HV). Based on these simulation results, it can be clearly seen that when responding to a moderately aggressive manually driven vehicle's cutting-in behavior, the ego vehicle is able to actively respond by accelerating to prevent the manually driven vehicle from cutting in front of the ego vehicle, thus ensuring the ego vehicle's driving efficiency and improving the intelligence of autonomous driving.

[0048] It should be noted that all the above examples are only for explaining the present invention and are not intended to limit the scope of protection of the present invention.

[0049] Example 2: This example is based on the same inventive concept as the game theory-based longitudinal speed control system for an autonomous driving vehicle described in Example 1, and provides a game theory-based longitudinal speed control method for an autonomous driving vehicle, such as Figure 5 As shown, the following steps are included: S100, the steps for calculating the benefits of the longitudinal driving game of the vehicle include: Constructing a first strategy set for the longitudinal driving game of the own vehicle; calculating a first game payoff corresponding to the longitudinal driving game strategy of the own vehicle based on the driving state information of the own vehicle, the driving state information of the neighboring vehicle, and the first strategy set, and taking into account driving safety factors, driver and passenger riding comfort factors, and traffic efficiency factors; S200, the steps for calculating the benefits of the lane-changing game of manually driven vehicles include: Constructing a second strategy set for the lane-changing game of manually driven vehicles; calculating the second game payoff corresponding to the lane-changing game strategy of the manually driven vehicle based on the driving state information of the manually driven vehicle, the driving state information of neighboring vehicles of the manually driven vehicle, and the second strategy set, and taking into account factors such as position advantage, comfort, traffic efficiency, and different driving styles of different drivers; S300, comprehensive game solution steps, including: According to the first strategy set, the second strategy set, the first game payoff, and the second game payoff, an optimal strategy of the vehicle is calculated based on a master-slave game strategy; and an optimal longitudinal driving trajectory of the vehicle is planned according to the optimal strategy of the vehicle.

[0050] Different from the existing technology, the application adopts a longitudinal speed control system and method of autonomous driving vehicles based on game theory, which can establish a multi-dimensional game strategy model for manually driven vehicles and autonomous driving vehicles, comprehensively considering the driver's behavioral characteristics, environmental constraints and multi-objective optimization, and improving the decision-making robustness in mixed driving environments; this system can dynamically evaluate position advantages and strategic benefits, effectively suppress unreasonable cutting-in behaviors and reduce collision risks, while balancing comfort and traffic efficiency; based on the master-slave game method, real-time strategy optimization is achieved to ensure that the vehicle responds quickly in complex interactive scenarios, significantly enhance environmental adaptability, and ultimately achieve the safe, efficient and comfortable driving goals of autonomous driving vehicles, which is significantly better than traditional static decision-making solutions.

[0051] It should be understood that in the various embodiments of this document, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this document.

[0052] It should also be understood that in the embodiments herein, the term "and / or" merely describes an association between associated objects, indicating that three possible relationships exist. For example, "A and / or B" could represent: A alone, A and B simultaneously, or B alone. Furthermore, the character " / " in this document generally indicates an "or" relationship between the associated objects.

[0053] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this document.

[0054] Those skilled in the art will clearly understand that, for the sake of convenience and brevity of description, the specific logical process of the method described above can refer to the corresponding working processes of the systems, devices and units in the aforementioned method embodiments, and will not be repeated here.

[0055] In the several embodiments provided herein, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices, or units, or can be an electrical, mechanical, or other form of connection.

[0056] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments herein.

