Self-driving vehicle sensor fault remediation

Patent metadata

Field	Value
Publication number	US-9940761-B2
Application number	US-201615226217-A
Country	US
Kind code	B2
Filing date	Aug 2, 2016
Priority date	Aug 2, 2016
Publication date	Apr 10, 2018
Grant date	Apr 10, 2018

Abstract

Methods, systems, and computer program products for self-driving vehicle sensor fault remediation are provided herein. A computer-implemented method includes detecting a fault in one or more sensors of a self-driving vehicle; determining a remedial action in response to the detected fault, wherein said determining comprises (i) comparing the fault to a database comprising (a) historical sensor fault information and (b) sensor fault remedy information, and (ii) analyzing one or more items of contextual information pertaining to the location of the self-driving vehicle; generating a signal comprising one or more instructions pertaining to carrying out the determined remedial action; and outputting the generated signal to one or more remote-controlled pilotless airborne devices configured to remotely carry out the determined remedial action on the self-driving vehicle.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
detecting a fault in one or more sensors of a self-driving vehicle;
determining a remedial action in response to the detected fault, wherein said determining comprises (i) comparing the fault to a database comprising (a) historical sensor fault information and (b) sensor fault remedy information, (ii) analyzing one or more items of contextual information pertaining to the location of the self-driving vehicle, and (iii) generating an estimated risk associated with the detected fault being dangerous to at least one of the self-driving vehicle, a passenger of the self-driving vehicle, and a pedestrian proximate to the self-driving vehicle;
generating a signal comprising one or more instructions pertaining to carrying out the determined remedial action; and
outputting the generated signal to one or more remote-controlled pilotless airborne devices configured to remotely carry out the determined remedial action on the self-driving vehicle;
wherein the steps are carried out by at least one computing device.

2. The computer-implemented method of claim 1 , wherein the one or more sensors comprise one or more LIDAR sensors, one or more radar sensors, one or more ultrasonic sensors, and/or one or more image sensors.

3. The computer-implemented method of claim 1 , wherein the remedial action comprises performing a diagnostic test on the one or more sensors.

4. The computer-implemented method of claim 1 , wherein the remedial action comprises performing a repair of the one or more sensors.

5. The computer-implemented method of claim 1 , wherein the remedial action comprises replacing the one or more sensors.

6. The computer-implemented method of claim 1 , wherein the remedial action comprises cleaning the one or more sensors.

7. The computer-implemented method of claim 1 , wherein the remedial action comprises deicing the one or more sensors.

8. The computer-implemented method of claim 1 , wherein the remedial action comprises providing a sensor by proxy to the self-driving vehicle.

9. The computer-implemented method of claim 1 , wherein the remedial action comprises physically connecting the one or more remote-controlled pilotless airborne devices to the self-driving vehicle.

10. The computer-implemented method of claim 1 , wherein the remedial action comprises wirelessly connecting the one or more remote-controlled pilotless airborne devices to the self-driving vehicle.

11. The computer-implemented method of claim 1 , wherein the one or more items of contextual information comprises the width of the road on which the self-driving vehicle is currently located.

12. The computer-implemented method of claim 1 , wherein the one or more items of contextual information comprises weather-related information pertaining to the location of the self-driving vehicle.

13. The computer-implemented method of claim 1 , wherein the historical sensor fault information comprises the age of the one or more sensors and/or the date of any previous replacements for the one or more sensors.

14. The computer-implemented method of claim 1 , wherein the historical sensor fault information comprises a history of expected sensor lifetimes for each of one or more classes of sensors.

15. The computer-implemented method of claim 1 , wherein the one or more instructions pertaining to carrying out the determined remedial action comprises an instruction to switch the self-driving vehicle from self-driving mode to human-operated mode.

16. The computer-implemented method of claim 1 , wherein the one or more instructions pertaining to carrying out the determined remedial action comprises an instruction to alter the route of the self-driving vehicle.

17. A computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a device to cause the device to:
detect a fault in one or more sensors of a self-driving vehicle;
determine a remedial action in response to the detected fault, wherein said determining comprises (i) comparing the fault to a database comprising (a) historical sensor fault information and (b) sensor fault remedy information, (ii) analyzing one or more items of contextual information pertaining to the location of the self-driving vehicle, and (iii) generating an estimated risk associated with the detected fault being dangerous to at least one of the self-driving vehicle, a passenger of the self-driving vehicle, and a pedestrian proximate to the self-driving vehicle;
generate a signal comprising one or more instructions pertaining to carrying out the determined remedial action; and
output the generated signal to one or more remote-controlled pilotless airborne devices configured to remotely carry out the determined remedial action on the self-driving vehicle.

18. The computer program product of claim 17 , wherein said determining further comprises generating an estimated risk associated with the detected fault being dangerous to the self-driving vehicle, a passenger of the self-driving vehicle, and/or a pedestrian proximate to the self-driving vehicle.

19. A system comprising:
a memory; and
at least one processor coupled to the memory and configured for:
detecting a fault in one or more sensors of a self-driving vehicle;
determining a remedial action in response to the detected fault, wherein said determining comprises (i) comparing the fault to a database comprising (a) historical sensor fault information and (b) sensor fault remedy information, (ii) analyzing one or more items of contextual information pertaining to the location of the self-driving vehicle, and (iii) generating an estimated risk associated with the detected fault being dangerous to at least one of the self-driving vehicle, a passenger of the self-driving vehicle, and a pedestrian proximate to the self-driving vehicle;
generating a signal comprising one or more instructions pertaining to carrying out the determined remedial action; and
outputting the generated signal to one or more remote-controlled pilotless airborne devices configured to remotely carry out the determined remedial action on the self-driving vehicle.

Assignees

• IBM

Inventors

• Kundu Ashish
• Nanavati Amit A
• Pickover Clifford A
• Weldemariam Komminist S

Classifications

• B64U2201/20

  Remote controls · CPC title

• G05D1/0255

  using acoustic signals, e.g. ultra-sonic singals (sonar systems designed for anti-collision purposes G01S15/93) · CPC title

• G05D1/0248

  in combination with a laser (lasers per se H01S) · CPC title

• G07C5/008 Primary

  communicating information to a remotely located station (transmission systems for measured values G08C) · CPC title

• B64C2201/126

  Operations & Transport · mapped topic