Robot Spatial Perception by Stereoscopic Vision and 3D Evidence Grids - Robotics Institute Carnegie Mellon University

Robot Spatial Perception by Stereoscopic Vision and 3D Evidence Grids

Hans Moravec
Tech. Report, CMU-RI-TR-96-34, Robotics Institute, Carnegie Mellon University, September, 1996

Abstract

Very encouraging results have been obtained from a new program that derives a dense three-dimensional evidence grid representation of a robot's surroundings from wide-angle stereoscopic images. The program adds several spatial rays of evidence of evidence to a grid for each of about 2,500 logical image features chosen per stereo pair. It was used to construct a 256x256x64 grid, representing 6 by 6 by 2 meters, from a hand-collected test set of twenty stereo image pairs of an office scene. Fifty nine stereo pairs of an 8 by 8 meter laboratory were also processed. The positive (probably occupied) cells of the grids, viewed in perspective, resemble dollhouse scenes. Details as small as the curvature of chair armrests are discernible. The processing time, on a 100 MIPS Sparc 20, is less than five seconds per stereo pair, and total memory is under 16 megabytes. The results seem abundantly adequate for very reliable navigation of freely roaming mobile robots, and plausibly adequate for shape identification of objects bigger than 10 centimeters. The program is a first proof of concept, and awaits optimization, enhancements, extensions, and applications.

BibTeX

@techreport{Moravec-1996-14212,
author = {Hans Moravec},
title = {Robot Spatial Perception by Stereoscopic Vision and 3D Evidence Grids},
year = {1996},
month = {September},
institute = {Carnegie Mellon University},
address = {Pittsburgh, PA},
number = {CMU-RI-TR-96-34},
}