Publications:Vision-based low-level navigation using a feed-forward neural network

From CERES
Jump to: navigation, search

Do not edit this section

Keep all hand-made modifications below

Title Vision-based low-level navigation using a feed-forward neural network
Author Magnus Jonsson and Per-Arne Wiberg and Nicholas Wickström
Year 1997
PublicationType Conference Paper
Journal
HostPublication Proc. International Workshop on Mechatronical Computer Systems for Perception and Action (MCPA'97), Pisa, Italy, Feb. 10-12
DOI
Conference
Diva url http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:239973
Abstract In this paper we propose a simple method for low-level navigation for autonomous mobile robots, employing an artificial neural network. Both corridor following and obstacle avoidance in indoor environments are managed by the same network. Raw grayscale images of size 32 x 23 pixels are processed one at a time by a feed-forward neural network. The output signals from the network directly control the motor control system of the robot. The feed-forward network is trained using the RPROP algorithm. Experiments in both familiar and unfamiliar environments are reported.