A Curve Adaptive Intelligent Driving Human-Machine Co-driving Steering Control Method

Abstract

This invention discloses a cornering adaptive intelligent driving human-machine co-driving steering control method. The method first obtains the curvature of the curve, calculates the driver intervention torque threshold, the driver takeover torque threshold, and the maximum weight of the human-machine co-driving system based on the curvature, and then combines the driver's steering torque to obtain the control weight of the assisted driving system. Then, the driver's steering torque and the steering torque generated by the assisted driving system are superimposed and integrated according to the control weight of the assisted driving system to obtain the final executed steering torque.

Description

Technical Field

[0001] This invention relates to the field of driver assistance technology, specifically to an intelligent driving human-machine co-driving steering control method with curve adaptive capability. Background Technology

[0002] In many scenarios of Level 3 autonomous driving, the vehicle is jointly controlled by the driver and the system. However, the control weights required by the system and the criteria for judging the driver's control intentions should be different in curves with different curvatures. Summary of the Invention

[0003] The purpose of this invention is to provide an adaptive intelligent driving human-machine co-driving steering control method for cornering, thereby improving the driving experience during steering.

[0004] To solve the above-mentioned technical problems, the present invention provides a technical solution: a cornering adaptive intelligent driving human-machine co-driving steering control method, characterized in that it includes:

[0005] Based on the curvature of the curve, the driver intervention torque threshold, driver takeover torque threshold, and maximum weight of the human-machine co-driving system are calculated by combining the maximum curvature supported by the driver assistance system with preset coefficient values. The curvature of the curve is obtained from the driving image containing lane lines acquired by the vehicle-mounted sensor. When the curvature of the curve is larger, the driver intervention torque threshold, driver takeover torque threshold, and maximum weight of the human-machine co-driving system increase accordingly.

[0006] Obtain the driver's steering torque generated when the driver turns the steering wheel;

[0007] When the driver's steering torque is less than or equal to the driver intervention torque threshold, the control weight of the driver assistance system is 1, and the vehicle's steering action is completely controlled by the driver assistance system.

[0008] When the driver's steering torque is greater than or equal to the driver take-over torque threshold, the control weight of the driver assistance system is 0, and the vehicle's steering action is completely controlled by the driver.

[0009] When the driver's steering torque is greater than the driver intervention torque threshold but less than the driver takeover torque threshold, the control weight of the driver assistance system is obtained based on the driver intervention torque threshold, the driver takeover torque threshold, the maximum weight of the human-machine co-driving system, and the driver's steering torque. The value of the driver assistance system control weight is between 0 and 1. At this time, the value of the driver control weight is 1 minus the value of the driver assistance system control weight. The steering torque control value of the steering system response is the product of the driver control weight and the driver's steering torque, plus the sum of the product of the requested torque of the driver assistance system and the control weight of the driver assistance system.

[0010] According to the above scheme, the driver intervention torque threshold Trqinter The calculation process is as follows;

[0011]

[0012] In the formula, Trq inter0 For the preset driver intervention torque threshold on a straight road, Crv max Trq is the maximum cornering curvature supported by the driver assistance system. inter_crv The driver intervention torque coefficient is superimposed on the preset curve.

[0013] According to the above scheme, the driver takeover torque threshold Trq takeover The calculation process is as follows;

[0014]

[0015] In the formula, Trq takeover0 For the preset driver takeover torque threshold on a straight road, Crv max Trq is the maximum cornering curvature supported by the driver assistance system. takeover_crv The preset curve is superimposed with the driver's takeover torque coefficient.

[0016] According to the above scheme, the maximum weight K of the human-machine co-driving system is... inter_max The calculation process is as follows;

[0017]

[0018] In the formula, K inter0_max To set the maximum weight for the human-machine co-driving system on the preset straight road, Crv max K represents the maximum curvature of the cornering path supported by the driver assistance system. inter_crv The preset curve overlay driving assistance system control coefficients.

[0019] According to the above scheme, the calculation process of the control weight K of the assisted driving system is as follows;

[0020]

[0021] A cornering adaptive intelligent driving human-machine co-driving steering control system for implementing the cornering adaptive intelligent driving human-machine co-driving steering control method described above, comprising:

[0022] The curve curvature acquisition module includes a forward-looking camera, which is used to acquire forward-looking driving images and calculate the curve curvature (Crv) of the lane lines in front of the vehicle.

