Experimental analysis of sample-based maps for long-term SLAM

Biber, Peter and Duckett, Tom (2009) Experimental analysis of sample-based maps for long-term SLAM. International Journal of Robotics Research, 28 (1). pp. 20-33. ISSN 0278-3649

Documents
Experimental analysis of sample-based maps for long-term SLAM
Journal article in Internation Journal of Robotics Research
[img]
[Download]
[img]
Preview
PDF
Biber-Duckett-IJRR-2009.pdf

999kB

Official URL: http://dx.doi.org/10.1177/0278364908096286

Abstract

This paper presents a system for long-term SLAM (simultaneous localization and mapping) by mobile service robots and its experimental evaluation in a real dynamic environment. To deal with the stability-plasticity dilemma (the trade-off between adaptation to new patterns and preservation of old patterns), the environment is represented at multiple timescales simultaneously (5 in our experiments). A sample-based representation is
proposed, where older memories fade at different rates depending on the timescale, and robust statistics are used to interpret the samples. The dynamics of this representation are analysed in a five week experiment, measuring the relative influence of short- and long-term memories over time, and further demonstrating the robustness of the approach.

Item Type:Article
Keywords:mobile robotics
Subjects:G Mathematical and Computer Sciences > G700 Artificial Intelligence
Divisions:College of Science > School of Computer Science
ID Code:2095
Deposited By: Tom Duckett
Deposited On:16 Dec 2009 09:59
Last Modified:04 Dec 2013 16:07

Repository Staff Only: item control page