Shared steering control method for human-machine conflict resolution

Abstract

This invention provides a shared steering control method for resolving human-machine conflict. The vehicle's autonomous driving system tracks the vehicle's trajectory in real time, determines the steering angle intention of the autonomous driving system based on the vehicle trajectory parameters, and considers the driver's steering operation intention in real time. It also dynamically adjusts the driving authority during the process. Simultaneously, it judges whether a human-machine conflict has occurred based on the overall driving system and the driver's steering intention. When a human-machine conflict occurs, the path is replanned, and the front wheel steering angle is determined comprehensively based on the two driving intentions. This ensures the driver's driving experience, ensures the driver's trust in the autonomous driving system, and ultimately ensures driving safety, reducing the possibility of traffic accidents.

Description

Technical Field

[0001] This invention relates to an autonomous driving control method, and more particularly to a shared steering control method for resolving human-machine conflict. Background Technology

[0002] Autonomous driving technology can significantly improve vehicle safety and is classified into six levels. Level 5 represents the highest level of autonomous driving technology and is the ultimate goal. However, developing higher levels of autonomous driving technology means facing greater technical challenges and requiring higher R&D costs. Therefore, before achieving Level 5 autonomous driving technology, i.e., for Level 3 and Level 4 driving systems, human-machine co-driving technology is currently a recognized alternative solution, with relatively lower implementation difficulty and costs.

[0003] Shared steering control systems are one such example. This technology, based on steer-by-wire or front-wheel active steering systems, enables human-machine co-driving, reducing the safety risks associated with driver error. Shared steering control systems have two control units—the driver and the autonomous driving system.

[0004] In existing technologies, there are two methods for switching driving authority levels: rule-based driving authority allocation and Nash equilibrium-based optimization methods. However, when human-machine conflicts occur, existing methods cannot ensure the driver's driving intentions or take into account the driver's driving experience. For example, in obstacle avoidance scenarios, when there are multiple obstacle avoidance routes and the solution proposed by the driver is completely opposite to that proposed by the autonomous driving system, simply adjusting driving authority cannot take into account the driver's driving intentions. This may amplify human-machine conflicts, cause the driver to distrust the autonomous driving system, threaten the vehicle's driving safety, and even cause serious traffic accidents.

[0005] Therefore, in order to solve the above-mentioned technical problems, it is urgent to propose a new technical approach. Summary of the Invention

[0006] In view of this, the purpose of this invention is to provide a shared steering control method for resolving human-machine conflict. The vehicle's autonomous driving system tracks the vehicle trajectory in real time, determines the steering angle intention of the autonomous driving system based on the vehicle trajectory parameters, and considers the driver's steering operation intention in real time, dynamically adjusting the driving authority during the process. At the same time, it judges whether a human-machine conflict has occurred based on the overall driving system and the driver's steering intention. When a human-machine conflict occurs, the path is replanned, and the front wheel steering angle is determined comprehensively based on the two driving intentions, thereby ensuring the driver's driving experience, ensuring the driver's trust in the autonomous driving system, and ultimately ensuring driving safety and reducing the possibility of traffic accidents.

[0007] This invention provides a shared steering control method for resolving human-machine conflict, comprising the following steps:

[0008] S1. Obtain vehicle driving parameters, including the vehicle's lateral velocity, longitudinal velocity, desired path curvature, and heading angle;

[0009] S2. Construct a vehicle trajectory tracking model based on the vehicle's driving process parameters, and determine the heading angle error and lateral position error based on the vehicle trajectory tracking model;

[0010] S3. Based on the heading angle error and lateral position error, a driving rights allocation model is determined, and the driving rights of the vehicle and the driver are determined;

[0011] S4. Construct a vehicle dynamics model, and determine the front wheel steering angle determined by the vehicle controller based on the vehicle dynamics model. Then, determine whether a human-machine conflict has occurred based on the front wheel steering angle determined by the vehicle controller and the front wheel steering angle input by the driver. If so, trigger trajectory reconstruction and control the vehicle to drive according to the reconstructed trajectory; otherwise, control the vehicle to drive according to the original trajectory.