[0023] The driver steering torque acquisition module is used to acquire the driver steering torque Trq.

[0024] The driver assistance system control weight calculation module is used to calculate the driver assistance system control weight K based on the curve curvature Crv and the driver steering torque Trq.

[0025] The steering execution module is used to execute steering actions based on the control weight K of the driver assistance system, the steering torque generated by the driver assistance system, and the driver's steering torque Trq.

[0026] According to the above scheme, the calculation process of the control weight K of the assisted driving system is as follows;

[0027]

[0028] In the above formula, Trq inter The driver intervention torque threshold Trq is calculated based on the curve curvature Crv. inter Trq takeover The threshold for driver takeover torque is calculated based on the curve curvature Crv.

[0029] K inter_max The maximum weight of the human-machine co-driving system is calculated based on the curve curvature Crv.

[0030] According to the above scheme, the driver intervention torque threshold Trq inter The calculation process is as follows;

[0031]

[0032] In the formula, Trq inter0 For the preset driver intervention torque threshold on a straight road, Crv max Trq is the maximum cornering curvature supported by the driver assistance system. inter_crv The driver intervention torque coefficient is superimposed on the preset curve.

[0033] According to the above scheme, the driver takeover torque threshold Trq takeover The calculation process is as follows;

[0034]

[0035] In the formula, Trq takeover0 For the preset driver takeover torque threshold on a straight road, Crv max Trq is the maximum cornering curvature supported by the driver assistance system. takeover_crv The preset curve is superimposed with the driver's takeover torque coefficient.

[0036] According to the above scheme, the maximum weight K of the human-machine co-driving system is... inter_max The calculation process is as follows;

[0037]

[0038] In the formula, K inter0_max To set the maximum weight for the human-machine co-driving system on the preset straight road, Crv max K represents the maximum curvature of the cornering path supported by the driver assistance system. inter_crv The preset curve overlay driving assistance system control coefficients.

[0039] The beneficial effects of this invention are as follows: This solution obtains the curvature of the curve and calculates the driver intervention torque threshold, driver takeover torque threshold, and the maximum weight of the human-machine co-driving system based on the curvature. Then, it combines the driver's steering torque to obtain the control weight of the assisted driving system. Finally, it superimposes and integrates the driver's steering torque and the steering torque generated by the assisted driving system based on the assisted driving system control weight to obtain the final executed steering torque. In this solution, when the curvature of the curve increases, the driver intervention torque threshold, driver takeover torque threshold, and the maximum weight of the human-machine co-driving system all increase. Consequently, the range of values ​​for the assisted driving system control weight that are not 1 or 0 (i.e., the human-machine co-driving interval) is wider, which is more conducive to driver participation in control and improves steering maneuverability in complex curve scenarios. Attached Figure Description

[0040] Figure 1 This is a graph showing the relationship between the driver's steering torque and the control weight of the driver assistance system in Embodiment 1 of the present invention.

[0041] Figure 2 This is a schematic diagram illustrating the relationship between the driver's steering torque and the control weight of the driver assistance system as a function of the curvature of a curve, according to Embodiment 1 of the present invention. Figure 2 The diagonal line in the diagram changes from thin to thick, indicating that the curvature of the curve gradually increases.

[0042] Figure 3 This is a cornering adaptive intelligent driving human-machine co-driving steering control method according to Embodiment 1 of the present invention. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the described embodiments of this disclosure without creative effort are within the scope of protection of this disclosure.

[0044] Example 1:

[0045] See Figures 1-3 A cornering adaptive intelligent driving human-machine co-driving steering control method, comprising:

[0046] S1. Calculate the driver intervention torque threshold Trq based on the curve curv. inter Driver takeover torque threshold Trq takeover Maximum weight K of human-machine co-driving system inter_max ;

[0047] Driver intervention torque threshold Trq inter The calculation process is as follows;

[0048]

[0049] In the formula, Trq inter0 For the preset driver intervention torque threshold on a straight road, Crv max Trq is the maximum cornering curvature supported by the driver assistance system. inter_crv The driver intervention torque coefficient is superimposed on the preset curve (which can be obtained through actual vehicle calibration).

