System identification of industrial robot dynamics for safety-critical applications
AssigneeVeo Robotics, Inc.
InventorsScott Denenberg, Brad C. Mello, Matthew Galligan, Clara Vu, Patrick Sobalvarro, Marek Wartenberg, Alberto Moel
Life of this patent
Estimating the term…
Abstract
Embodiments of the present invention provide automated robotic system identification and stopping time and distance estimation, significantly improving on existing ad-hoc methods of robotic system identification. Systems and methods in accordance herewith can be used by end users, system integrators, and the robot manufacturers to estimate the dynamic parameters of a robot on an application-by-application basis.
Claims18
A system for generating a system identification for a robotic system, the system comprising:
- a. a processor;
- b. a memory including instructions executable by the processor for providing:
- 1) an excitation-trajectory module for generating a set of robot motions and causing the robotic system to physically execute the set of robot motions;
- 2) a monitoring module for monitoring the physical execution of the robot motions by the robotic system;
- and
- 3) a parameter solver, responsive to the excitation-trajectory module, for numerically estimating dynamic model parameters for the robot based on the monitored physical execution;
- and
- c. a controller for controlling the robotic system in accordance with a safety constraint by operating the robotic system based on the estimated dynamic model parameters.
A method of computationally generating a system identification for a robotic system, the method comprising the steps of:
- causing the robotic system to physically execute a set of robot motions;
- monitoring the physical execution of the robot motions by the robotic system;
- based on the monitored physical execution, numerically estimating dynamic model parameters for the robotic system;
- and
- enforcing a safety constraint by operating the robotic system in accordance with a robot model based on the estimated dynamic model parameters.
Dependencies are inferred from the claim text.