[0012] Regardless of whether trajectory reconstruction is triggered, the vehicle operates according to the comprehensive front wheel steering angle determined based on driving authority, the driver's input front wheel steering angle, and the vehicle's own determined front wheel steering angle.

[0013] Furthermore, the vehicle trajectory tracking model is constructed as follows:

[0014] (1);

[0015] in: Indicates the heading angle error. This indicates the lateral position error. These represent the error coefficients, Indicates the lateral speed of the vehicle. Indicates the longitudinal speed of the vehicle. Indicates the desired path curvature. This indicates the vehicle's heading angle.

[0016] Furthermore, in step S3, determining the driving control allocation model based on the heading angle error and lateral position error specifically includes:

[0017] Feature variables were constructed based on heading angle error and lateral position error. and characteristic variables :

[0018] (2);

[0019] in: This indicates the threshold for the vehicle's lateral position error. This indicates the vehicle's heading angle error threshold.

[0020] Based on feature variables and characteristic variables Constructing eigenvalues and eigenvalues :

[0021] (3);

[0022] in: and Eigenvalues The adjustment coefficient;

[0023] (4);

[0024] in: and Eigenvalues The adjustment coefficient;

[0025] Construct a driving rights allocation model:

[0026] (5);

[0027] in: , , These are the set coefficients;

[0028] The driver's driving rights are : ;

[0029] The right to drive the vehicle is : .

[0030] Furthermore, a vehicle dynamics model is constructed, and the front wheel steering angle determined by the vehicle controller based on the vehicle dynamics model specifically includes:

[0031] The vehicle dynamics model is as follows:

[0032] (6);

[0033] in: and These are the lateral stiffness of the front and rear wheels, respectively. and These are the slip angles of the front and rear wheels, respectively, and x and y are the longitudinal and lateral displacements of the vehicle in the xoy coordinate system, respectively. The front wheel steering angle of the vehicle. and The deviation measurements are for the front and rear wheels, respectively. This indicates the yaw rate of the vehicle. To represent the moment of inertia about the z-axis in the xoy coordinate system, a and b represent the distances from the vehicle's center of mass to the front and rear axles, respectively.

[0034] make , ;

[0035] Convert the vehicle dynamics model to:

[0036] (7)

[0037] (8);

[0038] (9);

[0039] The vehicle controller determines the front wheel steering angle as follows:

[0040] (10).

[0041] Furthermore, determining whether a human-machine conflict has occurred based on the front wheel steering angle determined by the vehicle controller and the front wheel steering angle input by the driver specifically includes:

[0042] ;

[0043] in: Indicates an indicator of human-machine conflict. This represents the threshold value indicating the difference between the front wheel steering angle determined by the vehicle controller and the front wheel steering angle input by the driver. This indicates the front wheel steering angle input by the driver. This indicates that the vehicle controller determines the front wheel steering angle;

[0044] when Greater than or equal to When, path reconstruction is triggered, when Less than or equal to At that time, the path reconstruction is solved; among which This indicates the upper limit threshold for human-machine conflict. This represents the lower threshold for human-machine conflict.

[0045] Furthermore, the combined front wheel steering angle is determined by the following method:

[0046] .

[0047] The beneficial effects of this invention are as follows: Through this invention, the vehicle autonomous driving system tracks the vehicle trajectory in real time, determines the steering angle intention of the autonomous driving system based on the vehicle trajectory parameters, and considers the driver's steering operation intention in real time, dynamically adjusting the driving authority during the process. At the same time, it judges whether a human-machine conflict occurs based on the overall driving system and the driver's steering intention. In the event of a human-machine conflict, the path is replanned, and the front wheel steering angle is determined comprehensively based on the two driving intentions, thereby ensuring the driver's driving experience, ensuring the driver's trust in the autonomous driving system, and ultimately ensuring driving safety and reducing the possibility of traffic accidents. Attached Figure Description

[0048] The present invention will be further described below with reference to the accompanying drawings and embodiments:

[0049] Figure 1 This is a schematic diagram of the process of the present invention.

