Location specific assistance for autonomous vehicle control system

• US 10,133,273 B2
• Filed: 09/20/2016
• Issued: 11/20/2018
• Est. Priority Date: 09/20/2016
• Status: Active Grant

• Current Assignee: Blackberry Limited
• Original Assignee: 2236008 Ontario Inc. (Blackberry Limited)
• Inventors: Linke, Scott Lee
• Primary Examiner(s): Badii, Behrang
• Assistant Examiner(s): Testardi, David A
• Application Number:
  US15/271,170
• Publication Number:
  US 20180081362A1
• Time in Patent Office: 791 Days
• CPC Class Codes: B60W 2050/0292 Fail-safe or redundant systems, e.g. limp-home or backup systems
• 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 2420/54 Audio sensitive means, e.g. ultrasound
• CPC Class Codes: B60W 2552/53 Road markings, e.g. lane marker or crosswalk
• CPC Class Codes: B60W 2554/406 Traffic density
• CPC Class Codes: B60W 2555/20 Ambient conditions, e.g. wind or rain
• CPC Class Codes: B60W 2556/45 External transmission of data to or from the vehicle
• CPC Class Codes: B60W 50/029 Adapting to failures or work around with other constraints, e.g. circumvention by avoiding use of failed parts
• CPC Class Codes: B60W 60/001 Planning or execution of driving tasks
• CPC Class Codes: B60W 60/00186 related to the vehicle
• CPC Class Codes: G05D 1/0022 characterised by the communication link data switching networks in general H04L12/00
• CPC Class Codes: G05D 1/0221 involving a learning process
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G08G 1/00 Traffic control systems for road vehicles arrangement of road signs or traffic signals E01F9/00 ; automatic vehicle control B62D
• 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 1/0145 for active traffic flow control
• CPC Class Codes: G08G 1/096725 where the received information generates an automatic action on the vehicle control
• CPC Class Codes: G08G 1/096741 : where the source of the transmitted information selects which information to transmit to each vehicle
• CPC Class Codes: G08G 1/096775 : where the origin of the information is a central station

Abstract

Systems and methods to provide location specific assistance are presented. A condition at a geographic location may be identified that is sensed in an environment of a vehicle and that a first autonomous vehicle control system is unable to, without location specific assistance, perceive, interpret and/or react to if navigating an area. A course at the geographic location that was previously determined by a second autonomous vehicle control system and/or followed by a person-driven vehicle when the condition was present at the geographic location may be found. The vehicle may be caused to follow the course previously determined by a second autonomous vehicle control system and/or followed by the person-driven vehicle.

Claims

1. A system to provide location specific assistance, the system comprising:

a processor configured to;

determine with a first autonomous vehicle control system how to navigate a first vehicle based on a first artificial intelligence learning model supplied with first sensor data from at least one sensor of the first vehicle;

receive a second artificial intelligence learning model in response to a failure of the first autonomous vehicle control system to determine how to navigate the first vehicle past a condition present at a geographic location based on the first artificial intelligence learning model, the second artificial intelligence learning model is usable for a predetermined timeframe, the second artificial intelligence learning model trained with second sensor data collected when the condition was present at the geographic location and a course past the condition was determined by a second autonomous vehicle control system and/or followed by a person-driven vehicle;

find the course based on an application of the second artificial intelligence learning model within the predetermined timeframe to third sensor data sensed in an environment of the first vehicle at the geographic location; and

cause the first vehicle to follow the course.

2. The system of claim 1 wherein the course is found if the course at the geographic location was within a threshold time period of when the condition is identified.

3. The system of claim 1 wherein the second artificial intelligence learning model is trained with a database of location specific conditions, the database is populated with data from at least one of person-driven vehicles or vehicles controlled by the second autonomous vehicle control system.

4. An autonomous vehicle, the autonomous vehicle comprising:

a processor configured to;

determine that, due to a condition at a geographic location sensed in an environment of the autonomous vehicle, a first autonomous vehicle control system, based on a first artificial intelligence learning model, is unable to cause the autonomous vehicle to navigate past the condition;

receive a second artificial intelligence learning model in response to a determination that the first autonomous vehicle control system is unable to cause the autonomous vehicle to navigate past the condition at the geographic location, the second artificial intelligence learning model only usable for a predetermined timeframe, the second artificial intelligence learning model specifically trained with information collected when the condition was present at the geographic location and a course past the condition was determined by a second autonomous vehicle control system and/or followed by a person-driven vehicle;

find the course at the geographic location based on the second artificial learning model; and

cause the autonomous vehicle to follow the course previously determined by the second autonomous vehicle control system and/or followed by the person-driven vehicle.

5. The autonomous vehicle of claim 4 wherein the course is found via a search of a database of conditions and geographic locations for a match with the condition at the geographic location.

6. The autonomous vehicle of claim 5 wherein the database is on a server remotely located with respect to the autonomous vehicle.

7. The autonomous vehicle of claim 4 wherein the first autonomous vehicle control system is unable to navigate past the condition if the first autonomous vehicle control system indicates that the first autonomous vehicle control system is unable to at least one of perceive, interpret, or react to the condition.

8. The autonomous vehicle of claim 4, wherein the condition is identified in response to a determination that the first autonomous vehicle control system is unable to at least one of perceive, interpret or react to the condition.

9. The autonomous vehicle of claim 4 wherein the course is found if the course at the geographic location was followed by the person-driven vehicle within a predetermined time period of when the condition is identified.

10. The autonomous vehicle of claim 4 comprising a database of conditions, geographic locations, and courses, the database populated with data from person-driven vehicles, wherein the processor is configured to find the course via a search of the database based on a match of the condition.

11. A method comprising:

determining a condition at a geographic location that is sensed in an environment of a vehicle, the condition preventing a first autonomous vehicle control system, which is based on a first artificial learning model, from navigating an area that includes the geographic location, and/or the condition causing a confidence level of the first autonomous vehicle control system in navigating the area to fall below a threshold level;

receiving a second artificial intelligence learning model usable for a predetermined timeframe, the second artificial intelligence learning model trained with sensor data collected when the condition was present at the geographic location and a course past the condition was determined by a second autonomous vehicle control system and/or followed by a person-driven vehicle;

finding the course at the geographic location based on application of the second artificial intelligence learning model; and

causing the vehicle to follow the course at the geographic location past the condition.

12. The method of claim 11 wherein the determining comprises receiving an indication from the first autonomous vehicle control system that the condition prevents the first autonomous vehicle control system from navigating the area that includes the geographic location and/or causes the confidence level to fall below the threshold level.

13. The method of claim 11 wherein finding the course comprises finding the course at the geographic location previously followed by the person-driven vehicle within a threshold time period.

14. A non-transitory computer readable storage medium comprising computer executable instructions executable by at least one processor to:

determine a condition at a geographic location that is sensed in an environment of a vehicle, the condition preventing a first autonomous vehicle control system, which is based on a first artificial learning model, from navigating an area that includes the geographic location, and/or the condition causing a confidence level of the first autonomous vehicle control system in navigating the area to fall below a threshold level;

receive a second artificial intelligence learning model usable for a predetermined timeframe, the second artificial intelligence learning model trained with sensor data collected when the condition was present at the geographic location and a course past the condition was determined by a second autonomous vehicle control system and/or followed by a person-driven vehicle;

find the course at the geographic location based on application of the second artificial intelligence learning model; and

cause the vehicle to follow the course past the condition.