Bootstrap Learning for Place Recognition

We present a method whereby a robot can learn to recognize places with high accuracy, in spite of perceptual aliasing (different places appear the same) and image variability (the same place appears differently). The first step in learning place recognition restricts attention to distinctive states identified by the map-learning algorithm, and eliminates image variability by unsupervised learning of clusters of similar sensory images. The clusters define views associated with distinctive states, often increasing perceptual aliasing. The second step eliminates perceptual aliasing by building a causal/topological map and using history information gathered during exploration to disambiguate distinctive states. The third step uses the labeled images for supervised learning of direct associations from sensory images to distinctive states. We evaluate the method using a physical mobile robot in two environments, showing high recognition rates in spite of large amounts of perceptual aliasing.

Authors

• Benjamin Kuipers and Patrick Beeson The University of Texas at Austin

Keywords

No keywords are indexed for this paper.