Experimental Analysis of Sample-Based Maps for Long-Term SLAM

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 shortand long-term memories over time, and further demonstrating the robustness of the approach.