Self-Organizing Mapping of Robotic Environments Based on Neural Networks

An important aspect in robotics is mapping environments, it means know free space configuration of the robot and establish landmarks. It enables the robot to calculate its position in the environment. In this context, this paper proposes a method for mapping generic environments (structured or not) based on topological maps (SOM and Growing Cell Structures), which uses self-organizing networks. The results obtained on different dynamic and ambiguous environment demonstrate both generalization and compactness.