Vehicle emergency risk avoiding control system and method in pedestrian-vehicle conflict scene

Abstract

The invention belongs to the technical field of automobile intelligent control methods, and particularly relates to a vehicle emergency risk avoiding control method in a man-vehicle conflict scene, which comprises the following steps of: firstly, defining a brake control parameter and a steering control parameter of a vehicle, constructing a vehicle kinematic model, and solving a vehicle risk avoiding track based on the brake control parameter and the steering control parameter of the vehicle; and then constructing a human-vehicle conflict simulation model, solving pedestrian collision damage based on the vehicle risk avoiding track, finally constructing a multi-target optimization algorithm, and optimizing brake control parameters and steering control parameters of the vehicle by taking the minimum pedestrian collision damage as a target to serve as a vehicle emergency risk avoiding strategy. According to the vehicle emergency risk avoiding control method disclosed by the invention, an overall optimization framework of the vehicle risk avoiding track, the pedestrian-vehicle conflict simulation and the pedestrian collision damage is constructed, so that the solution of the vehicle emergency risk avoiding strategy with the minimum pedestrian collision damage is realized, and an effective vehicle control optimization method is provided when a collision accident cannot be avoided; and the driving safety is improved.

Description

Technical Field

[0001] This invention belongs to the technical field of automotive intelligent control methods, specifically relating to a vehicle emergency avoidance control system and method for human-vehicle conflict scenarios. Background Technology

[0002] In complex road environments where pedestrians and vehicles share the road, the unpredictable nature of pedestrian movement means that traditional collision protection measures are ineffective in ensuring pedestrian safety.

[0003] In existing technologies, vehicle active control schemes typically employ intelligent driving technologies such as Automatic Emergency Braking (AEB), Automatic Emergency Steering (AES), and vehicle-road coordination to implement emergency avoidance measures just before an accident occurs, thereby reducing the probability of accidents. Some vehicle active control schemes determine the vehicle's trajectory based on a vehicle dynamics model and a feasibility set, thus solving the collision-free trajectory planning problem for autonomous vehicles on highways. Furthermore, some vehicle active control schemes combine four-wheel steering, active rear steering, and differential braking through adaptive model predictive control, proposing a comprehensive collision avoidance strategy for autonomous vehicles in emergency situations based on steering and braking.

[0004] However, the main solutions in the existing technology are to avoid collisions between vehicles and pedestrians. Due to the complexity and unpredictability of the traffic environment, the existing active vehicle control methods cannot completely avoid collisions. They can only reduce the probability of accidents to a certain extent, and they will still cause great harm to pedestrians when a collision occurs. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to overcome the shortcomings of the existing vehicle active control schemes, which cannot completely avoid collision accidents and still cause great harm to pedestrians when a collision occurs, thereby providing a vehicle emergency avoidance control system and method for human-vehicle conflict scenarios.

[0006] A method for emergency vehicle avoidance control in a pedestrian-vehicle conflict scenario includes the following steps: Define the vehicle's braking control parameters and steering control parameters; Construct a vehicle kinematic model and solve the vehicle's avoidance trajectory based on the vehicle's braking control parameters and steering control parameters; Construct a simulation model of pedestrian-vehicle conflict and solve pedestrian collision damage based on the vehicle's avoidance trajectory; A multi-objective optimization algorithm is constructed to optimize the vehicle's braking and steering control parameters with the goal of minimizing pedestrian collision damage, serving as an emergency avoidance strategy for the vehicle.

[0007] Furthermore, spatial constraints are constructed for the vehicle's avoidance trajectory, and braking control parameters and steering control parameters that do not meet the spatial constraints are filtered out; the spatial constraints include longitudinal constraints, lateral constraints and rotational constraints.

[0008] Furthermore, in the spatial constraints, the longitudinal constraint requires that the longitudinal movement distance of the vehicle's avoidance trajectory be less than the preset braking distance; the lateral constraint requires that the lateral movement distance of the vehicle's avoidance trajectory be less than the preset lateral distance; and the rotation constraint requires that the absolute value of the heading angle of the vehicle's avoidance trajectory be less than the preset angle.

[0009] Furthermore, the braking control parameters are segmented braking, including a first-stage braking deceleration, a first-stage braking duration, a second-stage braking duration, a third-stage braking deceleration, and a third-stage braking duration. The braking control parameters control the vehicle to brake with the first-stage braking deceleration and the first-stage braking duration during emergency avoidance control, then stop braking with the second-stage braking duration, and then brake with the third-stage braking deceleration and the third-stage braking duration to bring the vehicle speed to zero.