[0057] In addition, the functional units in the various embodiments herein may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0058] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this article is essentially or the part that contributes to the existing technology, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of this article. The aforementioned storage medium includes: various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0059] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention's description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A longitudinal speed control system for an autonomous driving vehicle based on game theory, characterized in that: include: The ego vehicle game strategy module is used to construct a first strategy set for the longitudinal driving game of the ego vehicle; Calculating a first game payoff corresponding to the longitudinal driving game strategy of the vehicle based on the vehicle's driving state information, the neighboring vehicle's driving state information, and the first strategy set, and taking into account driving safety factors, driver and passenger riding comfort factors, and traffic efficiency factors; A manually driven vehicle game strategy module is configured to construct a second strategy set for the manually driven vehicle lane changing game; based on the manually driven vehicle's driving state information, the manually driven vehicle's neighboring vehicle's driving state information, and the second strategy set, and taking into account factors such as positional advantage, comfort, traffic efficiency, and the different driving styles of different drivers, the module calculates the second game payoff corresponding to the manually driven vehicle lane changing game strategy; a game solving module, configured to calculate an optimal strategy for the ego vehicle based on the first strategy set, the second strategy set, the first game payoff, and the second game payoff, and based on a master-slave game strategy; and plan an optimal longitudinal driving trajectory for the ego vehicle based on the optimal strategy for the ego vehicle; The environment perception module is used to cooperate with the self-vehicle game strategy module, the manually driven vehicle game strategy module and the game solving module to obtain the corresponding self-vehicle state information or neighboring vehicle state information.

2. The game theory-based autonomous driving vehicle longitudinal speed control system according to claim 1, characterized in that: The self-vehicle is an autonomous vehicle; The self-driving vehicle game strategy module is further specifically used to: use a quintic spline curve to establish a longitudinal driving model of the autonomous driving vehicle; based on the longitudinal driving model of the autonomous driving vehicle, sample the execution time and corresponding target longitudinal position of the autonomous driving vehicle under different longitudinal driving game strategies at equal intervals, and construct the first strategy set based on several of the execution times and corresponding target longitudinal positions.

3. The game theory-based longitudinal speed control system for an autonomous driving vehicle according to claim 2, characterized in that: The self-driving vehicle game strategy module is further configured to calculate the driving safety benefit of the manually driven vehicle to the autonomous vehicle based on the multiple lane change options of the manually driven vehicle; The self-driving vehicle game strategy module is further configured to calculate the comfort benefit of the self-driving vehicle based on the acceleration and jerk of the self-driving vehicle during the longitudinal lane change process; The self-driving vehicle game strategy module is further specifically used to calculate the traffic efficiency benefit of the autonomous driving vehicle based on the difference between the real-time speed of the autonomous driving vehicle and the target speed of the autonomous driving vehicle during the longitudinal lane change process of the autonomous driving vehicle.

4. The game theory-based longitudinal speed control system for an autonomous driving vehicle according to claim 3, characterized in that: The self-vehicle game strategy module is further specifically configured to: set the sum of the driving safety benefit, the comfort benefit, and the traffic efficiency benefit as the first game benefit.

5. The game theory-based longitudinal speed control system for an autonomous driving vehicle according to claim 1, characterized in that: The manually driven vehicle game strategy module is further specifically used to: establish a lane-changing model of the manually driven vehicle using a quintic spline curve; based on the lane-changing model of the manually driven vehicle, sample a number of lane-changing times and corresponding target longitudinal positions of the manually driven vehicle at equal intervals, and construct a second strategy set according to the number of lane-changing times of the manually driven vehicle and the number of target longitudinal positions of the manually driven vehicle.

6. The game theory-based autonomous driving vehicle longitudinal speed control system according to claim 1, characterized in that: The manually driven vehicle game strategy module is further configured to calculate the positional advantage benefit of the manually driven vehicle based on the positional safety between the manually driven vehicle and the autonomous vehicle under different lane change selections at different driving positions of the manually driven vehicle; The manually driven vehicle game strategy module is further configured to calculate the comfort benefit of the manually driven vehicle using the jerk of the manually driven vehicle during the lane change game; The manually driven vehicle game strategy module is further configured to calculate the traffic efficiency benefit of the manually driven vehicle by using the difference between the real-time speed of the manually driven vehicle and the target speed of the manually driven vehicle during the lane change game; The manually driven vehicle game strategy module is further specifically used to: set the manually driven vehicle aggressiveness coefficient according to the driver's different driving style, and take the weighted sum of the position advantage benefit, the comfort benefit and the traffic efficiency benefit with respect to the manually driven vehicle aggressiveness coefficient as the second game benefit.

