Method for operating an autonomous driving function of a vehicle

Patent metadata

Field	Value
Publication number	US-12128890-B2
Application number	US-202017642367-A
Country	US
Kind code	B2
Filing date	Nov 3, 2020
Priority date	Nov 11, 2019
Publication date	Oct 29, 2024
Grant date	Oct 29, 2024

Abstract

A method for operating an autonomous driving function of a vehicle. The vehicle includes a computer unit and sensors for detecting surroundings data. The computer unit is configured to determine a setpoint trajectory for the vehicle, based on the detected surroundings data. In step a), an actual trajectory, and distances from objects in the surroundings, are detected. In step b), an ascertainment of the quality of the autonomous driving function takes place by comparing the actual trajectory to the setpoint trajectory and monitoring the detected distances from objects in the surroundings. In step c), a control of the quality to a predefined target value takes place by selecting sensors to be used for the autonomous driving function from the plurality of sensors and/or by changing a measuring rate, at which measurements are carried out, of at least one sensor from the plurality of sensors.

First claim

What is claimed is:

1. A method for operating an autonomous driving function of a vehicle, the vehicle including a computer unit and a plurality of sensors configured to detect surroundings data representing surroundings of the vehicle, and the computer unit being configured to determine a setpoint trajectory, along which the vehicle is guided, based on the detected surroundings data, the method comprising the following steps:
a) detecting an actual trajectory of the vehicle, the actual trajectory representing a path actually covered by the vehicle;
b) comparing the detected actual trajectory to the setpoint trajectory;
c) detecting distances of the vehicle from objects in the surroundings of the vehicle;
d) ascertaining an actual quality of the autonomous driving function based on (i) a result of the comparison of the detected actual trajectory to the setpoint trajectory and (ii) the detected distances; and
e) based on a difference between the ascertained actual quality and a predefined target quality, performing a modification that includes at least one of (i) turning on or off one of more of the plurality of sensors for a continued operation of the autonomous driving function and (ii) for each of one or more of the plurality of sensors, changing a measuring rate at which measurements are carried out by the respective sensor, the modification being performed in a manner that is determined to reduce the difference.

2. The method as recited in claim 1 , wherein, taking at least one further parameter into consideration, at least one assessment factor is determined and taken into consideration during the selection of the sensors to be used and/or during the change of the measuring rate, the at least one further parameter being selected from: (i) a capacity utilization of the computer unit, and/or (ii) a traffic situation in which the vehicle is situated, (iii) a scenario in which the vehicle situated, and/or (iv) information about weather at the location of the vehicle.

3. The method as recited in claim 2 , wherein the assessment factor is individually determined for each individual sensor of the plurality of sensors.

4. The method as recited in claim 1 , wherein sensors which are not selected are switched off or transferred into a stand-by mode.

5. The method as recited in claim 1 , wherein the determination of the setpoint trajectory takes place using a first artificial intelligence model, which was obtained by machine learning.

6. The method as recited in claim 1 , wherein the selection of sensors to be used and/or the change of a measuring rate takes place using a second artificial intelligence model, which was obtained by machine learning.

7. The method as recited in claim 1 , wherein: (i) the determination of the setpoint trajectory, and (ii) the selection of sensors to be used and/or the change of a measuring rate, take place using a shared artificial intelligence model, which was obtained by machine learning.

8. The method as recited in claim 1 , wherein a capacity utilization of the computer unit is taken into consideration for determining how to perform the modification.

9. The method as recited in claim 1 , wherein the modification includes turning off the one or more of the plurality of sensors in response to the ascertained actual quality being greater than the predefined target quality or a tolerance range of the target quality, to thereby reduce the actual quality.

10. The method as recited in claim 1 , wherein the modification includes turning on the one or more of the plurality of sensors in response to the ascertained actual quality being less than the predefined target quality or a tolerance range of the target quality, to thereby increase the actual quality.

11. The method as recited in claim 1 , wherein:
the modification includes the changing of the measuring rate; and
the changing of the measuring rate is performed by lowering the measuring rate in response to the ascertained actual quality being greater than the predefined target quality or a tolerance range of the target quality, to thereby reduce the actual quality.

12. The method as recited in claim 1 , wherein:
the modification includes the changing of the measuring rate; and
the changing of the measuring rate is performed by increasing the measuring rate in response to the ascertained actual quality being lower than the predefined target quality or a tolerance range of the target quality, to thereby increase the actual quality.

13. A method for operating an autonomous driving function of a vehicle, the vehicle including a plurality of sensors configured to detect surroundings data and a computer unit configured to determine a setpoint trajectory along which the vehicle is guided based on the detected surroundings data, the method comprising the following steps:
a) detecting an actual trajectory of the vehicle, the actual trajectory representing a path actually covered by the vehicle;
b) detecting distances from objects based on the surroundings data;
b) ascertaining a quality of the autonomous driving function by comparing the actual trajectory to the setpoint trajectory and the detected distances; and
c) controlling the quality to a predefined target value by changing a measuring rate at which measurements are carried out by at least one sensor of the plurality of sensors, wherein;
(i) a processing rate of the computer unit for processing the surroundings data is adapted to the measuring rate; or
(ii) a processing rate of the surroundings data is constant, the changing of the measuring rate includes reducing the measuring rate, and a multiple transfer of individual measured values is carried out in response to the reduction of the measuring rate.

14. The method as recited in claim 13 , wherein the processing rate of the computer is adapted to the measuring rate.

15. The method as recited in claim 13 , wherein the processing rate of the surroundings data is constant, the changing of the measuring rate includes the reduction of the measuring rate, and the multiple transfer of individual measured values is carried out in response to the reduction of the measuring rate.

16. A non-transitory computer-readable medium on which is stored a computer program for operating an autonomous driving function of a vehicle, the vehicle including a computer unit and a plurality of sensors configured to detect surroundings data representing surroundings of the vehicle, and the computer unit being configured to determine a setpoint trajectory, along which the vehicle is guided, based on the detected surroundings data, the computer program, when executed by a computer, causing the computer to perform the following steps:
a) detecting an actual trajectory of the vehicle, the actual trajectory representing a path actually covered by the vehicle;
b) comparing the detected actual trajectory to the setpoint trajectory;
c) detecting distances of the vehicle from objects in the surroundings of the vehicle;
d) ascertaining an actual quality of the autonomous driving function based on (i) a result of the comparison of the detected actual trajectory to the setpoint trajectory and (ii) the detected distances; and
e) based on a difference between controlling the ascertained actual quality and a predefined target quality, performing a modification that includes at least one of (i) turning on or off one of more of the plurality of sensors for a continued operation of the autonomous driving function and (ii) for each of one or more of the plurality of sensors, changing a measuring rate at which measurements are carried out by the respective sen

Assignees

• Bosch Gmbh Robert

Inventors

• Ewert Marlon Ramon

Classifications

• B60W50/06

  Improving the dynamic response of the control system, e.g. improving the speed of regulation or avoiding hunting or overshoot · CPC title

• B60W2554/802

  Longitudinal distance · CPC title

• B60W2555/20

  Ambient conditions, e.g. wind or rain · CPC title

• B60W60/0015

  specially adapted for safety · CPC title

• B60W2050/065

  by reducing the computational load on the digital processor of the control computer · CPC title