[0010] Furthermore, the steering control parameters are reciprocating steering parameters, which include a first-stage steering angle acceleration, a first-stage steering duration, a second-stage steering angle acceleration, and a second-stage steering duration. The steering directions of the first and second stages are opposite. The steering control parameters control the vehicle to first steer with the first-stage steering angle acceleration and the first-stage steering duration during emergency avoidance control, and then steer with the second-stage steering angle acceleration and the second-stage steering duration.

[0011] Furthermore, the vehicle avoidance trajectory includes the horizontal coordinate, vertical coordinate, and heading angle of the vehicle at each moment during the emergency avoidance control process.

[0012] Furthermore, the multi-objective optimization algorithm is a fast non-dominated sorting genetic algorithm with an elite retention strategy. The multi-objective optimization algorithm calculates the Pareto optimal solution set of the vehicle's braking control parameters and steering control parameters, and the vehicle's emergency avoidance strategy is generated from the Pareto optimal solution set.

[0013] Furthermore, the optimization objective of the multi-objective optimization algorithm includes the peak acceleration of the pedestrian's head, which includes the peak acceleration of the first collision and the peak acceleration of the second collision. The peak acceleration of the first collision is generated when the pedestrian's head comes into contact with the vehicle, and the peak acceleration of the second collision is generated when the pedestrian's head comes into contact with the ground when the pedestrian lands.

[0014] Furthermore, the optimization objective of the multi-objective optimization algorithm includes the pedestrian's head injury value, expressed as: ; in, a ( t () indicates the combined acceleration of the head. g It represents the acceleration due to gravity.

[0015] A vehicle emergency avoidance control system for human-vehicle conflict scenarios is provided to implement the aforementioned vehicle emergency avoidance control method.

[0016] The vehicle emergency avoidance control system includes a design optimization platform, a technical computing environment, and human dynamics simulation software. The design optimization platform is used to define the vehicle's braking control parameters and steering control parameters; and to construct a multi-objective optimization algorithm, with the goal of minimizing pedestrian collision damage, to optimize the vehicle's braking control parameters and steering control parameters as an emergency avoidance strategy for the vehicle. The technical computing environment is used to solve the vehicle's hazard avoidance trajectory based on the vehicle's braking control parameters and steering control parameters. The human dynamics simulation software is used to solve pedestrian collision damage based on vehicle avoidance trajectories.

[0017] Beneficial Effects: This invention discloses a vehicle emergency avoidance control method for pedestrian-vehicle conflict scenarios. First, it defines the vehicle's braking and steering control parameters, constructs a vehicle kinematic model, and solves for the vehicle's avoidance trajectory based on these parameters. Then, it constructs a pedestrian-vehicle conflict simulation model and solves for pedestrian collision damage based on the vehicle's avoidance trajectory. Finally, it constructs a multi-objective optimization algorithm to optimize the vehicle's braking and steering control parameters with the goal of minimizing pedestrian collision damage, serving as the vehicle's emergency avoidance strategy. The vehicle emergency avoidance control method disclosed in this invention constructs an overall optimization framework for vehicle avoidance trajectory, pedestrian-vehicle conflict simulation, and pedestrian collision damage, thereby achieving a solution for the vehicle emergency avoidance strategy that minimizes pedestrian collision damage. This provides an effective vehicle control optimization method when collisions are unavoidable, improving driving safety. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart of the vehicle emergency avoidance control method of the present invention; Figure 2 This is a schematic diagram of the braking control parameters of the present invention; Figure 3 This is a schematic diagram of the steering control parameters of the present invention. Detailed Implementation

[0020] To make the above-mentioned objectives, features, and advantages of this application more apparent and understandable, the specific embodiments of this application are described in detail below with reference to the accompanying drawings. Many specific details are set forth in the following description to provide a thorough understanding of this application. However, this application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar modifications without departing from the spirit of this application. Therefore, this application is not limited to the specific embodiments disclosed below.

[0021] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0022] Example 1: Reference Figure 1 As shown, this embodiment provides a vehicle emergency avoidance control method for pedestrian-vehicle conflict scenarios, including the following steps: Step S1: Define the vehicle's braking control parameters and steering control parameters; Step S2: Construct a vehicle kinematic model and solve the vehicle's avoidance trajectory based on the vehicle's braking control parameters and steering control parameters; Step S3: Construct a simulation model of pedestrian-vehicle conflict and solve for pedestrian collision damage based on the vehicle's avoidance trajectory; Step S4: Construct a multi-objective optimization algorithm to optimize the vehicle's braking and steering control parameters with the goal of minimizing pedestrian collision damage, as an emergency avoidance strategy for the vehicle.

