A Model-Based Recurrent Neural Network with Randomness for Efficient Control with Applications

Yangming Li, Shuai Li, Blake Hannaford

Research output: Journal article publicationJournal articleAcademic researchpeer-review

17 Citations (Scopus)

Abstract

Recently, recurrent neural network (RNN) control schemes for redundant manipulators have been extensively studied. These control schemes demonstrate superior computational efficiency, control precision, and control robustness. However, they lack planning completeness. This paper explains why RNN control schemes suffer from the problem. Based on the analysis, this work presents a new random RNN control scheme, which 1) introduces randomness into RNN to address the planning completeness problem, 2) improves control precision with a new optimization target, and 3) improves planning efficiency through learning from exploration. Theoretical analyses are used to prove the global stability, the planning completeness, and the computational complexity of the proposed method. Software simulation is provided to demonstrate the improved robustness against noise, the planning completeness and the improved planning efficiency of the proposed method over benchmark RNN control schemes. Real-world experiments are presented to demonstrate the application of the proposed method.

Original languageEnglish
Article number8458433
Pages (from-to)2054-2063
Number of pages10
JournalIEEE Transactions on Industrial Informatics
Volume15
Issue number4
DOIs
Publication statusPublished - 1 Apr 2019

Keywords

  • Motion planning
  • random neural networks
  • recurrent neural networks
  • redundant manipulator
  • robot

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Information Systems
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this