Eecient Learning of Variable-resolution Cognitive Maps for Autonomous Indoor Navigation

This paper presents an adaptive method that allows mobile robots to learn cognitive maps of indoor environments incrementally and on-line. Our approach models the environment by means of a variable-resolution partitioning that discretizes the world in perceptually homogeneous regions. The resulting model incorporates both a compact geometrical representation of the environment and a topological map of the spatial relationships between its obstacles-free areas. The eeciency of the learning process is based on the use of local memory-based techniques for partitioning and of active learning techniques for selecting the most appropriate region to be explored next. In addition, a feed-forward neural network interprets sensor readings eeciently. Finally, we present experimental results obtained with two extremely diierent mobile robots, namely a Nomad 200 and a Khepera, which connrm the validity and generality of our approach .