Systems and methods for remote operation of robot vehicles

Patent metadata

Field	Value
Publication number	US-2019056733-A1
Application number	US-201816048737-A
Country	US
Kind code	A1
Filing date	Jul 30, 2018
Priority date	Jul 28, 2017
Publication date	Feb 21, 2019
Grant date	—

Abstract

An autonomous robot vehicle in accordance with aspects of the present disclosure includes a land vehicle conveyance system, a sensor system configured to capture information including surrounding environment information and/or vehicle subsystem information, a communication system configured to communicate with a remote human operator management system, at least one processor, and a memory storing instructions. The instructions, when executed by the processor(s), cause the autonomous robot land vehicle to, autonomously, determine based on the captured information to request a remote human operator, and communicate a request to the remote human operator management system for a remote human operator to assume control of the land vehicle conveyance system, where the request includes at least a portion of the captured information.

First claim

What is claimed is:

1 . An autonomous robot land vehicle comprising:
a land vehicle conveyance system; a sensor system configured to capture information including at least one of: surrounding environment information or vehicle subsystem information; a communication system configured to communicate with a remote human operator management system; at least one processor; and a memory storing instructions which, when executed by the at least one processor, cause the autonomous robot land vehicle to, autonomously:
determine, based on the captured information, to request a remote human operator, and
communicate a request to the remote human operator management system for a remote human operator to assume control of the land vehicle conveyance system, the request including at least a portion of the captured information.

2 . The autonomous robot land vehicle of claim 1 , wherein in determining to request a remote human operator, the instructions, when executed by the at least one processor, cause the autonomous robot land vehicle to determine, based on the vehicle subsystem information, that at least one subsystem is not functioning properly.

3 . The autonomous robot land vehicle of claim 1 , wherein in determining to request a remote human operator, the instructions, when executed by the at least one processor, cause the autonomous robot land vehicle to determine, based on the captured information, that a next maneuver cannot be autonomously determined.

4 . The autonomous robot land vehicle of claim 1 , wherein in determining to request a remote human operator, the instructions, when executed by the at least one processor, cause the autonomous robot land vehicle to determine, based on the surrounding environment information, that a surrounding environment situation is not recognized.

5 . The autonomous robot land vehicle of claim 4 , wherein in determining to request a remote human operator, the instructions, when executed by the at least one processor, cause the autonomous robot land vehicle to:
access predetermined situations or predetermined roadways that are predetermined to require a request for a remote human operator; and determine, based on the captured information, that at least one of the predetermined situations or the predetermined roadways has been encountered.

6 . The autonomous robot land vehicle of claim 1 , wherein in determining to request a remote human operator, the instructions, when executed by the at least one processor, cause the autonomous robot land vehicle to determine, based on the surrounding environment information, that a surrounding environment situation should not be autonomously handled.

7 . The autonomous robot land vehicle of claim 6 , wherein in determining to request a remote human operator, the instructions, when executed by the at least one processor, cause the autonomous robot land vehicle to determine, based on the vehicle subsystem information, that a situation of at least one subsystem is not recognized.

8 . The autonomous robot land vehicle of claim 6 , wherein in determining to request a remote human operator, the instructions, when executed by the at least one processor, cause the autonomous robot land vehicle to:
access a predetermined operating geography; and determine, based on the surrounding environment information, that the autonomous robot land vehicle is outside the predetermined operating geography.

9 . The autonomous robot land vehicle of claim 6 , wherein in determining to request a remote human operator, the instructions, when executed by the at least one processor, cause the autonomous robot land vehicle to determine, based on the captured information, that multiple attempts to execute an autonomous maneuver have failed.

10 . The autonomous robot land vehicle of claim 1 , wherein the instructions, when executed by the at least one processor, cause the autonomous robot land vehicle to determine a risk rating based on the captured information.

11 . The autonomous robot land vehicle of claim 10 , wherein in determining a risk rating based on the captured information, the instructions, when executed by the at least one processor, cause the autonomous robot land vehicle to determine the risk rating based on estimated safety of autonomous risk mitigation procedures that can be effectuated while waiting for a remote human operator to assume control.

12 . The autonomous robot land vehicle of claim 11 , wherein in determining the risk rating based on estimated safety of autonomous risk mitigation procedures, the instructions, when executed by the at least one processor, cause the autonomous robot land vehicle to:
access the risk mitigation procedures; estimate, based on the captured information, probability of success in executing the risk mitigation procedures; and determine the risk rating based on the estimated probability of success.

13 . The autonomous robot land vehicle of claim 12 , wherein in estimating the probability of success in executing the risk mitigation procedures, the instructions, when executed by the at least one processor, cause the autonomous robot land vehicle to estimate the probability of success based on at least one of: road speed limits, current vehicle speed, current speed of surrounding vehicles, number of surrounding vehicles, number of surrounding pedestrians, number of surrounding objects, road width, weather conditions, available time to react, or proximity to surrounding vehicles.

14 . The autonomous robot land vehicle of claim 10 , wherein the instructions, when executed by the at least one processor, cause the autonomous robot land vehicle to control the land vehicle conveyance system to mitigate risk while waiting for a remote human operator to assume control.

15 . The autonomous robot land vehicle of claim 14 , wherein in controlling the land vehicle conveyance system to mitigate risk, the instructions, when executed by the at least one processor, cause the autonomous robot land vehicle to perform at least one of: park at a curb, parking in a parking lot, travel on roadways in search of parking, or depart from a planned route to a roadway having lower risk.

16 . The autonomous robot land vehicle of claim 14 , wherein in controlling the land vehicle conveyance system to mitigate risk, the instructions, when executed by the at least one processor, cause the autonomous robot land vehicle to travel at a slower speed than a travel speed without the risk.

17 . The autonomous robot land vehicle of claim 1 , wherein the autonomous robot land vehicle does not contain any space for a human passenger or human operator to be within the autonomous robot land vehicle.

18 . A system for assigning remote human operators to autonomous land vehicles, the system comprising:
a database including experience information on a plurality of remote human operators; a communication system configured to communicate with a plurality of remote autonomous land vehicles; at least one processor; and a memory storing instructions which, when executed by the at least one processor, cause the system to:
receive, via the communication system, requests from the remote autonomous land vehicles for remote human operators to assume control, each of the requests including risk information generated by the corresponding remote autonomous land vehicle,
determine that a number of the requests is greater than a number of available remote human operators,
access risk ratings associated with the requests, wherein the risk ratings include at least one of: ratings determine

Assignees

• Nuro Inc

Inventors

• Ferguson David
• Zhu Jiajun
• Shen Yi
• Giroud Calvin
• Pu Qunyan

Classifications

• G01C21/343

  Calculating itineraries (travelling salesman problem G06Q10/04; optimisation of routes G06Q10/047) · CPC title

• G06N20/00

  Machine learning · CPC title

• G06Q10/08

  Logistics, e.g. warehousing, loading or distribution; Inventory or stock management · CPC title

• B64U2201/10

  autonomous, i.e. by navigating independently from ground or air stations, e.g. by using inertial navigation systems [INS] · CPC title

• G06Q10/083

  Shipping · CPC title