[0050] Figure 2 This is a schematic diagram of vehicle trajectory tracking according to the present invention.

[0051] Figure 3 This is a schematic diagram of the vehicle dynamics model of the present invention.

[0052] Figure 4 This is the trajectory reconstruction triggering mechanism of the present invention. Detailed Implementation

[0053] The present invention will be further described in detail below:

[0054] This invention provides a shared steering control method for resolving human-machine conflict, comprising the following steps:

[0055] S1. Obtain vehicle driving parameters, including the vehicle's lateral velocity, longitudinal velocity, desired path curvature, and heading angle;

[0056] S2. Construct a vehicle trajectory tracking model based on the vehicle's driving process parameters, and determine the heading angle error and lateral position error based on the vehicle trajectory tracking model; such as Figure 2 As shown, Figure 2 In this context, the xoy coordinate system is the vehicle's position coordinate system, while the XOY coordinate system is the inertial coordinate system.

[0057] S3. Based on the heading angle error and lateral position error, a driving rights allocation model is determined, and the driving rights of the vehicle and the driver are determined;

[0058] S4. Construct a vehicle dynamics model, and determine the front wheel steering angle determined by the vehicle controller based on the vehicle dynamics model. Then, determine whether a human-machine conflict has occurred based on the front wheel steering angle determined by the vehicle controller and the front wheel steering angle input by the driver. If so, trigger trajectory reconstruction and control the vehicle to drive according to the reconstructed trajectory; otherwise, control the vehicle to drive according to the original trajectory.

[0059] Regardless of whether trajectory reconstruction is triggered, the vehicle operates according to a comprehensive front wheel steering angle determined based on driving authority, the driver's input front wheel steering angle, and the vehicle's own determined front wheel steering angle. Through this method, the vehicle's autonomous driving system tracks the vehicle's trajectory in real time, determines the system's steering angle intent based on the trajectory parameters, and considers the driver's steering intentions in real time, dynamically adjusting driving authority during the process. Simultaneously, it assesses whether a human-machine conflict has occurred based on the overall driving system and the driver's steering intentions. In the event of a conflict, the path is replanned, and the front wheel steering angle is comprehensively determined based on both driving intentions. This ensures a positive driving experience, maintains the driver's trust in the autonomous driving system, ultimately ensuring driving safety and reducing the likelihood of traffic accidents.

[0060] In this embodiment, the vehicle trajectory tracking model is constructed as follows:

[0061] (1);

[0062] in: Indicates the heading angle error. This indicates the lateral position error. These represent the error coefficients, Indicates the lateral speed of the vehicle. Indicates the longitudinal speed of the vehicle. Indicates the desired path curvature. This indicates the vehicle's heading angle.

[0063] In step S3, determining the driving control allocation model based on the heading angle error and lateral position error specifically includes:

[0064] Feature variables were constructed based on heading angle error and lateral position error. and characteristic variables :

[0065] (2);

[0066] in: This indicates the threshold for lateral position error of the vehicle. This value is determined by the vehicle width, road width, and safety factor; this is existing technology. This represents the vehicle's heading angle error threshold; where, It characterizes the degree of deviation between the vehicle's actual lateral position and its desired lateral position. It represents the degree of deviation between the vehicle's actual heading angle and the desired heading angle.

[0067] Based on feature variables and characteristic variables Constructing eigenvalues and eigenvalues :

[0068] (3);

[0069] in: and Eigenvalues The adjustment coefficient is used to adjust... The size of the range of values;

[0070] (4);

[0071] in: and Eigenvalues The adjustment coefficient is used to adjust The size of the range of values;

[0072] Construct a driving rights allocation model:

[0073] (5);

[0074] in: , , These are the set coefficients;

[0075] The driver's driving rights are : ;

[0076] The right to drive the vehicle is : .

[0077] The overall front wheel steering angle is determined based on the allocation of driving authority:

[0078] The driver's input front wheel steering angle is determined by the steering wheel. When the driver operates the steering wheel, the input front wheel steering angle can be calculated based on the steering wheel's rotation angle (this calculation process is existing technology). The vehicle controller (i.e., the autonomous driving system) calculates the front wheel steering angle as follows: Based on the above, after the comprehensive front wheel steering angle is determined, the vehicle is controlled according to the comprehensive front wheel steering angle, so that the common intentions of the automatic driving system and the driver are taken into account during driving, thereby ensuring driving safety.

