Controlling driving modes of self-driving vehicles

• US 9,944,291 B2
• Filed: 10/27/2015
• Issued: 04/17/2018
• Est. Priority Date: 10/27/2015
• Status: Active Grant

• Current Assignee: Maplebear Inc.
• Original Assignee: International Business Machines Corporation
• Inventors: Gordon, Michael S., Kozloski, James R., Kundu, Ashish, Malkin, Peter K., Pickover, Clifford A.
• Primary Examiner(s): Edwards, Jerrah
• Assistant Examiner(s): WALLACE, DONALD JOSEPH
• Application Number:
  US14/924,034
• Publication Number:
  US 20170113689A1
• Time in Patent Office: 903 Days
• CPC Class Codes: B60W 2050/0014 Adaptive controllers
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 2420/408 Radar; Laser, e.g. lidar
• CPC Class Codes: B60W 2420/60 Doppler effect
• CPC Class Codes: B60W 2554/408 Traffic behavior, e.g. swarm
• CPC Class Codes: B60W 2554/80 Spatial relation or speed relative to objects
• CPC Class Codes: B60W 2555/20 Ambient conditions, e.g. wind or rain
• CPC Class Codes: B60W 2556/10 Historical data
• CPC Class Codes: B60W 2556/65 Data transmitted between vehicles
• CPC Class Codes: B60W 2754/10 Spatial relation or speed relative to objects
• CPC Class Codes: B60W 30/0956 the prediction being responsive to traffic or environmental parameters
• CPC Class Codes: B60W 40/04 Traffic conditions
• CPC Class Codes: B60W 50/0098 Details of control systems ensuring comfort, safety or stability not otherwise provided for
• CPC Class Codes: B60W 60/0051 from occupants to vehicle
• CPC Class Codes: B60W 60/0053 from vehicle to occupant
• CPC Class Codes: B60W 60/0059 Estimation of the risk associated with autonomous or manual driving, e.g. situation too complex, sensor failure or driver incapacity
• CPC Class Codes: B62D 15/02 Steering position indicators ; Steering position determination; Steering aids
• CPC Class Codes: G05D 1/0214 in accordance with safety or protection criteria, e.g. avoiding hazardous areas monitoring the location of vehicles within a certain area, e.g. forbidden or allowed areas, in traffic control systems for road vehicles G08G1/13

Abstract

A method and/or computer program product controls an operational mode of a self-driving vehicle (SDV) that is initially being operated in a nominal autonomous mode. Detectors on an SDV detect an erratically driven vehicle (EDV) that is being operated in an unsafe manner within a predetermined distance of an SDV. In response to detecting the EDV, a driving mode device in the SDV changes an operational mode of the SDV from the nominal autonomous mode to an evasive autonomous mode.

Claims

1. A method for controlling an operational mode of a self-driving vehicle (SDV), the method comprising:

detecting, by one or more physical detectors, an erratically driven vehicle (EDV) that is being operated in an unsafe manner within a predetermined distance of an SDV, wherein the SDV is initially being operated in a nominal autonomous mode;

in response to the one or more physical detectors detecting the EDV, changing, by an operational mode device in the SDV, an operational mode of the SDV from the nominal autonomous mode to an evasive autonomous mode;

retrieving, by one or more processors, traffic pattern data for other SDVs;

examining, by one or more processors, the traffic pattern data to determine a first traffic flow of the other SDVs while operating in the evasive autonomous mode;

examining, by one or more processors, the traffic pattern data to determine a second traffic flow of the other SDVs while operating in a manual mode; and

in response to determining that the first traffic flow has a higher accident rate than the second traffic flow, changing, by the operational mode device, the operational mode of the SDV from the evasive autonomous mode to the manual mode.

2. The method of claim 1, further comprising:

transmitting, by a transceiver on the SDV, an alert to other SDVs describing the EDV.

3. The method of claim 1, further comprising:

transmitting, by a transceiver on the SDV, an alert to an authority agency describing the EDV.

4. The method of claim 1, further comprising:

detecting, based on sensor readings from a roadway sensor, a current roadway condition of a roadway upon which the SDV and the EDV are traveling; and

further adjusting, by the operational mode device, the operational mode of the SDV based on the current roadway condition of the roadway upon which the SDV and the EDV are traveling.

