Controlling driving modes of self-driving vehicles

• US 9,834,224 B2
• Filed: 10/15/2015
• Issued: 12/05/2017
• Est. Priority Date: 10/15/2015
• 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): OH, HARRY Y
• Application Number:
  US14/883,708
• Publication Number:
  US 20170106876A1
• Time in Patent Office: 782 Days
• Field of Search: 701 23
• CPC Class Codes: B60W 2030/082 Vehicle operation after collision
• CPC Class Codes: B60W 2050/0071 Controller overrides driver automatically
• CPC Class Codes: B60W 2050/0095 Automatic control mode change
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 2540/00 Input parameters relating to occupants
• CPC Class Codes: B60W 2540/043 Identity of occupants
• CPC Class Codes: B60W 2540/045 Occupant permissions
• CPC Class Codes: B60W 2540/221 Physiology, e.g. weight, heartbeat, health or special needs
• CPC Class Codes: B60W 2540/229 Attention level, e.g. attentive to driving, reading or sleeping
• CPC Class Codes: B60W 2540/30 Driving style
• CPC Class Codes: B60W 2552/35 Road bumpiness, e.g. potholes
• CPC Class Codes: B60W 2555/20 Ambient conditions, e.g. wind or rain
• CPC Class Codes: B60W 2556/00 Input parameters relating to data
• CPC Class Codes: B60W 30/182 Selecting between different operative modes, e.g. comfort and performance modes
• CPC Class Codes: B60W 60/0051 from occupants to vehicle
• 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: G05D 1/0061 for transition from automatic pilot to manual pilot and vice versa

Abstract

A processor-implemented method, system, and/or computer program product control a driving mode of a self-driving vehicle (SDV). One or more processors detect that an SDV is being operated in manual mode by a human driver. The processor(s) determine that the human driver is unqualified to operate the SDV in manual mode, and then transfer control of the SDV to an SDV on-board computer in order to place the SDV in autonomous mode.

Claims

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

detecting, by one or more processors, that an SDV is being operated in manual mode by a human driver;

detecting, by one or more processors within an SDV on-board computer within the SDV that monitors a telecommunication device within the SDV, that the telecommunication device within the SDV is receiving a telecommunication message;

in response to detecting that the telecommunication device within the SDV is receiving the telecommunication message, determining, by the one or more processors, that the human driver is unqualified to operate the SDV in manual mode based on the telecommunication device receiving the telecommunication message; and

in response to determining that the human driver is unqualified to operate the SDV in manual mode, transferring, by the one or more processors, control of the SDV to the SDV on-board computer to place the SDV in autonomous mode, wherein the SDV is in the autonomous mode when steering, braking, throttle control, and obstacle avoidance by the SDV are all controlled by the SDV on-board computer.

2. The processor-implemented method of claim 1, further comprising:

determining, by the one or more processors, a response requirement of the telecommunication message, wherein an urgent response requirement requires a response to the telecommunication message within a first predefined amount of time after receipt of the telecommunication message, and wherein a non-urgent response requirement requires no response to the telecommunication message until after a second predefined amount of time after receipt of the telecommunication message, wherein the first predefined amount of time is shorter than the second predefined amount of time; and

in response to determining that the response requirement is the urgent response requirement, automatically placing, by the one or more processors, the SDV into autonomous mode.

3. The processor-implemented method of claim 1, wherein said determining that the human driver is unqualified to operate the SDV in manual mode comprises:

determining, by the one or more processors looking up data from a database about the human driver, that the human driver is required to wear prescription eyewear;

detecting, by the one or more processors receiving images of the human driver that are received from a cabin camera that captures images of the human driver while the human driver is within a cabin of the SDV, that the human driver is not wearing prescription eyewear; and

in response to detecting that the human driver is not wearing prescription eyewear, further determining, by the one or more processors, that the human driver is unqualified to operate the SDV in manual mode based on the human driver not wearing prescription eyewear and transferring, by the one or more processors, control of the SDV to the SDV on-board computer in order to place the SDV in the autonomous mode.

