Index
Logic
Uncertainty
Robotics
Recent

Steps Toward Detecting and Recovering from Perceptual Failures

M. Broxvall, L. Karlsson and A. Saffiotti

Abstract
An important requirement for autonomous systems is the ability to detect and recover from exceptional situations such as failures in observations. In this paper we investigate how traditional AI planning techniques can be used to reason about observations and to recover from these situations. In this first step we concentrate on failures in perceptual anchoring. We illustrate our approach by showing experiments run on a mobile robot equipped with a color camera.
Citation
M. Broxvall, L. Karlsson and A. Saffiotti. Steps Toward Detecting and Recovering from Perceptual Failures. Proc. of the 8th Int. Conf. on Intelligent Autonomous Systems (IAS) 793-800. Amsterdam, NL, 2004.
BibTeX entry
Contact
Email Mathias Broxvall
Email Lars Karlsson
Email Alessandro Saffiotti
Availability (©)
PS PostScript file (2.2 Mb)
Compressed PostScript file (943 Kb)
PDF PDF file (712 Kb)
 
Page hosted by  AASS Designed and maintained by Alessandro Saffiotti