[0023] In step S1, the vehicle's braking control parameters are defined. a ( t and steering control parameters t ( t In this embodiment, vehicle braking control parameters a ( t and steering control parameters t ( t Defined via ISIGHT software.

[0024] Reference Figure 2As shown, the braking control parameters a ( t (This refers to segmented braking, where the braking control parameters include the first-stage braking deceleration.) A 1. Duration of the first stage of braking t 1. Duration of the second phase t 2- t 1. Third-stage braking deceleration A 2 and third stage braking duration t 3- t 2; The braking control parameters control the vehicle during emergency avoidance control, initially using a first-stage braking deceleration. A 1. Braking during the first stage of braking duration. t 1, then for the duration of the second phase t 2- t 1. Stop braking, then decelerate using the third stage of braking. A Braking is performed during the second and third stage braking durations. t 3- t 2, in t At time 3, the vehicle's speed is brought to zero. In this embodiment, the vehicle brakes by first decelerating, then maintaining a constant speed, and then decelerating again.

[0025] Reference Figure 3 As shown, the steering control parameters t ( t For reciprocating steering, the steering control parameters include the first-stage steering angular acceleration. N a Duration of the first stage of the turn t a Second stage steering angle acceleration N b Second-stage turning duration t b - t a The steering directions in the first and second stages are opposite; the steering control parameters control the vehicle during emergency avoidance control, initially using the first stage steering angle acceleration. N a and the duration of the first stage turn t a To turn, then use the second stage of steering angular acceleration. N b Second-stage turning duration t b - t a To turn, in t cThe vehicle decelerates to zero speed. In this embodiment, the vehicle's steering angle changes according to a sinusoidal law.

[0026] In step S2, a vehicle kinematic model is constructed, and the vehicle's avoidance trajectory is solved based on the vehicle's braking control parameters and steering control parameters. (Based on the vehicle's braking control parameters...) a ( t and steering control parameters t ( t This can be used to deduce the vehicle speed. v ( t ), displacement s ( t ), and angular velocity oh ( t ) and heading angle i ( t ), represented as: ; ; ; .

[0027] In this embodiment, the vehicle kinematics model is constructed and solved using MATLAB.

[0028] Assume the vehicle is in O The coordinates at position 1 are ( x 1, y 1) The heading angle is i 1. When the vehicle i The heading angle of 2 moves to O When the position is 2, its coordinates can be derived. x 2, y 2) To further obtain the vehicle's hazard avoidance trajectory. f ( t , x , y , i The vehicle's avoidance trajectory includes the horizontal coordinate, vertical coordinate, and heading angle of the vehicle at each moment during the emergency avoidance control process, expressed as: ; .

[0029] As a further improvement to this embodiment, after obtaining the vehicle's avoidance trajectory, spatial constraints are constructed for the vehicle's avoidance trajectory, and braking control parameters and steering control parameters that do not meet the spatial constraints are filtered out; the spatial constraints include longitudinal constraints. W 1. Lateral constraints W2 and rotation constraints W 3.

[0030] In this embodiment, the obtained vehicle avoidance trajectory is input into the ISIGHT software, and it is determined whether the spatial constraints are met. If not, the vehicle braking control parameters are reselected. a ( t and steering control parameters t ( t The system calculates the vehicle's avoidance trajectory and, if the conditions are met, imports the vehicle trajectory into the MADYMO software.

[0031] In spatial constraints, longitudinal constraints W 1. The longitudinal movement distance of the vehicle's avoidance trajectory must be less than a preset braking distance. In this embodiment, the vehicle needs to reduce its speed to zero during braking, and the braking distance must be less than the braking distance specified in the national standard. The constraint requires controlling the integral area of ​​the braking acceleration to meet the deceleration requirements, and simultaneously, when the vehicle decelerates to 0, its displacement and heading angle no longer change, and the vehicle comes to a stop.

[0032] Lateral constraints W 2. The lateral movement distance of the vehicle's avoidance trajectory must be less than a preset lateral distance. Specifically, this constraint means that the horizontal displacement caused by the vehicle's steering cannot exceed the lane width. D r The maximum space a vehicle can occupy during a turn is l If a vehicle is traveling in the middle of the lane, then the absolute value of the vehicle's maximum lateral displacement should be less than half the difference between the lane width and the space occupied by the vehicle, expressed as: .

[0033] Rotational constraints W 3. The absolute value of the heading angle of the vehicle's avoidance trajectory is required to be less than a preset angle. In this embodiment, the absolute value of the vehicle's heading angle is required to be less than 30 degrees, so as to avoid the vehicle from experiencing sudden and violent rotation during the turning process, which would cause the vehicle to become unstable.

