Mishap amelioration based on second-order sensing by a self-driving vehicle

• US 10,061,326 B2
• Filed: 12/09/2015
• Issued: 08/28/2018
• Est. Priority Date: 12/09/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Gordon, Michael S., Kozloski, James R., Kundu, Ashish, Malkin, Peter K., Pickover, Clifford A.
• Primary Examiner(s): Black, Thomas G
• Assistant Examiner(s): Thomas, Ana D
• Application Number:
  US14/963,272
• Publication Number:
  US 20170168502A1
• Time in Patent Office: 993 Days
• CPC Class Codes: B60K 28/14 responsive to accident or emergency, e.g. deceleration, tilt of vehicle
• CPC Class Codes: B60R 2021/0027 Post collision measures, e.g. notifying emergency services
• CPC Class Codes: B60R 21/0132 responsive to vehicle motion parameters , e.g. to vehicle longitudinal or transversal deceleration or speed value
• CPC Class Codes: B60R 21/0134 responsive to imminent contact with an obstacle , e.g. using radar systems
• CPC Class Codes: B60R 21/01512 Passenger detection systems
• CPC Class Codes: B60W 2030/082 Vehicle operation after collision
• CPC Class Codes: B60W 2556/65 Data transmitted between vehicles
• CPC Class Codes: B60W 30/09 Taking automatic action to avoid collision, e.g. braking and steering
• CPC Class Codes: B60W 40/08 related to drivers or passengers
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle

Abstract

A self-driving vehicle (SDV) ameliorates a vehicular mishap incurred by a second vehicle. At least one sensor on a first SDV detects a second vehicle that has been involved in a vehicular mishap. One or more processors determine a confidence level L, which is a confidence level of a mishap assessment accuracy of determining that the second vehicle has been involved in the vehicular mishap. In response to the confidence level L exceeding a predetermined value, the SDV executes an amelioration action to ameliorate a condition of the second vehicle that has been involved in the vehicular mishap.

Claims

1. A method for a first self-driving vehicle (SDV) ameliorating a vehicular mishap incurred by a second vehicle, the method comprising:

detecting, by at least one sensor on a first SDV, a second vehicle that has been involved in a vehicular mishap;

determining, by one or more processors, a confidence level L, wherein the confidence level L is a confidence level of a mishap assessment accuracy of determining that the second vehicle has been involved in the vehicular mishap; and

in response to the confidence level L exceeding a predetermined value, executing, by the first SDV, an amelioration action to ameliorate a condition of the second vehicle that has been involved in the vehicular mishap, wherein the amelioration action is an action that is performed by the first SDV independently of the second vehicle.

2. The method of claim 1, wherein the vehicular mishap is a collision in which the second vehicle was involved.

3. The method of claim 1, wherein the vehicular mishap is an equipment failure in the second vehicle.

4. The method of claim 1, wherein the first SDV was not involved in the vehicular mishap.

5. The method of claim 1, wherein said at least one sensor on the first SDV is from a group consisting of a light detection and ranging (LIDAR) system, a video camera, a microphone, and a vibration detector.

6. The method of claim 1, wherein multiple inputs from multiple sensors on the first SDV describing the vehicular mishap increase a value of the confidence level L.

7. The method of claim 1, wherein the amelioration action is taking and transmitting a photo of the vehicular mishap to a third party.

8. The method of claim 1, wherein the amelioration action is capturing and transmitting air sensor readings to a third party, wherein the air sensor readings describe chemicals being released from the second vehicle.

9. The method of claim 1, wherein the first SDV is dedicated to autonomously scouting for vehicular mishaps.

10. The method of claim 1, further comprising:

reporting, by the first SDV, a report of the vehicular mishap to other SDVs within a predefined distance of the vehicular mishap.

11. The method of claim 1, further comprising:

determining, by the first SDV, that a second SDV is on a collision course with the second vehicle; and

in response to determining that the second SDV is on the collision course with the second vehicle, issuing, from the first SDV to the second SDV, electronic control instructions that redirect the second SDV on a course that avoids colliding with the second vehicle.

