Loading [MathJax]/extensions/MathZoom.js
A Self-Organizing Neural Model for Fault-Tolerant Control of Redundant Robots | IEEE Conference Publication | IEEE Xplore

A Self-Organizing Neural Model for Fault-Tolerant Control of Redundant Robots


Abstract:

This paper describes a self-organizing neural model that is capable of controlling the kinematics of robots with redundant degrees of freedom. The self-organized learning...Show More

Abstract:

This paper describes a self-organizing neural model that is capable of controlling the kinematics of robots with redundant degrees of freedom. The self-organized learning process is based on action perception cycles where the robot is perturbed minimally about a given joint configuration and learns to map these perturbations to changes in sensor readings corresponding to these minimal perturbations. This motor babbling phase provides self-generated movement commands that activate correlated sensory, spatial and motor information that are used to learn an internal coordinate transformation between sensory and motor systems. This idea was tested on two different tasks: reaching targets in 2-D space with a three degree of freedom robot and saccading to targets in 3-D with a twelve degree of freedom head-neck-eye system. Computer simulations show that the resulting controller is highly fault-tolerant and robust to previously unseen disturbances much like biological systems.
Date of Conference: 12-17 August 2007
Date Added to IEEE Xplore: 29 October 2007
ISBN Information:

ISSN Information:

Conference Location: Orlando, FL, USA

I. Introduction

This paper describes a self-organized method for control of robots with redundant degrees of freedom based on a neural model. Unlike prior work in the area of robotics [[1]–[2]],this model draws its inspiration from the analysis of how visual, spatial and motor representations are formed and combined for the control of goal-oriented behaviors in humans [3]–[11]. We argue that it is not coincidental but a deliberate evolutionary adaptation of nature to have redundancy in the design of motor systems wherein goals can be reached using multiple motor means. This phenomenon known as motor equivalence [3] addresses how animals and humans can correctly choose among the alternative means that are available to perform a given goal in different situations.

References

References is not available for this document.