[0050] Driver takeover torque threshold Trq takeover The calculation process is as follows;

[0051]

[0052] In the formula, Trq takeover0 Trq is the preset driver takeover torque threshold for straight roads. takeover_crv The driver takeover torque coefficient is superimposed on the preset curve (which can be obtained through actual vehicle calibration).

[0053] Maximum weight K of human-machine co-driving system inter_max The calculation process is as follows;

[0054]

[0055] In the formula, K inter0_max K represents the maximum weight of the human-machine co-driving system on the preset straight road. inter_crv The preset curve overlay driver assistance system control coefficients (which can be obtained through real vehicle calibration) are used.

[0056] The curve curvature Crv is obtained from a driving image containing lane lines (at the preview time) acquired by the onboard sensors; the larger the curve curvature Crv, the higher the driver intervention torque threshold Trq. inter Driver takeover torque threshold Trq takeover Maximum weight K of human-machine co-driving system inter_max It increases accordingly;

[0057] S2. Obtain the driver's steering torque Trq generated by the driver turning the steering wheel. When the driver's steering torque Trq is less than or equal to the driver intervention torque threshold Trq... interWhen the driver assistance system control weight K is 1, the driver steering torque Trq is greater than the driver intervention torque threshold Trq. inter And less than the driver takeover torque threshold Trq takeover At that time, the control weight K of the driver assistance system is based on the driver intervention torque threshold Trq. inter Driver takeover torque threshold Trq takeover Maximum weight K of human-machine co-driving system inter_max And the driver steering torque Trq is obtained; when the driver steering torque Trq is greater than or equal to the driver take-off torque threshold Trq takeover When the driver assistance system control weight K is 0, the value range of the driver assistance system control weight K is 0 to 1. A driver assistance system control weight K of 0 indicates that the vehicle steering action is completely controlled by the driver, and a driver assistance system control weight K of 1 indicates that the vehicle steering action is completely controlled by the driver assistance system.

[0058] The calculation process for the control weight K of the driver assistance system is as follows;

[0059]

[0060] When K is 1, the driver does not participate in steering control at all, which corresponds to the automatic driving mode.

[0061] When K is between 0 and 1, the driver and the driver assistance system jointly control the steering, which corresponds to the human-machine co-driving mode.

[0062] When K is 0, the steering action is completely controlled by the driver, corresponding to the manual driving condition.

[0063] In many L3-level autonomous driving scenarios, the vehicle is jointly controlled by the driver and the system. However, the steering control weights required by the system and the criteria for judging the driver's control intentions should differ in curves with varying curvatures. As the curvature increases, the human-machine co-driving range should expand to facilitate driver intervention, and the system should be more sensitive to driver intervention as the curvature of the curve increases. This invention proposes an algorithm that dynamically adjusts the system and driver control weights based on different curve curvatures and the driver's control intentions. This results in more accurate recognition of driver intervention intentions and improves the curve adaptability of the human-machine co-driving algorithm in steering control.

[0064] Example 2:

[0065] The principle and method of this embodiment are basically the same as those of Embodiment 1. Based on Embodiment 1, a cornering adaptive intelligent driving human-machine co-driving steering control system is also proposed, including:

[0066] The curve curvature acquisition module includes a forward-looking camera, which is used to acquire forward-looking driving images and calculate the curve curvature (Crv) of the lane lines in front of the vehicle.

[0067] The driver steering torque acquisition module is used to acquire the driver steering torque Trq.

[0068] The driver assistance system control weight calculation module is used to calculate the driver assistance system control weight K based on the curve curvature Crv and the driver's steering torque Trq; the calculation process of the driver assistance system control weight K is as follows;

[0069]

[0070] In the above formula, Trq inter The driver intervention torque threshold Trq is calculated based on the curve curvature Crv. inter Trq takeover K is the driver takeover torque threshold calculated based on the curve curvature Crv. inter_max The maximum weight of the human-machine co-driving system is calculated based on the curve curvature CRV.

[0071] The driver intervention torque threshold Trq inter The calculation process is as follows;

[0072]

[0073] In the formula, Trq inter0 For the preset driver intervention torque threshold on a straight road, Crv max Trq is the maximum cornering curvature supported by the driver assistance system. inter_crv The driver intervention torque coefficient is superimposed on the preset curve.