12. The method of claim 1, further comprising:

directing, by the first SDV, multiple SDVs to automatically provide a protective swarm around the second vehicle that has been involved in the vehicular mishap, wherein the protective swarm protects the second vehicle from being struck by other vehicles.

13. The method of claim 1, further comprising:

transmitting, from the second vehicle to a health care provider, real-time medical status information regarding persons that were impacted by the vehicular mishap.

14. The method of claim 1, further comprising:

detecting, by said at least one sensor on the first SDV, a hazardous fluid proximate to the second vehicle that was involved in the vehicular mishap; and

transmitting, by the first SDV, a message describing the hazardous fluid to a first responder authority.

15. The method of claim 1, further comprising:

detecting, by said at least one sensor on the first SDV, a level of passenger movement of passengers within the second vehicle to create a passenger movement signal; and

transmitting the passenger movement signal from the first SDV to a first responder authority.

16. The method of claim 1, further comprising:

detecting, by said at least one sensor on the first SDV, an absence of any passengers within the second vehicle to create an empty vehicle signal; and

transmitting the empty vehicle signal from the first SDV to a first responder authority.

17. The method of claim 1, wherein the amelioration action does not direct the second vehicle to perform any action.

18. The method of claim 1, further comprising:

pooling, by one or more processors, sensor information from multiple SDVs that sensed the vehicular mishap to create a multi-point-of-view (mPOV) composite report on the vehicular mishap, wherein the mPOV composite report comprises information about a location, speed, heading, and movement of the second vehicle before and after the vehicular mishap, and wherein the mPOV composite report comprises panoramic imagery, light detection and ranging (LIDAR) models, and rotational information through scene and object stitching based on sensor readings from the multiple SDVs.

19. A computer program product for a self-driving vehicle (SDV) ameliorating a vehicular mishap incurred by a second vehicle, the computer program product comprising a non-transitory computer readable storage medium having program code embodied therewith, the program code readable and executable by a processor to perform a method comprising:

detecting, by at least one sensor on a first SDV, a second vehicle that has been involved in a vehicular mishap;

determining a confidence level L, wherein the confidence level L is a confidence level of a mishap assessment accuracy of determining that the second vehicle has been involved in the vehicular mishap;

in response to the confidence level L exceeding a predetermined value, executing, by the first SDV, an amelioration action to ameliorate a condition of the second vehicle that has been involved in the vehicular mishap; and

directing, by the first SDV, multiple SDVs to automatically provide a protective swarm around the second vehicle that has been involved in the vehicular mishap, wherein the protective swarm protects the second vehicle from being struck by other vehicles.

20. A self-driving vehicle (SDV) comprising:

a processor, a computer readable memory, and a non-transitory computer readable storage medium;

first program instructions to detect, by at least one sensor on the SDV, a second vehicle that has been involved in a vehicular mishap;

second program instructions to determine a confidence level L, wherein the confidence level L is a confidence level of a mishap assessment accuracy of determining that the second vehicle has been involved in the vehicular mishap;

third program instructions to, in response to the confidence level L exceeding a predetermined value, execute, by the SDV, an amelioration action to ameliorate a condition of the second vehicle that has been involved in the vehicular mishap; and

fourth program instructions to pool sensor information from multiple SDVs that sensed the vehicular mishap to create a multi-point-of-view (mPOV) composite report on the vehicular mishap, wherein the mPOV composite report comprises information about a location, speed, heading, and movement of the second vehicle before and after the vehicular mishap, and wherein the mPOV composite report comprises panoramic imagery, light detection and ranging (LIDAR) models, and rotational information through scene and object stitching based on sensor readings from the multiple SDVs; and

wherein

the first, second, third, and fourth program instructions are stored on the non-transitory computer readable storage medium for execution by one or more processors via the computer readable memory.