5. The method of claim 1, wherein the SDV and the EDV are traveling on a roadway, and wherein the processor-implemented method further comprises:

switching the operational mode of the SDV from the manual mode to the evasive autonomous mode;

retrieving, by one or more processors, driver profile information about a human driver of the SDV;

assigning, by one or more processors, the human driver of the SDV to a cohort of drivers who have traveled on the roadway in other SDVs, wherein the human driver of the SDV shares more than a predetermined quantity of traits with members of the cohort of drivers who have traveled in the other SDVs; and

in response to assigning the human driver of the SDV to the cohort of drivers who have traveled on the roadway in other SDVs, switching the operational mode of the SDV from the evasive autonomous mode to the manual mode.

6. The method of claim 1, wherein the SDV and the EDV are traveling on a roadway, and wherein the method further comprises:

switching the operational mode of the SDV from the manual mode to the evasive autonomous mode;

receiving, by one or more processors, sensor readings from multiple sensors, wherein each of the multiple sensors detects a different type of current condition of the roadway;

weighting, by one or more processors, each of the sensor readings for different current conditions of the roadway;

summing, by one or more processors, weighted sensor readings for the different current conditions of the roadway;

determining, by one or more processors, whether the summed weighted sensor readings exceed a predefined level; and

in response to determining that the summed weighted sensor readings exceed the predefined level, changing, by the operational mode device, the operational mode of the SDV from the evasive autonomous mode to a stopping autonomous mode.

7. The method of claim 1, further comprising:

switching, by one or more processors, the operational mode of the SDV from the manual mode to the evasive autonomous mode;

receiving, by one or more processors, operational readings from one or more SDV operational sensors on the SDV, wherein the SDV operational sensors detect a current state of mechanical equipment on the SDV;

detecting, by the one or more processors and based on received operational readings, a mechanical fault with the mechanical equipment on the SDV; and

in response to detecting the mechanical fault with the mechanical equipment on the SDV, changing, by the operational mode device, the operational mode of the SDV from the evasive autonomous mode to a stopping autonomous mode.

8. A computer program product for controlling an operational mode of a self-driving vehicle (SDV), 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 one or more physical detectors, an erratically driven vehicle (EDV) that is being operated in an unsafe manner within a predetermined distance of an SDV, wherein the SDV and the EDV are traveling on a roadway, and wherein the SDV is initially being operated in a nominal autonomous mode;

in response to the one or more physical detectors detecting the EDV, changing, by an operational mode device in the SDV, an operational mode of the SDV from the nominal autonomous mode to an evasive autonomous mode;

retrieving driver profile information about a human driver of the SDV;

assigning the human driver of the SDV to a cohort of drivers who have traveled on the roadway in other SDVs, wherein the human driver of the SDV shares more than a predetermined quantity of traits with members of the cohort of drivers who have traveled in the other SDVs; and

in response to assigning the human driver of the SDV to the cohort of drivers who have traveled on the roadway in other SDVs, switching the operational mode of the SDV from the evasive autonomous mode to a manual mode.

9. The computer program product of claim 8, wherein the method further comprises:

transmitting, by a transceiver on the SDV, an alert to other SDVs describing the EDV.

10. The computer program product of claim 8, wherein the method further comprises:

transmitting, by a transceiver on the SDV, an alert to an authority agency describing the EDV.

11. The computer program product of claim 8, wherein the method further comprises:

detecting, based on sensor readings from a roadway sensor, a current roadway condition of a roadway upon which the SDV and the EDV are traveling; and

further adjusting, by the operational mode device, the operational mode of the SDV based on the current roadway condition of the roadway upon which the SDV and the EDV are traveling.

12. The computer program product of claim 8, wherein the method further comprises:

switching the operational mode of the SDV from the manual mode to the evasive autonomous mode;

retrieving traffic pattern data for the other SDVs as they traveled on the roadway;

examining the traffic pattern data to determine a first traffic flow of the other SDVs while operating in the evasive autonomous mode on the roadway;

examining the traffic pattern data to determine a second traffic flow of the other SDVs while operating in a manual mode on the roadway; and

in response to determining that the first traffic flow has a higher accident rate than the second traffic flow, changing, by the operational mode device, the operational mode of the SDV from the evasive autonomous mode to the manual mode.

13. The computer program product of claim 8, wherein the method further comprises:

switching the operational mode of the SDV from the manual mode to the evasive autonomous mode;

receiving sensor readings from multiple sensors, wherein each of the multiple sensors detects a different type of current condition of the roadway;

weighting each of the sensor readings for different current conditions of the roadway;

summing weighted sensor readings for the different current conditions of the roadway;

determining whether the summed weighted sensor readings exceed a predefined level; and

in response to determining that the summed weighted sensor readings exceed the predefined level, changing, by the operational mode device, the operational mode of the SDV from the evasive autonomous mode to a stopping autonomous mode.

