Modifying behavior of autonomous vehicle based on advanced predicted behavior analysis of nearby drivers

• US 10,249,194 B2
• Filed: 08/30/2016
• Issued: 04/02/2019
• Est. Priority Date: 08/30/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Erickson, Thomas D., Pickover, Clifford A., Walcott, Aisha, Weldemariam, Komminist
• Primary Examiner(s): Kan, Yuri
• Application Number:
  US15/251,104
• Publication Number:
  US 20180061237A1
• Time in Patent Office: 945 Days
• CPC Class Codes: B60W 2040/0872 Driver physiology
• CPC Class Codes: B60W 2540/045 Occupant permissions
• CPC Class Codes: B60W 2556/05 Big data
• CPC Class Codes: B60W 2556/65 Data transmitted between vehicles
• CPC Class Codes: B60W 30/0956 the prediction being responsive to traffic or environmental parameters
• CPC Class Codes: B60W 40/09 Driving style or behaviour
• CPC Class Codes: B60W 60/00276 for two or more other traffic participants
• CPC Class Codes: G08G 1/0112 from the vehicle, e.g. floating car data [FCD]
• CPC Class Codes: G08G 1/0129 for creating historical data or processing based on historical data
• CPC Class Codes: G08G 1/0141 for traffic information dissemination
• CPC Class Codes: G08G 1/163 involving continuous checking
• CPC Class Codes: G08G 1/164 Centralised systems, e.g. external to vehicles
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes
• CPC Class Codes: G08G 5/0069 specially adapted for an unmanned aircraft

Abstract

A method, apparatus, and computer program product for assessing one or more features of drivers within a threshold distance of a self-driving vehicle which has sensors to monitor driving conditions on a travel route within the threshold distance, predicting the behavior of one or more vehicles within the threshold distance based on the assessment of those features, and utilizing the predicted behavior for the self-driving vehicle to drive on the travel route. Changes in the condition or usage of the travel route, the surroundings, and pedestrians and other types of vehicles in the vicinity of the travel route can go into the assessment. Changes in the assessment can alert the self-driving vehicle to change course and the way it monitors data. Information regarding other drivers can be privatized and utilized using a blockchain system.

Claims

1. A method comprising:

assessing one or more features of drivers within a threshold distance of a self-driving vehicle, wherein the self-driving vehicle comprises sensors to monitor driving conditions on a travel route within the threshold distance;

based on the assessing, predicting a behavior of one or more vehicles within the threshold distance;

driving by the self-driving vehicle on the travel route utilizing the predicted behavior.

2. The method of claim 1, wherein the threshold distance is changed based on at least one of the following on the travel route:

road conditions;

weather conditions;

time of day;

types/classes of nearby vehicles;

safety features of nearby vehicles.

3. The method of claim 1, wherein the threshold distance is changed based on at least one of the following aspects surrounding and/or intersecting the travel route:

number of pedestrians;

density of pedestrians;

turbulence of pedestrians;

presence of children and other classes requiring extra vigilance;

presence of people utilizing other types of vehicles not requiring licenses.

4. The method of claim 1, wherein the one or more features comprise at least one of the following:

past driving history;

cohort of driver; and

behavior of the driver over a previous time period.

5. The method of claim 1, further comprising at least one of the following:

communicating with at least one other vehicle within the threshold distance;

activating sensors in at least one other vehicle within the threshold distance and utilizing such active sensor data;

accessing data from at least one other vehicle within the threshold distance; and

dynamically controlling the driving of at least one other self-driving vehicle within the threshold distance.

6. The method of claim 1, further comprising:

based on the predicting, determining a risk of collision and, in response to a risk of collision determined to be over a threshold, altering an alert level.

7. The method of claim 6, further comprising:

in response to the altering of the alert level changing the driving by the self-driving vehicle by at least one of the following;

speed;

position; and

lane; and

vigilance.

8. The method of claim 7, wherein vigilance comprises at least one of the following:

a detail level of processing data retrieved from sensor monitoring;

an algorithm of processing data retrieved from sensor monitoring;

a usage level of data retrieved from sensor monitoring;

a weighting of data retrieved from sensor monitoring;

a utilization of data from an activation of backup, redundant, and/or secondary sensors to monitor the travel route;

a leveraging of data from communicating with other vehicles within the threshold distance; and

a mixing of data by dynamically controlling sensors of various capabilities.

9. The method of claim 1, further comprising:

employing a blockchain system for driver privacy and information validation, wherein the blockchain system maintains a driving history of the one or more features of drivers within the threshold distance.

10. The method of claim 9, wherein the employing comprises logging the sensor data into the blockchain system, wherein any transaction that writes or reads data to/from the blockchain system is managed by consensus.

11. The method of claim 9, further comprising, fetching the one or more features of drivers within the threshold distance in real-time via a client application connected to the blockchain system, wherein the fetching is based on an identification associated with drivers.

12. The method of claim 9, wherein the blockchain system is an open blockchain network.

13. The method of claim 1, further comprising:

learning an environment context from at least wisdom crowdsourcing, blockchain data sources, or collaborative networks.

14. The method of claim 1, wherein the sensors of the self-driving vehicle further comprise a feed video stream for visual analytics and deep learning.

15. The method of claim 1, wherein the self-driving vehicle is an autonomous flying vehicle).

16. The method of claim 1, wherein the one or more features comprises a level of the driver'"'"'s attention to driving, estimated upon at least one of the following:

high variance of reaction time to particular events;

non-driving behaviors such as talking, looking around, adjusting a mirror;

detection of proximal human behavior such as a companion who is talking or gesturing;

detection of potentially distracting proximal events such as a roadside accident; and

physiological signs of attentional deficits.

17. The method of claim 1, wherein drivers comprise those operating mobile machinery.

18. An apparatus, comprising:

at least one processor; and

at least one memory including computer program code,

the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following;

assessing one or more features of drivers within a threshold distance of a self-driving vehicle, wherein the self-driving vehicle comprises sensors to monitor driving conditions on a travel route within the threshold distance;

based on the assessing, predicting a behavior of one or more vehicles within the threshold distance;

driving by the self-driving vehicle on the travel route utilizing the predicted behavior.

19. A computer program product comprising a tangible computer-readable medium bearing computer program code embodied therein for use with a computer, the computer program code comprising code for:

assessing one or more features of drivers within a threshold distance of a self-driving vehicle, wherein the self-driving vehicle comprises sensors to monitor driving conditions on a travel route within the threshold distance;

based on the assessing, predicting a behavior of one or more vehicles within the threshold distance;

driving by the self-driving vehicle on the travel route utilizing the predicted behavior.