[0079] In this embodiment, constructing a vehicle dynamics model and determining the front wheel steering angle determined by the vehicle controller based on the vehicle dynamics model specifically includes:

[0080] The vehicle dynamics model is as follows:

[0081] (6);

[0082] in: and These are the lateral stiffness of the front and rear wheels, respectively. and These are the slip angles of the front and rear wheels, respectively, and x and y are the longitudinal and lateral displacements of the vehicle in the xoy coordinate system, respectively. The front wheel steering angle of the vehicle. and The deviation measurements are for the front and rear wheels, respectively. This indicates the yaw rate of the vehicle. To represent the moment of inertia about the z-axis in the xoy coordinate system, a and b represent the distances from the vehicle's center of mass to the front and rear axles, respectively.

[0083] make , ;

[0084] Convert the vehicle dynamics model to:

[0085] (7)

[0086] (8);

[0087] (9);

[0088] The vehicle controller determines the front wheel steering angle as follows:

[0089] (10). The above method can effectively ensure the accuracy of the vehicle controller in determining the front wheel steering angle, providing accurate data support for subsequent operations.

[0090] In this embodiment, determining whether a human-machine conflict has occurred based on the front wheel steering angle determined by the vehicle controller and the front wheel steering angle input by the driver specifically includes:

[0091] ;

[0092] in: Indicates an indicator of human-machine conflict. This represents the threshold value indicating the difference between the front wheel steering angle determined by the vehicle controller and the front wheel steering angle input by the driver. This indicates the front wheel steering angle input by the driver. This indicates that the vehicle controller determines the front wheel steering angle;

[0093] when Greater than or equal to When, path reconstruction is triggered, when Less than or equal to At that time, the path reconstruction is solved; among which This indicates the upper limit threshold for human-machine conflict. Indicates the lower threshold of human-machine conflict, such as Figure 4 As shown: When Greater than or equal to When the path is reconstructed, the path reconstruction process is triggered. After path reconstruction, the route is traveled according to the reconstructed path, and the path is recalculated. and Then update The value, after being updated, even Less than It will not cancel the path reconstruction process, so until Less than or The path reconstruction process is only encountered at that time.

[0094] The following is a brief description of path reconstruction:

[0095] In the Frenet coordinate system, the vehicle's motion can be decomposed into one-dimensional lateral motion and one-dimensional longitudinal motion, establishing a one-dimensional acceleration integral system:

[0096] (11);

[0097] in: , Represents lateral movement or longitudinal movement , It represents lateral acceleration or longitudinal acceleration, that is, the rate of change of lateral acceleration or longitudinal acceleration;

[0098] Describing the lateral path of the vehicle using a fifth-order polynomial :

[0099] (12);

[0100] Lateral path planning is primarily responsible for vehicle obstacle avoidance. The initial value at time is

[0101] (13);

[0102] The target value at time is ;

[0103] So The polynomial representations of and its first and second orders are as follows:

[0104] (14);

[0105] Separately Solve :

[0106] (15);

[0107] When the initial value and target value Given this, the lateral dynamic trajectory is represented by formula (12). Solving from formulas (14) and (15), since the road reference line is generally chosen as the lane centerline, the vehicle should try to be along or parallel to the road reference line, so the target value .

[0108] For longitudinal path planning, we ignore parking and following situations as well as longitudinal position. Only the vehicle's longitudinal speed and acceleration need to be planned. The initial value at time is , The target value at time is Longitudinal movement Expressed using a four-term polynomial:

[0109] (16);

[0110] Convert formula (16) into a matrix:

[0111] (17);

[0112] when and And when get and as follows:

[0113] (18);

[0114] Given initial values and target value The longitudinal motion path can then be solved, and the vehicle's trajectory is a composite trajectory of the vehicle's lateral and longitudinal trajectories (trajectory synthesis is an existing technology and will not be elaborated here).

