US 12,330,315 B2
Systems, devices, and methods for developing robot autonomy
Geordie Rose, Vancouver (CA)
Assigned to Sanctuary Cognitive Systems Corporation, Vancouver (CA)
Filed by Sanctuary Cognitive Systems Corporation, Vancouver (CA)
Filed on Apr. 12, 2022, as Appl. No. 17/719,110.
Claims priority of provisional application 63/173,670, filed on Apr. 12, 2021.
Prior Publication US 2022/0324113 A1, Oct. 13, 2022
Int. Cl. B25J 9/16 (2006.01); G05B 19/4155 (2006.01)
CPC B25J 9/1689 (2013.01) [B25J 9/163 (2013.01); G05B 19/4155 (2013.01); G05B 2219/40195 (2013.01); G05B 2219/50391 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method of operation of a fleet of robots, the method comprising:
identifying, by a first robot in the fleet of robots, a set of candidate actions that may be performed by a first robot;
collecting, by at least one sensor onboard the first robot and for each candidate action of the set of candidate actions, a respective set of sensor data;
transmitting, by the first robot, a request for instructions to a tele-operation system, the tele-operation system communicatively coupled to the fleet of robots, the request for the instructions which includes each candidate action of the set of candidate actions and each respective set of sensor data;
receiving, by the first robot, the instructions from the tele-operation system;
executing, by the first robot, the instructions;
updating, by the first robot, a first control model of the first robot, based at least in part on each candidate action of the set of candidate actions, each respective set of sensor data, and the instructions, to increase a level of autonomy of the first robot;
sending, by the first robot and directly to a second robot in the fleet of robots, control model update instructions based on the update made to the first control model; and
updating, by the second robot, a second control model of the second robot, based at least in part on the update made to the first control model of the first robot, to increase a level of autonomy of the second robot, wherein the second control model of the second robot is different from the first control model of the first robot.