No Cover Image

Journal article 273 views 71 downloads

Deep Recurrent Neural Networks Based Obstacle Avoidance Control for Redundant Manipulators

Zhihao Xu, Xuefeng Zhou, Shuai Li Orcid Logo

Frontiers in Neurorobotics, Volume: 13

Swansea University Author: Shuai Li Orcid Logo

  • xu2019(2).pdf

    PDF | Version of Record

    Released under the terms of a Creative Commons Attribution License (CC-BY).

    Download (1.17MB)

Abstract

Obstacle avoidance is an important subject in the control of robot manipulators, but is remains challenging for robots with redundant degrees of freedom, especially when there exist complex physical constraints. In this paper, we propose a novel controller based on deep recurrent neural networks. By...

Full description

Published in: Frontiers in Neurorobotics
ISSN: 1662-5218 1662-5218
Published: 2019
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa52000
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: Obstacle avoidance is an important subject in the control of robot manipulators, but is remains challenging for robots with redundant degrees of freedom, especially when there exist complex physical constraints. In this paper, we propose a novel controller based on deep recurrent neural networks. By abstracting robots and obstacles into critical point sets respectively, the distance between the robot and obstacles can be described in a simpler way, then the obstacle avoidance strategy is established in form of inequality constraints by general class-K functions. Using minimal-velocity-norm (MVN) scheme, the control problem is formulated as a quadratic-programming case under multiple constraints. Then a deep recurrent neural network considering system models is established to solve the QP problem online. Theoretical conduction and numerical simulations show that the controller is capable of avoiding static or dynamic obstacles, while tracking the predefined trajectories under physical constraints.
Keywords: recurrent neural network, redundant manipulator, obstacle avoidance, zeroing neural network, motion plan