4. The processor-implemented method of claim 1, wherein said determining that the human driver is unqualified to operate the SDV in manual mode comprises:

determining, by the one or more processors, that the SDV is driving towards an object that is brighter than a predetermined level of brightness based on data from a roadway sensor detecting a position of a sun relative to the SDV;

detecting, by the one or more processors receiving images of the human driver that are received from a cabin camera that captures images of the human driver while the human driver is within a cabin of the SDV, that the human driver is not wearing sunglasses; and

in response to detecting that the human driver is not wearing sunglasses while the SDV is driving towards the object that is brighter than the predetermined level of brightness, further determining, by the one or more processors, that the human driver is unqualified to operate the SDV in manual mode based on the SDV driving towards the object that is brighter than the predetermined level of brightness and the human driver not wearing sunglasses and transferring, by the one or more processors, control of the SDV to the SDV on-board computer in order to place the SDV in the autonomous mode.

5. The processor-implemented method of claim 1, wherein said determining that the human driver is unqualified to operate the SDV in manual mode comprises:

detecting, by the one or more processors searching a database of holders of a valid driver'"'"'s license, that the human driver currently is not a holder of the valid driver'"'"'s license; and

in response to detecting that the human driver currently is not the holder of the valid driver'"'"'s license, further determining, by the one or more processors, that the human driver is unqualified to operate the SDV in manual mode based on the human driver not currently being the holder of the valid driver'"'"'s license and transferring, by the one or more processors, control of the SDV to the SDV on-board computer in order to place the SDV in the autonomous mode.

6. The processor-implemented method of claim 1, wherein said determining that the human driver is unqualified to operate the SDV in manual mode comprises:

detecting, by the one or more processors receiving a signal from a collision detector on the SDV, that the SDV has been involved in an accident; and

in response to detecting that the SDV has been involved in the accident, further determining, by the one or more processors, that the human driver is unqualified to operate the SDV in manual mode based on the SDV being involved in the accident and transferring, by the one or more processors, control of the SDV to the SDV on-board computer in order to place the SDV in the autonomous mode.

7. The processor-implemented method of claim 1, wherein said determining that the human driver is unqualified to operate the SDV in manual mode comprises:

detecting, by the one or more processors receiving a signal from an airbag in the SDV, that the airbag in the SDV has deployed; and

in response to detecting that the airbag in the SDV has deployed, further determining, by the one or more processors, that the human driver is unqualified to operate the SDV in manual mode based on the airbag having deployed and transferring, by the one or more processors, control of the SDV to the SDV on-board computer in order to place the SDV in the autonomous mode.

8. The processor-implemented method of claim 1, wherein said determining that the human driver is unqualified to operate the SDV in manual mode comprises:

detecting, by the one or more processors receiving a signal from roadway sensors on the SDV, a current roadway condition for a roadway upon which the SDV is traveling;

further determining, by the one or more processors and based on a driving history of the human driver, that the human driver is unqualified to operate the SDV in manual mode based on the current roadway condition being beyond an ability of the human driver to control the SDV based on a lack of experience by the human driver in driving in the current roadway condition; and

transferring, by the one or more processors, control of the SDV to the SDV on-board computer in order to place the SDV in the autonomous mode.

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

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

assigning, by the one or more processors and based on a predetermined quantity of traits shared by the human driver with members of a cohort of drivers traveling on the roadway in multiple SDVs, the human driver of the SDV to the cohort of drivers traveling on the roadway in multiple SDVs, wherein the human driver of the SDV shares more than the predetermined quantity of traits with members of the cohort of drivers;

retrieving, by the one or more processors, traffic pattern data for the multiple SDVs occupied by the cohort of drivers traveling on the roadway;

examining, by the one or more processors, the traffic pattern data to determine a first traffic flow of the multiple SDVs occupied by members of the cohort of drivers, wherein the multiple SDVs in the first traffic flow are operating in the autonomous mode on the roadway;

examining, by the one or more processors, the traffic pattern data to determine a second traffic flow of the multiple SDVs occupied by members of the cohort of drivers, wherein the multiple SDVs in the second traffic flow are operating in manual mode on the roadway; and

in response to determining that the first traffic flow has a lower accident rate than the second traffic flow, prohibiting, by the one or more processors, the SDV from operating in manual mode.

