DocumentCode :
2551527
Title :
A neural model for sonar-based navigation in obstacle fields
Author :
Horiuchi, Timothy K.
Author_Institution :
Dept. of Electr. & Comput. Eng., Maryland Univ., College Park, MD
fYear :
2006
fDate :
21-24 May 2006
Abstract :
The rapid control of sonar-guided vehicles through obstacle fields has been a goal of robotics for decades. How sensory data is represented strongly affects how obstacles and goal information can be combined to select a direction of travel. While typical approaches combine attractive and repulsive effects to directly determine steering, we are investigating an algorithm that evaluates multiple directions simultaneously followed by a winner-take-all (WTA) function which then guides steering. In this paper we describe a neuromorphic VLSI implementation of this algorithm using the inherent echo delay to create a range-dependent gain in a ´race-to-first-spike´ neural WTA circuit. The chip was fabricated in a commercially-available 0.5 mum CMOS process and in this paper we present preliminary test results
Keywords :
CMOS digital integrated circuits; VLSI; collision avoidance; mobile robots; navigation; neural nets; sonar detection; 0.5 micron; CMOS process; echo delay; goal information; neural model; neuromorphic VLSI implementation; obstacle fields; robotics; sensory data; sonar-based navigation; sonar-guided vehicles; winner-take-all function; Automotive engineering; Cognitive robotics; Cognitive science; Control systems; Educational institutions; Neurons; Neuroscience; Robot sensing systems; Sonar navigation; Vehicles; bat echolocation; multiple obstacles; robot navigation; spike-timing; step inhibition; winner-take-all;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Circuits and Systems, 2006. ISCAS 2006. Proceedings. 2006 IEEE International Symposium on
Conference_Location :
Island of Kos
Print_ISBN :
0-7803-9389-9
Type :
conf
DOI :
10.1109/ISCAS.2006.1693640
Filename :
1693640
Link To Document :
بازگشت