Systems and methods for deploying an autonomous vehicle to oversee autonomous navigation

• US 10,818,187 B2
• Filed: 07/17/2017
• Issued: 10/27/2020
• Est. Priority Date: 07/17/2017
• Status: Active Grant

• Current Assignee: Uatc, LLC (Uber Technologies, Inc.)
• Original Assignee: Uatc, LLC (Uber Technologies, Inc.)
• Inventors: Perko, Eric Michael
• Primary Examiner(s): Hilgendorf, Dale W
• Assistant Examiner(s): Bost, Alexander C.
• Application Number:
  US15/651,362
• Publication Number:
  US 20190019416A1
• Time in Patent Office: 1,198 Days
• Field of Search: None
• CPC Class Codes: G05D 1/0011 associated with a remote control arrangement
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• 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 1/096758 where no selection takes place on the transmitted or the received information
• CPC Class Codes: G08G 1/096775 where the origin of the information is a central station
• CPC Class Codes: G08G 1/096791 where the origin of the information is another vehicle
• CPC Class Codes: G08G 1/162 event-triggered
• 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 1/165 for passive traffic, e.g. including static obstacles, trees
• CPC Class Codes: G08G 1/202 Dispatching vehicles on the basis of a location, e.g. taxi dispatching

Abstract

Systems and methods for controlling an autonomous vehicle to assist another autonomous vehicle are provided. In one example embodiment, a computer-implemented method includes obtaining data representing a vehicle route of a first autonomous vehicle, wherein the first autonomous vehicle travels along the vehicle route from a first location to a second location. The method includes obtaining data representing an occlusion point that affects an operation of the first autonomous vehicle along the vehicle route. The method includes selecting a second autonomous vehicle, based at least in part on (i) the vehicle route and (ii) the occlusion point, to assist the first autonomous vehicle. The method includes deploying the second autonomous vehicle to assist the first autonomous vehicle to travel along the vehicle route.

Claims

1. A computer-implemented method for controlling an autonomous vehicle to assist another autonomous vehicle, the method comprising:

obtaining, by a computing system comprising one or more computing devices, data representing a vehicle route of a first autonomous vehicle, wherein the first autonomous vehicle travels along the vehicle route from a first location to a second location;

obtaining, by the computing system, data representing an identified occlusion point at a geographic location, the identified occlusion point corresponding to one or more regions at the geographic location where one or more sensors of the autonomous vehicle are unable to perceive the surrounding environment;

accessing, by the computing system, a remote computing system storing autonomous vehicle (AV) data that comprises information corresponding to characteristics of a plurality of additional autonomous vehicles, the AV data comprising one or more of a vehicle route for each additional autonomous vehicle, a motion plan for each additional autonomous vehicle, occupancy status for each additional autonomous vehicle, geographic location for each additional autonomous vehicle, or vehicle type for each additional autonomous vehicle;

selecting, by the computing system, and based at least in part on (i) the vehicle route, (ii) the identified occlusion point, and (iii) the AV data corresponding to the characteristics of the plurality of additional autonomous vehicles, a second autonomous vehicle from the plurality of additional autonomous vehicles to assist the first autonomous vehicle, wherein the second autonomous vehicle is selected from the plurality of additional autonomous vehicles based at least in part on a time-to-deploy the second autonomous vehicle to the identified occlusion point; and

deploying, by the computing system, the second autonomous vehicle to assist the first autonomous vehicle to travel along the vehicle route;

wherein deploying the second autonomous vehicle to assist the first autonomous vehicle comprises providing, by the computing system, a communication to cause the second autonomous vehicle to travel to a vicinity of the geographic location, wherein the second autonomous vehicle travels to the vicinity of the geographic location in response to receiving the communication.

2. The computer-implemented method of claim 1, wherein the data representing the identified occlusion point is determined based on (i) sensor data acquired by one or more sensors on-board the first autonomous vehicle or (ii) sensor data acquired by one or more sensors on-board the second autonomous vehicle or (iii) sensor data acquired by one or more sensors on-board another autonomous vehicle.

3. The computer-implemented method of claim 1, wherein obtaining the data representing the identified occlusion point comprises:

obtaining data representing the identified occlusion point identified by the second autonomous vehicle or one or more other autonomous vehicles.