[0034] In step S3, a pedestrian-vehicle conflict simulation model is constructed, and pedestrian collision damage is solved based on the vehicle's avoidance trajectory. The pedestrian collision damage includes the pedestrian's peak head acceleration and head injury value.

[0035] In this embodiment, the pedestrian-vehicle conflict simulation model is constructed using MADYMO software, and the pedestrian collision damage is solved.

[0036] Peak head acceleration includes peak acceleration from a single impact. ACC Peak accelerations of the first and second collisions ACC 2, the peak value of the first collision acceleration ACC1 represents the peak value of the secondary collision acceleration generated by the pedestrian's head contacting the vehicle. ACC 2 is generated when a pedestrian's head comes into contact with the ground upon landing.

[0037] The head injury value of a pedestrian is expressed as: ; in, a ( t () indicates the combined acceleration of the head. g It represents the acceleration due to gravity.

[0038] In step S4, a multi-objective optimization algorithm is constructed to optimize the vehicle's braking and steering control parameters with the goal of minimizing pedestrian collision damage, serving as the vehicle's emergency avoidance strategy. The multi-objective optimization algorithm is a fast non-dominated sorting genetic algorithm (NSGA-II) with an elite preservation strategy. This algorithm calculates the Pareto optimal solution set for the vehicle's braking and steering control parameters, and the vehicle's emergency avoidance strategy is generated from this Pareto optimal solution set.

[0039] In this embodiment, thresholds are set for peak head acceleration and head injury value according to regulations to unify the dimensions. Peak head acceleration and head injury value are weighted in a 1:3 ratio, and the "inflection point" in the Pareto optimal solution set is selected as the vehicle's emergency avoidance strategy. This can significantly reduce peak head acceleration while slightly increasing the head injury value.

[0040] In this embodiment, the multi-objective optimization algorithm is constructed using ISIGHT software and Pareto optimal solution set is calculated to obtain the vehicle emergency avoidance strategy.

[0041] In this embodiment, the optimization objective of the multi-objective optimization algorithm includes the peak head acceleration and head injury value of the pedestrian.

[0042] Working principle: During vehicle operation, the vehicle emergency avoidance control system is activated to acquire the pedestrian's position and the vehicle's speed, direction, and maximum deceleration. Based on the maximum deceleration, the vehicle's braking and steering control parameters are defined. The vehicle's avoidance trajectory is then calculated based on these parameters. Data satisfying spatial constraints is selected from the pedestrian's position and the vehicle's avoidance trajectory. Pedestrian collision damage is calculated based on the vehicle's avoidance trajectory. A multi-objective optimization algorithm is used to optimize the vehicle's braking and steering control parameters, with the goal of minimizing pedestrian collision damage, as the vehicle's emergency avoidance strategy. The vehicle then implements control according to this strategy. The vehicle model in the vehicle conflict simulation model is customized based on the specific vehicle being used.

[0043] The vehicle emergency avoidance control method provided in this embodiment constructs an overall optimization framework for vehicle avoidance trajectory, pedestrian-vehicle conflict simulation, and pedestrian collision damage, thereby solving the vehicle emergency avoidance strategy with minimum pedestrian collision damage. This provides an effective vehicle control optimization method when collision accidents are unavoidable, improving driving safety.

[0044] Example 2: This embodiment provides a vehicle emergency avoidance control system for human-vehicle conflict scenarios, used to implement the above-mentioned vehicle emergency avoidance control method.

[0045] The vehicle emergency avoidance control system includes a design optimization platform, a technical computing environment, and human dynamics simulation software. The design optimization platform is used to define the vehicle's braking control parameters and steering control parameters; and to construct a multi-objective optimization algorithm to optimize the vehicle's braking control parameters and steering control parameters as an emergency avoidance strategy for the vehicle, with the goal of minimizing pedestrian collision damage.

[0046] The technical computing environment is used to solve the vehicle's hazard avoidance trajectory based on the vehicle's braking control parameters and steering control parameters. The human dynamics simulation software is used to solve pedestrian collision damage based on vehicle avoidance trajectories.

[0047] In this embodiment, the design optimization platform is preferably ISIGHT software, the technical computing environment is preferably MATLAB, and the human body dynamics simulation software is preferably MADYMO.