[0115] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A shared steering control method for resolving human-machine conflict, characterized in that: Includes the following steps: S1. Obtain vehicle driving parameters, including the vehicle's lateral velocity, longitudinal velocity, desired path curvature, and heading angle; S2. Construct a vehicle trajectory tracking model based on the vehicle's driving process parameters, and determine the heading angle error and lateral position error based on the vehicle trajectory tracking model; S3. Based on the heading angle error and lateral position error, a driving rights allocation model is determined, and the driving rights of the vehicle and the driver are determined; S4. Construct a vehicle dynamics model, and determine the front wheel steering angle determined by the vehicle controller based on the vehicle dynamics model. Then, determine whether a human-machine conflict has occurred based on the front wheel steering angle determined by the vehicle controller and the front wheel steering angle input by the driver. If so, trigger trajectory reconstruction and control the vehicle to drive according to the reconstructed trajectory. If not, then control the vehicle to travel according to the original trajectory; Regardless of whether trajectory reconstruction is triggered, the vehicle operates according to the comprehensive front wheel steering angle determined based on driving authority, the driver's input front wheel steering angle, and the vehicle's own determined front wheel steering angle.

2. The shared steering control method for resolving human-machine conflict according to claim 1, characterized in that: The specific steps for constructing a vehicle trajectory tracking model are as follows: (1)； in: Indicates the heading angle error. This indicates the lateral position error. These represent the error coefficients, Indicates the lateral speed of the vehicle. Indicates the longitudinal speed of the vehicle. Indicates the desired path curvature. This indicates the vehicle's heading angle.

3. The shared steering control method for resolving human-machine conflict according to claim 2, characterized in that: In step S3, determining the driving control allocation model based on the heading angle error and lateral position error specifically includes: Feature variables were constructed based on heading angle error and lateral position error. and characteristic variables : (2)； in: This indicates the threshold for the vehicle's lateral position error. This indicates the vehicle's heading angle error threshold; Based on feature variables and characteristic variables Constructing eigenvalues and eigenvalues : (3)； in: and Eigenvalues The adjustment coefficient; (4)； in: and Eigenvalues The adjustment coefficient; Construct a driving rights allocation model: (5)； in: , , These are the set coefficients; The driver's driving rights are : ; The right to drive the vehicle is : .

4. The shared steering control method for resolving human-machine conflict according to claim 3, characterized in that: Constructing a vehicle dynamics model and determining the front wheel steering angle based on the vehicle dynamics model specifically includes: The vehicle dynamics model is as follows: (6)； in: and These are the lateral stiffness of the front and rear wheels, respectively. and These are the slip angles of the front and rear wheels, respectively, and x and y are the longitudinal and lateral displacements of the vehicle in the xoy coordinate system, respectively. The front wheel steering angle of the vehicle. and The deviation measurements are for the front and rear wheels, respectively. This indicates the yaw rate of the vehicle. To represent the moment of inertia about the z-axis in the xoy coordinate system, a and b represent the distances from the vehicle's center of mass to the front and rear axles, respectively. make , ; Convert the vehicle dynamics model to: （7） （8）； （9）； The vehicle controller determines the front wheel steering angle as follows: （10）。 5. The shared steering control method for resolving human-machine conflict according to claim 1, characterized in that: Determining whether a human-machine conflict has occurred based on the front wheel steering angle determined by the vehicle controller and the front wheel steering angle input by the driver specifically includes: ； in: Indicates an indicator of human-machine conflict. This represents the threshold value indicating the difference between the front wheel steering angle determined by the vehicle controller and the front wheel steering angle input by the driver. This indicates the front wheel steering angle input by the driver. This indicates that the vehicle controller determines the front wheel steering angle; when Greater than or equal to When, path reconstruction is triggered, when Less than or equal to At that time, the path reconstruction is solved; among which This indicates the upper limit threshold for human-machine conflict. This represents the lower threshold for human-machine conflict.

6. The shared steering control method for resolving human-machine conflict according to claim 3, characterized in that: The combined front wheel steering angle is determined by the following method: 。

Images