Determining driver engagement with autonomous vehicle

• US 10,209,708 B2
• Filed: 07/28/2016
• Issued: 02/19/2019
• Est. Priority Date: 07/28/2016
• Status: Active Grant

• Current Assignee: Lytx, Inc.
• Original Assignee: Lytx, Inc.
• Inventors: Hoye, Brett
• Primary Examiner(s): Shaawat, Mussa A
• Application Number:
  US15/222,516
• Publication Number:
  US 20180032072A1
• Time in Patent Office: 936 Days
• CPC Class Codes: B60K 28/02 responsive to conditions relating to the driver
• CPC Class Codes: B60W 2040/0818 Inactivity or incapacity of driver
• CPC Class Codes: B60W 2050/0075 Automatic parameter input, automatic initialising or calibrating means
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 2540/045 Occupant permissions
• CPC Class Codes: B60W 2540/22 Psychological state; Stress level or workload
• CPC Class Codes: B60W 2540/223 Posture, e.g. hand, foot, or seat position, turned or inclined
• 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 2555/20 Ambient conditions, e.g. wind or rain
• CPC Class Codes: B60W 2556/10 Historical data
• CPC Class Codes: B60W 30/182 Selecting between different operative modes, e.g. comfort and performance modes
• CPC Class Codes: B60W 40/08 related to drivers or passengers
• CPC Class Codes: B60W 50/082 Selecting or switching between different modes of propelling
• CPC Class Codes: B60W 50/10 Interpretation of driver requests or demands
• CPC Class Codes: B60W 50/14 Means for informing the driver, warning the driver or prompting a driver intervention
• 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: G05D 1/0061 for transition from automatic pilot to manual pilot and vice versa

Abstract

A method, system, and computer program product of controlling driver interaction with an autonomous vehicle (AV) system for a vehicle are provided. In an embodiment, a signal indicating a present state of the driver is received. A signal indicating a past state of the driver is received. A present effectiveness of the driver is determined based on the received signals. A target level of engagement of the driver with the AV system is determined based on the present effectiveness of the driver.

Claims

1. A method of controlling driver interaction with an autonomous vehicle (AV) system for a vehicle, the method comprising:

receiving, by a processor, a signal indicating a present state of a driver, wherein the signal includes an image collected by a camera;

receiving, by the processor, a signal indicating a past state of the driver;

scoring, by the processor, performance of the driver including by determining an effectiveness of the driver based on the received signals;

determining, by the processor, a target level of engagement of the driver with the AV system based on the driver performance score;

determining, by the processor, that a present driver engagement level meets the target engagement level;

if the present driver engagement level meets the target engagement level, at least one of (i) outputting a recommendation to the driver regarding the AV system and (ii) automatically changing a mode of operation of the AV system;

identifying, by the processor, a skill of the driver to be improved;

determining, by the processor, based on at least one of sensor data, map data and environment information, that the driver is encountering a driving situation relevant to the skill to be improved;

in response to the determination that the vehicle is encountering the driving situation relevant to the skill, prompting the driver to practice the skill by at least one of;

(i) providing, by the processor, a recommendation to the driver to operate the vehicle in a non-autonomous mode and (ii) disengaging, by the processor, the AV system.

2. The method of claim 1, wherein the target level of engagement defines whether to recommend that the driver operate the vehicle in a non-autonomous mode.

3. The method of claim 1, further comprising:

receiving, by the processor, a policy, wherein the determination of the target level of engagement is further based on the policy.

4. The method of claim 3, further comprising:

at least one of (i) providing, by the processor, a recommendation to the driver and (ii) changing, by the processor, a mode of operation of the AV system, based on a determination, by the processor, that the policy has been violated.

5. The method of claim 1, wherein the determination of the target level of engagement is further based on an attentiveness level of the driver sufficient to maintain an experience rating.

6. The method of claim 1, wherein the determination of the target level of engagement is further based on an attentiveness level of the driver sufficient to operate the vehicle in an autonomous mode.

7. The method of claim 1, further comprising:

determining, by the processor, whether to recommend coaching for the driver based on the effectiveness of the driver.

8. The method of claim 1, further comprising:

determining, by the processor, whether to recommend simulation training for the driver based on the effectiveness of the driver.

9. The method of claim 1, wherein the present state signal is based on a detection, by a sensor, of driver activity.

10. The method of claim 1, wherein the determination of the target level of engagement includes determining a target time for disengaging the AV system.

11. The method of claim 1, wherein the determination of the target level of engagement includes determining a target time for providing a warning to the driver regarding disengagement of the AV system.

12. The method of claim 1, further comprising:

determining a target time for disengaging the AV system.

13. The method of claim 1, further comprising:

determining a target time for providing a warning regarding disengagement of the AV system.

14. The method of claim 1, wherein the past state signal includes when the driver recently napped.

15. The method of claim 1, wherein the past state signal includes at least one of:

vehicle information, environment, and driver behavioral information.

16. The method of claim 1, further comprising:

receiving, by the processor, environment data indicating a driving situation;

determining, by the processor, whether the AV system performs or is expected to perform below a threshold when encountering the driving situation;

if the AV system performs below the threshold, at least one of;

making a recommendation to the driver and disengaging the AV system.

17. The method of claim 1, further comprising:

responsive to driver operation of the vehicle in a non-autonomous mode in the driving situation, determining, by the processor, whether the skill of the driver has improved;

if the skill of the driver has not improved, recommending, by the processor, coaching for the driver.

18. A system for controlling driver interaction with an autonomous vehicle (AV) system for a vehicle, the system comprising:

a processor configured to;

receive a signal indicating a present state of the driver, wherein the signal includes an image collected by a camera;

receive a signal indicating a past state of the driver;

score performance of the driver including by determining an effectiveness of the driver based on the received signals;

determine a target level of engagement of the driver with the AV system based on the determined driver performance score;

determine that a present driver engagement level meets the target engagement level;

if the present driver engagement level meets the target engagement level, at least one of (i) output a recommendation to the driver regarding the AV system and (ii) automatically change a mode of operation of the AV system;

identify a skill of the driver to be improved;

determine, based on at least one of sensor data, map data and environment information, that the driver is encountering a driving situation relevant to the skill to be improved;

in response to the determination that the vehicle is encountering the driving situation relevant to the skill, prompt the driver to practice the skill by at least one of;

(i) provide a recommendation to the driver to operate the vehicle in a non-autonomous mode and (ii) disengage the AV system; and

a non-transitory memory coupled to the processor and configured to provide the processor with instructions.

19. A computer program product for controlling driver interaction with an autonomous vehicle (AV) system for a vehicle, the computer program product being embodied in a non-transitory computer-readable storage medium and comprising computer instructions for:

receiving a signal indicating a present state of the driver, wherein the signal includes an image collected by a camera;

receiving a signal indicating a past state of the driver;

scoring performance of the driver including by determining an effectiveness of the driver based on the received signals;

determining a target level of engagement of the driver with the AV system based on the driver performance score;

determining that a present driver engagement level meets the target engagement level;

if the present driver engagement level meets the target engagement level, at least one of (i) outputting a recommendation to the driver regarding the AV system and (ii) automatically changing a mode of operation of the AV system;

identifying a skill of the driver to be improved;

determining, based on at least one of sensor data, map data and environment information, that the driver is encountering a driving situation relevant to the skill to be improved;

in response to the determination that the vehicle is encountering the driving situation relevant to the skill, prompting the driver to practice the skill by at least one of;

(i) providing a recommendation to the driver to operate the vehicle in a non-autonomous mode and (ii) disengaging the AV system.