[0048] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0049] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for emergency vehicle avoidance control in a pedestrian-vehicle conflict scenario, characterized in that, The following methods and steps are included: Define the vehicle's braking control parameters and steering control parameters; Construct a vehicle kinematic model and solve the vehicle's avoidance trajectory based on the vehicle's braking control parameters and steering control parameters; Construct a simulation model of pedestrian-vehicle conflict and solve pedestrian collision damage based on the vehicle's avoidance trajectory; A multi-objective optimization algorithm is constructed to optimize the vehicle's braking and steering control parameters with the goal of minimizing pedestrian collision damage, serving as an emergency avoidance strategy for the vehicle.

2. The vehicle emergency avoidance control method for a pedestrian-vehicle conflict scenario according to claim 1, characterized in that, Also includes: Spatial constraints are constructed for the vehicle's avoidance trajectory, and braking control parameters and steering control parameters that do not meet the spatial constraints are filtered out; the spatial constraints include longitudinal constraints, lateral constraints and rotational constraints.

3. The vehicle emergency avoidance control method for a pedestrian-vehicle conflict scenario according to claim 2, characterized in that, In the spatial constraints, the longitudinal constraint requires that the longitudinal movement distance of the vehicle's avoidance trajectory be less than the preset braking distance; the lateral constraint requires that the lateral movement distance of the vehicle's avoidance trajectory be less than the preset lateral distance; and the rotation constraint requires that the absolute value of the heading angle of the vehicle's avoidance trajectory be less than the preset angle.

4. The vehicle emergency avoidance control method for a pedestrian-vehicle conflict scenario according to claim 1, characterized in that, The braking control parameters are segmented braking, including a first-stage braking deceleration, a first-stage braking duration, a second-stage braking duration, a third-stage braking deceleration, and a third-stage braking duration. The braking control parameters control the vehicle to brake with the first-stage braking deceleration and the first-stage braking duration during emergency avoidance control, then stop braking with the second-stage braking duration, and finally brake with the third-stage braking deceleration and the third-stage braking duration to bring the vehicle speed to zero.

5. The vehicle emergency avoidance control method for a pedestrian-vehicle conflict scenario according to claim 1, characterized in that, The steering control parameters are reciprocating steering parameters, which include a first-stage steering angle acceleration, a first-stage steering duration, a second-stage steering angle acceleration, and a second-stage steering duration. The steering directions of the first and second stages are opposite. The steering control parameters control the vehicle to first steer with the first-stage steering angle acceleration and the first-stage steering duration during emergency avoidance control, and then steer with the second-stage steering angle acceleration and the second-stage steering duration.

6. The vehicle emergency avoidance control method for a pedestrian-vehicle conflict scenario according to claim 1, characterized in that, The vehicle avoidance trajectory includes the horizontal coordinate, vertical coordinate, and heading angle of the vehicle at each moment during the emergency avoidance control process.

7. The vehicle emergency avoidance control method for a pedestrian-vehicle conflict scenario according to claim 1, characterized in that, The multi-objective optimization algorithm is a fast non-dominated sorting genetic algorithm with an elite retention strategy. The multi-objective optimization algorithm calculates the Pareto optimal solution set of the vehicle's braking control parameters and steering control parameters, and the vehicle's emergency avoidance strategy is generated from the Pareto optimal solution set.

8. The vehicle emergency avoidance control method for a pedestrian-vehicle conflict scenario according to claim 7, characterized in that, The optimization objective of the multi-objective optimization algorithm includes the peak head acceleration of the pedestrian, which includes the peak acceleration of the primary collision and the peak acceleration of the secondary collision. The peak acceleration of the primary collision occurs when the pedestrian's head comes into contact with the vehicle, and the peak acceleration of the secondary collision occurs when the pedestrian's head comes into contact with the ground upon landing.

9. A vehicle emergency avoidance control method for a pedestrian-vehicle conflict scenario according to claim 7, characterized in that, The optimization objective of the multi-objective optimization algorithm includes the pedestrian's head injury value, expressed as: ； in, a ( t () indicates the combined acceleration of the head. g It represents the acceleration due to gravity.

10. A vehicle emergency avoidance control system for pedestrian-vehicle conflict scenarios, characterized in that, Used to implement the vehicle emergency avoidance control method according to any one of claims 1-9; The vehicle emergency avoidance control system includes a design optimization platform, a technical computing environment, and human dynamics simulation software. The design optimization platform is used to define the vehicle's braking control parameters and steering control parameters; It is used to construct a multi-objective optimization algorithm, with the goal of minimizing pedestrian collision damage, to optimize the vehicle's braking control parameters and steering control parameters as an emergency avoidance strategy for the vehicle. The technical computing environment is used to solve the vehicle's hazard avoidance trajectory based on the vehicle's braking control parameters and steering control parameters. The human dynamics simulation software is used to solve pedestrian collision damage based on vehicle avoidance trajectories.

Images