Recognition of hands-off situations based on swarm data

Patent metadata

Field	Value
Publication number	US-11345401-B2
Application number	US-202017016882-A
Country	US
Kind code	B2
Filing date	Sep 10, 2020
Priority date	Sep 11, 2019
Publication date	May 31, 2022
Grant date	May 31, 2022

Abstract

The invention relates to a method for improving hands-off recognition in a vehicle with steering torque-based recognition in that swarm data are provided from vehicles that recognize hands-off situations with hand distance sensors in the steering wheel. Both recognition results over a certain route section are compared and, in the case of deviations, the correctness of the results of the hand distance sensors is assumed. On this basis, route sections are determined in which steering torque-based recognition is unreliable. Based on this recognition, systems with steering torque evaluation can then be re-parameterized in order to be more reliable relative to the route.

First claim

What is claimed is:

1. A method for preparing route-related calibration data for a driver assistance system that is designed to recognize hands-off situations in a vehicle comprising:
recognizing one or more hands-off situations using a driver assistance system with a first recognition quality by evaluating steering torque data;
recognizing one or more hands-off situations using a driver assistance system with a higher recognition quality by evaluating measurement data from a capacitive steering wheel sensor;
determining position data while the vehicle is moving along a route;
identifying one or more route sections of the route in which there is a difference in the number of hands-off situations recognized by the driver assistance system with the first recognition quality, and the number of hands-off situations recognized by the driver assistance system with a higher recognition quality; and
preparing therefrom the route-related calibration data while forming reliability parameters for recognition with the first recognition quality on the respective route sections depending on the existing difference.

2. The method of claim 1 , wherein a vehicle is used whose driver assistance system simultaneously performs both recognition with the first recognition quality as well as recognition with the higher recognition quality.

3. The method of claim 2 , wherein the route-related calibration data are transmitted by the vehicle or a central computing facility to other vehicles.

4. The method of claim 1 , wherein the route-related calibration data are transmitted by the vehicle or a central computing facility to other vehicles.

5. A driver assistance system configured to function as a driver assistance system with a first recognition quality in the method of claim 1 .

6. A vehicle comprising the driver assistance system of claim 5 .

7. A computing device designed to assume at least one function from the following group in the method of claim 1 :
receiving data from one or more vehicles and processing the data on route-related calibration data; and
receiving route-related calibration data from one or more vehicles and forwarding the data to other vehicles.

8. A driver assistance system configured to function as a driver assistance system with a higher recognition quality in the method of claim 1 .

9. A driver assistance system configured to function as a driver assistance system with a first recognition quality and as a driver assistance system with a higher recognition quality in the method of claim 1 .

10. The method of claim 1 , comprising assigning steering torque data and measurement data to one or more common points along the route.

11. A method for calibrating a driver assistance system that is designed to recognize hands-off situations in a vehicle, comprising:
detecting position data of the vehicle while the vehicle is moving along a route section; and in doing so by the driver assistance system, recognizing hands-off situations with a first recognition quality;
wherein the vehicle receives route-related calibration data and the driver assistance system uses the calibration data by:
extracting reliability parameters from the calibration data on those route sections in which the driver assistance system has recognized hands-off situations; and
adapting the recognition sensitivity of the driver assistance system for the respective route sections depending on the significance of the reliability parameter when it falls below a limit value.

12. The method of claim 11 , wherein the driver assistance system of the vehicle recognizes the hands-off situations by evaluating steering torque data.

13. The method of claim 12 , wherein the recognition sensitivity is decreased in that steering torque threshold values at which a hands-off situation is recognized, are reduced.

14. The method of claim 11 , wherein the recognition sensitivity is decreased in that steering torque threshold values at which a hands-off situation is recognized, are reduced.

15. A driver assistance system configured to function as a driver assistance system with a first recognition quality in the method of claim 11 .

16. A computing device designed to assume at least one function from the following group in the method of claim 11 :
receiving data from one or more vehicles and processing the data on route-related calibration data;
receiving route-related calibration data from one or more vehicles and forwarding the data to other vehicles.

Assignees

• Volkswagen Ag

Inventors

• Eigel Thomas
• Stahl Felix

Classifications

• B60W2510/202

  Steering torque · CPC title

• B60W2540/18

  Steering angle · CPC title

• B60W60/001

  Planning or execution of driving tasks · CPC title

• B60W40/08 Primary

  related to drivers or passengers · CPC title

• G08G1/0137

  for specific applications · CPC title