[0074] The driver takeover torque threshold Trq takeover The calculation process is as follows;

[0075]

[0076] In the formula, Trq takeover0 Trq is the preset driver takeover torque threshold for straight roads. takeover_crv The driver takeover torque coefficient is superimposed on the preset curve.

[0077] The maximum weight K of the human-machine co-driving system inter_max The calculation process is as follows;

[0078]

[0079] In the formula, K inter0_max K represents the maximum weight of the human-machine co-driving system on the preset straight road. inter_crv The preset curve overlay control coefficients of the driver assistance system;

[0080] The steering execution module is used to execute steering actions based on the control weight K of the driver assistance system, the steering torque generated by the driver assistance system, and the driver's steering torque Trq.

[0081] The above description is merely an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A cornering adaptive intelligent driving human-machine co-driving steering control method, characterized in that: include; Based on the curvature of the curve, the driver intervention torque threshold, the driver takeover torque threshold, and the maximum weight of the human-machine co-driving system are calculated by combining the maximum curvature of the curve supported by the driver assistance system with the preset coefficient value. The curvature of the curve is obtained from a driving image containing lane lines acquired by the vehicle-mounted sensor. As the curvature of the curve increases, the driver intervention torque threshold, the driver takeover torque threshold, and the maximum weight of the human-machine co-driving system also increase. Obtain the driver's steering torque generated when the driver turns the steering wheel; When the driver's steering torque is less than or equal to the driver intervention torque threshold, the control weight of the driver assistance system is 1, and the vehicle's steering action is completely controlled by the driver assistance system. When the driver's steering torque is greater than or equal to the driver take-over torque threshold, the control weight of the driver assistance system is 0, and the vehicle's steering action is completely controlled by the driver. When the driver's steering torque is greater than the driver intervention torque threshold but less than the driver takeover torque threshold, the control weight of the driver assistance system is obtained based on the driver intervention torque threshold, the driver takeover torque threshold, the maximum weight of the human-machine co-driving system, and the driver's steering torque. The value of the control weight of the driver assistance system is between 0 and 1. At this time, the value of the driver control weight is 1 minus the value of the control weight of the driver assistance system. The steering torque control value of the steering system response is the product of the driver control weight and the driver's steering torque, plus the sum of the product of the requested torque of the driver assistance system and the control weight of the driver assistance system. Driver intervention torque threshold The calculation process is as follows; In the formula, This is a preset threshold for driver intervention torque on a straight road. The maximum curvature of a curve supported by the driver assistance system. The driver intervention torque coefficient is superimposed on the preset curve. Driver takeover torque threshold The calculation process is as follows; In the formula, The preset threshold for driver takeover torque on a straight road. The driver takeover torque coefficient is superimposed on the preset curve. Maximum weight of human-machine co-driving system The calculation process is as follows; In the formula, The maximum weight of the human-machine co-driving system in the preset straight road is set. The preset curve overlay driving assistance system control coefficients.

2. The adaptive cornering intelligent driving human-machine co-driving steering control method according to claim 1, characterized in that: Control weights of driver assistance systems The calculation process is as follows; 。 3. A cornering adaptive intelligent driving human-machine co-driving steering control system for implementing the cornering adaptive intelligent driving human-machine co-driving steering control method according to any one of claims 1-2, characterized in that: include; The curve curvature acquisition module includes a forward-view camera, which is used to acquire forward-view driving images and calculate the curve curvature of the lane lines in front of the vehicle. The driver steering torque acquisition module is used to acquire the driver's steering torque. The driver assistance system control weight calculation module is used to calculate the control weight of the driver assistance system based on the curvature of the curve and the driver's steering torque. The steering execution module is used to execute steering actions based on the control weight of the driver assistance system, the steering torque generated by the driver assistance system, and the driver's steering torque.

4. The cornering adaptive intelligent driving human-machine co-driving steering control system according to claim 3, characterized in that: Control weights of driver assistance systems The calculation process is as follows; ； In the above formula, To be based on the curvature of the curve Calculated driver intervention torque threshold , To be based on the curvature of the curve The calculated driver takeover torque threshold, To be based on the curvature of the curve The calculated maximum weight of the human-machine co-driving system.

Images