Paper Info
Title
A Robot Vision System for Collision Avoidance Using a Bio-inspired Algorithm
Abstract
Locusts have a remarkable ability of visual guidance that includes collision avoidance exploiting the limited nervous networks in their small cephalon. We have designed and tested a real-time intelligent visual system for collision avoidance inspired by the visual nervous system of a locust. The system was implemented with mixed analog-digital integrated circuits consisting of an analog resistive network and field-programmable gate array (FPGA) circuits so as to take advantage of the real-time analog computation and programmable digital processing. The response properties of the system were examined by using simulated movie images, and the system was tested also in real-world situations by loading it on a motorized miniature car. The system was confirmed to respond selectively to colliding objects even in complex real-world situations.
Year
DOI
Venue
2007
10.1007/978-3-540-69162-4_12
ICONIP
Keywords
Field
DocType
real-time intelligent visual system,visual guidance,collision avoidance,limited nervous network,visual nervous system,real-time analog computation,real-world situation,bio-inspired algorithm,robot vision system,colliding object,analog resistive network,complex real-world situation,real time,nervous system,visual system,field programmable gate array
Computer vision,Computer science,Field-programmable gate array,Collision,CMOS sensor,Gate array,Artificial intelligence,Robot vision systems,Electronic circuit,Integrated circuit,Computation
Conference
Volume
ISSN
Citations 
4985
0302-9743
2
PageRank 
References 
Authors
0.48
4
2
Name
Order
Citations
PageRank
Hirotsugu Okuno1265.15
Tetsuya Yagi214027.73