4. The computer-implemented method of claim 1, wherein obtaining the data representing the identified occlusion point comprises:

obtaining, by the computing system, data indicative of the identified occlusion point from a memory accessible by the computing system, wherein the identified occlusion point is a predetermined occlusion point.

5. The computer-implemented method of claim 1, wherein the identified occlusion point comprises one or more geographic locations along the vehicle route where the first autonomous vehicle is occluded by one or more objects in a surrounding environment of the first autonomous vehicle.

6. The computer-implemented method of claim 1, wherein deploying the second autonomous vehicle to assist the first autonomous vehicle comprises:

deploying the second autonomous vehicle to determine the one or more objects in a surrounding environment of the second autonomous vehicle at the geographic location.

7. The computer-implemented method of claim 1, further comprising:

determining, by the computing system, one or more occlusion points corresponding to the first autonomous vehicle, wherein the determining comprises;

obtaining data representing a motion plan of the first autonomous vehicle, the motion plan including one or more maneuvers that, when executed, cause the first autonomous vehicle to travel along the vehicle route;

determining an occluded maneuver, among the one or more maneuvers in the motion plan of the first autonomous vehicle, that is occluded by one or more objects in a surrounding environment of the first autonomous vehicle along the vehicle route; and

determining a geographic location corresponding to the occluded maneuver.

8. The computer-implemented method of claim 1, wherein:

selecting the second autonomous vehicle to assist the first autonomous vehicle comprises selecting the second autonomous vehicle, from among one or more second autonomous vehicles located within a predetermined distance from the identified occlusion point; and

deploying the second autonomous vehicle to assist the first autonomous vehicle comprises controlling the second autonomous vehicle to assist the first autonomous vehicle with respect to the identified occlusion point.

9. The computer-implemented method of claim 8, wherein the second autonomous vehicle is further selected based at least in part by prioritizing one or more of an unoccupied autonomous vehicle or a vehicle type different from a vehicle type of the first autonomous vehicle.

10. The computer-implemented method of claim 8, wherein controlling the second autonomous vehicle to assist the first autonomous vehicle comprises:

controlling the second autonomous vehicle to obtain data indicative of an occluded region of an environment at the identified occlusion point, the occluded region being occluded to the first autonomous vehicle at the identified occlusion point but not being occluded to the second autonomous vehicle; and

controlling the second autonomous vehicle to provide the data indicative of the occluded region to the first autonomous vehicle when the first autonomous vehicle is in the vicinity of the geographic location associated with the identified occlusion point.

11. The computer-implemented method of claim 8, wherein controlling the second autonomous vehicle to assist the first autonomous vehicle comprises:

controlling the second autonomous vehicle to provide a leeway for the first autonomous vehicle at the identified occlusion point.

12. The computer-implemented method of claim 1, wherein deploying the second autonomous vehicle to assist the first autonomous vehicle comprises:

providing a communication to cause the second autonomous vehicle to travel to a vicinity of the identified occlusion point, wherein the communication is provided to a remote computing system that provides a second communication to the second autonomous vehicle, and the second autonomous vehicle travels to the vicinity of the identified occlusion point in response to receiving the second communication.

13. The computer-implemented method of claim 1, wherein deploying the second autonomous vehicle to assist the first autonomous vehicle comprises:

providing a communication to request the second autonomous vehicle to assist the first autonomous vehicle with respect to the identified occlusion point.

14. A computing system for controlling an autonomous vehicle assist another autonomous vehicle, the system comprising:

one or more processors; and

one or more tangible, non-transitory, computer readable media that collectively store instructions that when executed by the one or more processors cause the computing system to perform operations, the operations comprising;

obtaining data representing a vehicle route of a first autonomous vehicle, wherein the first autonomous vehicle travels along the vehicle route from a first location to a second location;

obtaining data representing an identified occlusion point at a geographic location, the identified occlusion point corresponding to one or more regions at the geographic location where one or more sensors of the autonomous vehicle are unable to perceive the surrounding environment;

accessing a remote computing system storing autonomous vehicle (AV) data that comprises information corresponding to characteristics of a plurality of additional autonomous vehicles, the AV data comprising one or more of a vehicle route for each additional autonomous vehicle, a motion plan for each additional autonomous vehicle, occupancy status for each additional autonomous vehicle, geographic location for each additional autonomous vehicle, or vehicle type for each additional autonomous vehicle;

