Robot control parameter interpolation

Patent metadata

Field	Value
Publication number	US-12521879-B2
Application number	US-202318319175-A
Country	US
Kind code	B2
Filing date	May 17, 2023
Priority date	May 27, 2020
Publication date	Jan 13, 2026
Grant date	Jan 13, 2026

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for computing interpolated robot control parameters. One of the methods includes receiving, by a real-time bridge from a control agent for a robot, a non-real-time command for the robot, wherein the non-real-time command specifies a trajectory to be attained by a component of the robot and a target value for a control parameter, wherein the control parameter controls how a real-time controller will cause the robot to react to one or more external stimuli encountered during a control cycle of the real-time controller. The real-time bridge provides the one or more real-time commands translated from the non-real-time command and interpolated control parameter information to the real-time controller, thereby causing the robot to effectuate the trajectory of the non-real-time command according to the interpolated control parameter information.

First claim

What is claimed is:

1 . A method performed by one or more computers, the method comprising:
receiving, by a robot interface subsystem, a command for a robot to perform a transition from performing a first task to performing a second task different than the first task; computing, by the robot interface subsystem, trajectory information for controlling the robot to execute the transition from performing the first task to performing the second task; computing, by the robot interface subsystem, interpolated control parameter information for the transition based on a first value of a control parameter assigned to the first task and a second value of a control parameter assigned to the second task, wherein the interpolated control parameter information is separate from the trajectory information and controls how the robot will react to external stimuli encountered by the robot when the robot performs the transition between the first task and the second task; and providing, by the robot interface subsystem, the trajectory information and the interpolated control parameter information to a real-time controller to effectuate the robot performing the transition according to the interpolated control parameter information.

2 . The method of claim 1 , wherein computing the interpolated control parameter information comprises:
obtaining, by the robot interface subsystem, a previous value of the control parameter; obtaining, by the robot interface subsystem, an updated value of the control parameter; and generating a control parameter trajectory that assigns a value between the previous value and the updated value of the control parameter to each of multiple points in a time period.

3 . The method of claim 2 , wherein the previous value of the control parameter is a current value of the control parameter.

4 . The method of claim 2 , wherein the multiple points in the time period correspond to real-time control cycles of the robot.

5 . The method of claim 1 , wherein the control parameter is a component stiffness parameter that represents how easily a robot component of the robot is moved by an external stimulus encountered by the robot.

6 . The method of claim 5 , wherein the interpolated control parameter information comprises values of the component stiffness parameter that transition from high stiffness to low stiffness over multiple periods of a real-time control cycle of the robot.

7 . The method of claim 5 , wherein the component stiffness parameter represents joint stiffness.

8 . The method of claim 1 , wherein the control parameter is at least one of (i) a damping value, (ii) feedback gain, or (iii) an interpolable control parameter.

9 . The method of claim 1 , wherein the real-time controller effectuating the robot to perform the transition comprises:
computing, by the real-time controller and based on the trajectory information and the interpolated control parameter information, real-time commands for a low-level controller of the robot to effectuate the low-level controller based on the real-time commands.

10 . The method of claim 2 , wherein computing the interpolated control parameter information further comprises:
updating, by the robot interface subsystem, values of the interpolated control parameter information at a particular frequency.

11 . The method of claim 1 , wherein the real-time controller effectuates real-time control of the robot using a real-time sensor and real-time interpolated control parameter information.

12 . The method of claim 11 , wherein the real-time interpolated control parameter information is computed using data from a non-real-time sensor.

13 . A system comprising:
one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising: receiving, by a robot interface subsystem, a command for a robot to perform a transition from performing a first task to performing a second task different than the first task; computing, by the robot interface subsystem, trajectory information for controlling the robot to execute the transition from performing the first task to performing the second task; computing, by the robot interface subsystem, interpolated control parameter information for the transition based on a first value of a control parameter assigned to the first task and a second value of a control parameter assigned to the second task, wherein the interpolated control parameter information is separate from the trajectory information and controls how the robot will react to external stimuli encountered by the robot when the robot performs the transition between the first task and the second task; and providing, by the robot interface subsystem, the trajectory information and the interpolated control parameter information to a real-time controller to effectuate the robot performing the transition according to the interpolated control parameter information.

14 . The system of claim 13 , wherein computing the interpolated control parameter information comprises:
obtaining, by the robot interface subsystem, a previous value of the control parameter; obtaining, by the robot interface subsystem, an updated value of the control parameter; and generating a control parameter trajectory that assigns a value between the previous value and the updated value of the control parameter to each of multiple points in a time period.

15 . The system of claim 14 , wherein the previous value of the control parameter is a current value of the control parameter.

16 . The system of claim 14 , wherein the multiple points in the time period correspond to real-time control cycles of the robot.

17 . The system of claim 13 , wherein the control parameter is a component stiffness parameter that represents how easily a robot component of the robot is moved by an external stimulus encountered by the robot.

18 . The system of claim 17 , wherein the interpolated control parameter information comprises values of the component stiffness parameter that transition from high stiffness to low stiffness over multiple periods of a real-time control cycle of the robot.

19 . The system of claim 17 , wherein the component stiffness parameter represents joint stiffness.

20 . One or more non-transitory computer storage media encoded with computer program instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:
receiving, by a robot interface subsystem, a command for a robot to perform a transition from performing a first task to performing a second task different than the first task; computing, by the robot interface subsystem, trajectory information for controlling the robot to execute the transition from performing the first task to performing the second task; computing, by the robot interface subsystem, interpolated control parameter information for the transition based on a first value of a control parameter assigned to the first task and a second value of a control parameter assigned to the second task, wherein the interpolated control parameter information is separate from the trajectory information and controls how the robot will react to external stimuli encountered by the robot when the robot performs the transition between the first task and the second task; and providing, by the robot interface subsystem, the trajectory information and the interpolated control paramete

Assignees

• Intrinsic Innovation Llc

Inventors

• Beardsworth Michael
• Kronander Klas Jonas Alfred
• Cassero Sean Alexander
• Kolluri Bala Venkata Sai Ravi Krishna

Classifications

• B25J9/163 Primary

  learning, adaptive, model based, rule based expert control · CPC title

• B25J9/1664

  characterised by motion, path, trajectory planning · CPC title

• G05B2219/39338

  Impedance control, also mechanical · CPC title

• G05B2219/34083

  Interpolation general · CPC title

• G05B2219/41021

  Variable gain · CPC title