Biber, Peter and Duckett, Tom (2005) Dynamic maps for long-term operation of mobile service robots. In: Robotics: Science and Systems 2005 Massachusetts Institute of Technology, Cambridge, Massachusetts, 8 - 11 June 2005, Cambridge, Massachusetts, USA.

PDF uoa23td02.pdf Restricted to Repository staff only Download (3141Kb)

Abstract

This paper introduces a dynamic map for mobile robots that adapts continuously over time. It resolves the stability plasticity dilemma (the tradeoff between adaptation to new patterns and preservation of old patterns) by representing the environment over multiple time scales simultaneously (five in our experiments). A sample-based representation is proposed, where older memories fade at different rates depending on the time scale. Robust statistics are used to interpret the samples. It is shown that this approach can track both stationary and non-stationary elements of the environment, covering the full spectrum of variations from moving objects to structural changes. The method was evaluated in a five-week experiment in a real dynamic environment. Experimental results show that the resulting map is stable, improves its quality over time and adapts to changes.

Item Type:	Conference or Workshop Item (Paper)
Additional Information:	This paper introduces a dynamic map for mobile robots that adapts continuously over time. It resolves the stability plasticity dilemma (the tradeoff between adaptation to new patterns and preservation of old patterns) by representing the environment over multiple time scales simultaneously (five in our experiments). A sample-based representation is proposed, where older memories fade at different rates depending on the time scale. Robust statistics are used to interpret the samples. It is shown that this approach can track both stationary and non-stationary elements of the environment, covering the full spectrum of variations from moving objects to structural changes. The method was evaluated in a five-week experiment in a real dynamic environment. Experimental results show that the resulting map is stable, improves its quality over time and adapts to changes.
Keywords:	Robotics, mobile robotics, Adaptation, Patterns
Subjects:	H Engineering > H671 Robotics
Divisions:	College of Sciences > Faculty of Science > Lincoln School of Computer Science
Depositing User:	Bev Jones
Date Deposited:	20 Sep 2007
Last Modified:	13 Mar 2013 08:25
URI:	http://eprints.lincoln.ac.uk/id/eprint/1204

Actions (login required)

View Item