14. The computer program product of claim 8, wherein the method further comprises:

switching the operational mode of the SDV from the manual mode to the evasive autonomous mode;

receiving operational readings from one or more SDV operational sensors on the SDV, wherein the SDV operational sensors detect a current state of mechanical equipment on the SDV;

detecting, based on received operational readings, a mechanical fault with the mechanical equipment on the SDV; and

in response to detecting the mechanical fault with the mechanical equipment on the SDV, changing, by the operational mode device, the operational mode of the SDV from the evasive autonomous mode to a stopping autonomous mode.

15. A self-driving vehicle comprising:

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

first program instructions to detect, by one or more physical detectors on an SDV, an erratically driven vehicle (EDV) that is being operated in an unsafe manner within a predetermined distance of an SDV, wherein the SDV is initially being operated in a nominal autonomous mode;

second program instructions to instruct an operational mode device in the SDV to change an operational mode of the SDV from the nominal autonomous mode to an evasive autonomous mode in response to detecting the EDV;

third program instructions to retrieve traffic pattern data for other SDVs;

fourth program instructions to examine the traffic pattern data to determine a first traffic flow of the other SDVs while operating in the evasive autonomous mode;

fifth program instructions to examine the traffic pattern data to determine a second traffic flow of the other SDVs while operating in the nominal autonomous mode; and

sixth program instructions to, in response to determining that the first traffic flow has a higher accident rate than the second traffic flow, instruct the operational mode device to change the operational mode of the SDV from the evasive autonomous mode back to the nominal autonomous mode; and

wherein

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

16. The self-driving vehicle of claim 15, further comprising:

seventh program instructions to instruct a transceiver on the SDV to transmit an alert to other SDVs describing the EDV; and

wherein

the seventh program instructions are stored on the non-transitory computer readable storage medium for execution by one or more processors via the computer readable memory.

17. The self-driving vehicle of claim 15, further comprising:

seventh program instructions to instruct a transceiver on the SDV to transmit an alert to an authority agency describing the EDV; and

wherein

the seventh program instructions are stored on the non-transitory computer readable storage medium for execution by one or more processors via the computer readable memory.

18. The self-driving vehicle of claim 15, further comprising:

seventh program instructions to receive sensor readings from a roadway sensor describing a current roadway condition of a roadway upon which the SDV and the EDV are traveling; and

eighth program instructions to further adjust, via the operational mode device, the operational mode of the SDV based on the current roadway condition of the roadway upon which the SDV and the EDV are traveling; and

wherein

the seventh and eighth program instructions are stored on the non-transitory computer readable storage medium for execution by one or more processors via the computer readable memory.

19. The self-driving vehicle of claim 15, wherein the SDV and the EDV are traveling on a roadway, wherein the SDV is a first SDV, and wherein the self-driving vehicle further comprises:

seventh program instructions to switch the operational mode of the SDV from the nominal autonomous mode to the evasive autonomous mode;

eighth program instructions to retrieve driver profile information about a human driver of the first SDV;

ninth program instructions to assign the human driver of the first SDV to a cohort of drivers traveling on the roadway in other SDVs, wherein the human driver of the first SDV shares more than a predetermined quantity of traits with members of the cohort of drivers of the other SDVs; and

tenth program instructions to in, response to assigning the human driver of the SDV to the cohort of drivers who have traveled on the roadway in other SDVs, switch the operational mode of the SDV from the evasive autonomous mode to a manual mode;

and wherein

the seventh, eighth, ninth, and tenth program instructions are stored on the non-transitory computer readable storage medium for execution by one or more processors via the computer readable memory.

20. The self-driving vehicle of claim 15, further comprising:

seventh program instructions to switch the operational mode of the SDV from the nominal autonomous mode to the evasive autonomous mode;

eighth program instructions to receive operational readings from one or more SDV operational sensors on the SDV, wherein the SDV operational sensors detect a current state of mechanical equipment on the SDV;

ninth program instructions to detect, based on received operational readings, a mechanical fault with the mechanical equipment on the SDV; and

tenth program instructions to instruct the operational mode device to change the operational mode of the SDV from the evasive autonomous mode to a stopping autonomous mode in response to detecting the mechanical fault with the mechanical equipment on the SDV; and

wherein

the seventh, eighth, ninth, and tenth program instructions are stored on the non-transitory computer readable storage medium for execution by one or more processors via the computer readable memory.