Visually stimulated motor control for a robot with a pair of LGMD visual neural networks

Yue, Shigang and Rind, Claire (2012) Visually stimulated motor control for a robot with a pair of LGMD visual neural networks. International Journal of Advanced Mechatronic Systems, 4 (5/6). pp. 237-247. ISSN 1756-8412

Full content URL: http://dx.doi.org/10.1504/IJAMECHS.2012.052219

Documents
IJAMECHS0405-0605 YUE.pdf
[img] PDF
IJAMECHS0405-0605 YUE.pdf - Whole Document
Restricted to Repository staff only

542kB
Item Type:Article
Item Status:Live Archive

Abstract

In this paper, we proposed a visually stimulated motor control (VSMC) system
for autonomous navigation of mobile robots. Inspired from a locusts’ motion sensitive
interneuron – lobula giant movement detector (LGMD), the presented VSMC system enables a
robot exploring local paths or interacting with dynamic objects effectively using visual input
only. The VSMC consists of a pair of LGMD visual neural networks and a simple motor
command generator. Each LGMD processes images covering part of the wide field of view and
extracts relevant visual cues. The outputs from the two LGMDs are compared and interpreted
into executable motor commands directly. These motor commands are then executed by the
robot’s wheel control system in real-time to generate corresponded motion adjustment
accordingly. Our experiments showed that this bio-inspired VSMC system worked well in
different scenarios.

Additional Information:Special Issue on Advanced Application of Modelling, Identification and Control
Keywords:visual neural networks, lobula giant movement detector, LGMD, locusts, mobile robot, visual stimulated motor control
Subjects:G Mathematical and Computer Sciences > G730 Neural Computing
Divisions:College of Science > School of Computer Science
ID Code:9309
Deposited On:03 May 2013 07:51

Repository Staff Only: item control page