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

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

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

determining, by the 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 a predefined level, prohibiting, by the one or more processors, the SDV from operating in manual mode.

11. The processor-implemented method of claim 1, further comprising:

receiving, by the one or more processors, operational readings from one or more operational sensors on the SDV, wherein the 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, prohibiting, by the one or more processors, the SDV from operating in manual mode and transferring autonomous control of the SDV to the SDV on-board computer.

12. A computer program product for controlling a driving 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 that an SDV is being operated in manual mode by a human driver;

detecting that a telecommunication device within the SDV is receiving a telecommunication message;

in response to detecting that the telecommunication device within the SDV is receiving the telecommunication message, determining that the human driver is unqualified to operate the SDV in manual mode based on the telecommunication device receiving the telecommunication message; and

in response to determining that the human driver is unqualified to operate the SDV in manual mode, transferring control of the SDV to an SDV on-board computer to place the SDV in autonomous mode, wherein the SDV is in the autonomous mode when steering, braking, throttle control, and obstacle avoidance by the SDV are all controlled by the SDV on-board computer.

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

determining a response requirement of the telecommunication message, wherein an urgent response requirement requires a response to the telecommunication message within a first predefined amount of time after receipt of the telecommunication message, and wherein a non-urgent response requirement requires no response to the telecommunication message until after a second predefined amount of time after receipt of the telecommunication message, wherein the first predefined amount of time is shorter than the second predefined amount of time; and

in response to determining that the response requirement is the urgent response requirement, automatically placing the SDV into autonomous mode.

14. The computer program product of claim 12, wherein said determining that the human driver is unqualified to operate the SDV in manual mode comprises:

determining that the human driver is required to wear prescription eyewear by looking up data from a database about the human driver;

detecting that the human driver is not wearing prescription eyewear by receiving images of the human driver that are received from a cabin camera that captures the images of the human driver while the human driver is within a cabin of the SDV; and

in response to detecting that the human driver is not wearing prescription eyewear, further determining that the human driver is unqualified to operate the SDV in manual mode based on the human driver not wearing prescription eyewear.

15. The computer program product of claim 12, wherein said determining that the human driver is unqualified to operate the SDV in manual mode comprises:

detecting that an airbag in the SDV has deployed; and

in response to detecting that the airbag in the SDV has deployed, further determining that the human driver is unqualified to operate the SDV in manual mode based on the airbag having deployed.

16. The computer program product of claim 12, wherein the SDV is traveling on a roadway, and wherein the method further comprises:

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

assigning the human driver of the SDV to a cohort of drivers traveling on the roadway in multiple SDVs, wherein the human driver of the SDV shares more than a predetermined quantity of traits with members of the cohort of drivers;

retrieving traffic pattern data for the multiple SDVs occupied by the cohort of drivers traveling on the roadway;

examining the traffic pattern data to determine a first traffic flow of the multiple SDVs occupied by members of the cohort of drivers, wherein the multiple SDVs in the first traffic flow are operating in the autonomous mode on the roadway;

examining the traffic pattern data to determine a second traffic flow of the multiple SDVs occupied by members of the cohort of drivers, wherein the multiple SDVs in the second traffic flow are operating in manual mode on the roadway; and

in response to determining that the first traffic flow has a lower accident rate than the second traffic flow, prohibiting the SDV from operating in manual mode.

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

receiving operational readings from one or more operational sensors on the SDV, wherein the 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, prohibiting, by the on-board SDV control processor, the SDV from operating in manual mode.

18. A computer system comprising:

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

first program instructions to detect that an SDV is being operated in manual mode by a human driver;

second program instructions to detect, based upon receipt of a signal from a collision detector on the SDV, that the SDV has been involved in an accident;

third program instructions to, in response to detecting that the SDV has been involved in the accident, determine that the human driver is unqualified to operate the SDV in manual mode based on the SDV being involved in the accident; and

fourth program instructions to, in response to determining that the human driver is unqualified to operate the SDV in manual mode, transfer control of the SDV to an SDV on-board computer to place the SDV in autonomous mode, wherein the SDV is in the autonomous mode when steering, braking, throttle control, and obstacle avoidance by the SDV are all controlled by the SDV on-board computer;

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 non-transitory computer readable memory.