US 12,474,705 B2
Task-specific and environment-specific adaptive control of legged robot
Marcel Menner, Arlington, MA (US); Stefano Di Cairano, Newton, MA (US); and Alexander Schperberg, Los Angeles, CA (US)
Assigned to Mitsubishi Electric Research Laboratories, Inc., Cambridge, MA (US)
Filed by Mitsubishi Electric Research Laboratories, Inc.
Filed on Dec. 6, 2022, as Appl. No. 18/062,167.
Claims priority of provisional application 63/365,164, filed on May 23, 2022.
Prior Publication US 2023/0376034 A1, Nov. 23, 2023
Int. Cl. B25J 9/16 (2006.01); B62D 57/032 (2006.01); G05D 1/00 (2006.01)
CPC G05D 1/0088 (2013.01) [B25J 9/163 (2013.01); B25J 9/1633 (2013.01); B62D 57/032 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A control system for controlling a legged robot, wherein the control system comprises a processor; and a memory having instructions stored thereon that, when executed by the processor, causes the control system to:
initialize, in response to receiving a task, a probabilistic filter with parameters associated with a state of a reference trajectory of the legged robot, wherein the parameters are predetermined for the task and encode the reference trajectory including a combination of different trajectories for coordinated motion primitives of different actuators of the legged robot, moving the legged robot according to the task, and wherein the parameters are defined based on a weighted combination of a set of basis functions, the set of basis functions includes a linear basis function for a center of mass of the legged robot and a cycloidal basis function for feet of the legged robot;
decode the parameters to generate the reference trajectory;
execute, in response to receiving a feedback signal indicative of a change of a state of the legged robot moving according to the reference trajectory, the probabilistic filter to iteratively track the state of the reference trajectory satisfying a performance objective with respect to the state of the legged robot to update the parameters;
update the reference trajectory by decoding the updated parameters;
generate control inputs to actuators of the legged robot based on the updated reference trajectory; and
control the actuators of the legged robot based on the corresponding control inputs.