Patent · US Active

Constraint adaptor for reinforcement learning control

US11676064B2 · kind B2 · utility

0Cited by
0References
14Claims
0Family size

Assignee

Inventors

Key dates

Filing dateAug 16, 2019
Grant dateJun 13, 2023
Priority date
Expiry dateNov 23, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG05B13/048
  • WIPO fieldControl
  • WIPO sectorInstruments

Abstract

A system for controlling an operation of a machine subject to state constraints in continuous state space of the machine and subject to control input constraints in continuous control input space of the machine is provided. The apparatus includes an input interface to accept data indicative of a state of the machine, a memory configured to store an optimization problem for computing the safety margin of a state and action pair satisfying the state constraints and a control policy mapping the state of the machine within a control invariant set (CIS) to a control input satisfying the control input constraints, and a processor configured to iteratively perform a reinforcement learning (RL) algorithm to jointly control the machine and update the control policy.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.