7. The game theory-based longitudinal speed control system for an autonomous driving vehicle according to claim 6, characterized in that: The lane change selection of the manually driven vehicle includes: Driving toward the autonomous vehicle; After driving towards the autonomous vehicle; Continue to follow the vehicle in front without changing lanes; The driving position corresponding to the lane change selection of the manually driven vehicle includes: First driving position: the manually driven vehicle is close to the autonomous vehicle and the vehicle preceding the autonomous vehicle, or the manually driven vehicle is close to the vehicle preceding the manually driven vehicle; Second driving position: the longitudinal position of the manually driven vehicle is between the autonomous vehicle and the vehicle preceding the autonomous vehicle, and the manually driven vehicle maintains a safe distance from the vehicle preceding the manually driven vehicle; Third driving position: a driving position other than the first driving position and the second driving position.

8. The game theory-based longitudinal speed control system for an autonomous driving vehicle according to claim 6, characterized in that: The manually driven vehicle game strategy module is further configured to: set a real-time aggressiveness coefficient of the manually driven vehicle using a master-slave non-cooperative game theory; when the aggressiveness coefficient of the manually driven vehicle is within a first interval, the manually driven vehicle game strategy module determines that the manually driven vehicle is a conservative vehicle; when the aggressiveness coefficient of the manually driven vehicle is within a second interval, the manually driven vehicle game strategy module determines that the manually driven vehicle is an aggressive vehicle; when the aggressiveness coefficient of the manually driven vehicle is within a third interval, the manually driven vehicle game strategy module determines that the manually driven vehicle is a normal vehicle; The first interval corresponds to a value of zero, the second interval corresponds to a value of one, and the third interval is located between the first interval and the second interval.

9. The game theory-based longitudinal speed control system for an autonomous driving vehicle according to claim 1, characterized in that: The game solving module is further specifically used to: solve the optimal strategy of the self-driving vehicle according to the master-slave game strategy based on the first game payoff, the second game payoff, the first strategy set and the second strategy set; plan the optimal longitudinal driving trajectory of the self-driving vehicle according to the optimal strategy of the self-driving vehicle, and establish a multi-objective trajectory planning cost function; calculate the optimal target longitudinal trajectory corresponding to the optimal strategy of the self-driving vehicle and the optimal longitudinal vehicle speed corresponding to the optimal target longitudinal trajectory based on the multi-objective trajectory planning cost function; and control the longitudinal driving of the autonomous driving vehicle according to the optimal longitudinal vehicle speed.

10. A method for controlling the longitudinal speed of an autonomous driving vehicle based on game theory, characterized in that: The following steps are involved: The calculation steps of the longitudinal driving game profit of the vehicle are as follows: Constructing a first strategy set for the longitudinal driving game of the own vehicle; calculating a first game payoff corresponding to the longitudinal driving game strategy of the own vehicle based on the driving state information of the own vehicle, the driving state information of the neighboring vehicle, and the first strategy set, and taking into account driving safety factors, driver and passenger riding comfort factors, and traffic efficiency factors; Steps to calculate the benefits of the lane-changing game for manually driven vehicles: Constructing a second strategy set for the lane-changing game of manually driven vehicles; calculating the second game payoff corresponding to the lane-changing game strategy of the manually driven vehicle based on the driving state information of the manually driven vehicle, the driving state information of neighboring vehicles of the manually driven vehicle, and the second strategy set, and taking into account factors such as position advantage, comfort, traffic efficiency, and different driving styles of different drivers; Comprehensive game solution steps: According to the first strategy set, the second strategy set, the first game payoff, and the second game payoff, an optimal strategy of the vehicle is calculated based on a master-slave game strategy; and an optimal longitudinal driving trajectory of the vehicle is planned according to the optimal strategy of the vehicle.

Images