selecting, based at least in part on (i) the vehicle route, (ii) the identified occlusion point, and (iii) the AV data corresponding to the characteristics of the plurality of additional autonomous vehicles, a second autonomous vehicle from the plurality of additional autonomous vehicles to assist the first autonomous vehicle, wherein the second autonomous vehicle is selected from the plurality of additional autonomous vehicles based at least in part on a time-to-deploy the second autonomous vehicle to the identified occlusion point; and

deploying the second autonomous vehicle to assist the first autonomous vehicle to travel along the vehicle route;

wherein deploying the second autonomous vehicle to assist the first autonomous vehicle comprises providing a communication to cause the second autonomous vehicle to travel to a vicinity of the geographic location, wherein the second autonomous vehicle travels to the vicinity of the geographic location in response to receiving the communication.

15. The computing system of claim 14, wherein:

selecting the second autonomous vehicle to assist the first autonomous vehicle comprises selecting the second autonomous vehicle, from among one or more second autonomous vehicles located within a predetermined distance from the identified occlusion point; and

deploying the second autonomous vehicle to assist the first autonomous vehicle comprises controlling the second autonomous vehicle to assist the first autonomous vehicle with respect to the identified occlusion point.

16. The computing system of claim 15, wherein controlling the second autonomous vehicle to assist the first autonomous vehicle comprises:

controlling the second autonomous vehicle to obtain data indicative of an occluded region at the identified occlusion point, the occluded region being occluded to the first autonomous vehicle at the identified occlusion point but not being occluded to the second autonomous vehicle.

17. The computing system of claim 15, wherein controlling the second autonomous vehicle to assist the first autonomous vehicle comprises:

controlling the second autonomous vehicle to provide a leeway for the first autonomous vehicle at the identified occlusion point.

18. An autonomous vehicle, comprising:

one or more processors; and

one or more tangible, non-transitory, computer readable media that collectively store instructions that when executed by the one or more processors cause the autonomous vehicle to perform operations, the operations comprising;

obtaining data representing a vehicle route of a first autonomous vehicle, wherein the first autonomous vehicle travels along the vehicle route from a first location to a second location;

obtaining data representing an identified occlusion point at a geographic location, the identified occlusion point corresponding to one or more regions at the geographic location where one or more sensors of the autonomous vehicle are unable to perceive the surrounding environment;

accessing a remote computing system storing autonomous vehicle (AV) data that comprises information corresponding to characteristics of a plurality of additional autonomous vehicles, the AV data comprising one or more of a vehicle route for each additional autonomous vehicle, a motion plan for each additional autonomous vehicle, occupancy status for each additional autonomous vehicle, geographic location for each additional autonomous vehicle, or vehicle type for each additional autonomous vehicle;

selecting, based at least in part on (i) the vehicle route, and (ii) the identified occlusion point, and (iii) the AV data corresponding to the characteristics of the plurality of additional autonomous vehicles, a second autonomous vehicle from the plurality of additional autonomous vehicles to assist the first autonomous vehicle, wherein the second autonomous vehicle is selected from the plurality of additional autonomous vehicles based at least in part on a time-to-deploy the second autonomous vehicle to the identified occlusion point; and

deploying the second autonomous vehicle to assist the first autonomous vehicle to travel along the vehicle route;

wherein deploying the second autonomous vehicle to assist the first autonomous vehicle comprises providing a communication to cause the second autonomous vehicle to travel to a vicinity of the geographic location, wherein the second autonomous vehicle travels to the vicinity of the geographic location in response to receiving the communication.

19. The autonomous vehicle of claim 18, further comprising:

determining one or more occlusion points corresponding to the first autonomous vehicle, wherein the determining comprises;

obtaining data representing a motion plan of the first autonomous vehicle, the motion plan including one or more maneuvers that, when executed, cause the first autonomous vehicle to travel along the vehicle route;

determining a maneuver, among the one or more maneuvers in the motion plan of the first autonomous vehicle, that is occluded by one or more objects in a surrounding environment of the first autonomous vehicle along the vehicle route; and

determining a geographic location corresponding to the occluded maneuver.

20. The autonomous vehicle of claim 18, wherein deploying the second autonomous vehicle to assist the first autonomous vehicle comprises:

providing a communication to request the second autonomous vehicle to assist the first autonomous vehicle with respect to the identified occlusion point.