Fuzzy Logic based Active Map Learning for Autonomous Robot

The paper proposes a fast map learning approach for real-time map building and active exploration in unknown indoor environments. This approach includes a map model, a map update method, an exploration method, and a map postprocessing method. The map adopts a grid-based representation and uses frequency value to measure the confidence that a cell is occupied by an obstacle. The exploration method is implemented by coordinating two novel behaviors: path-exploring behavior and environment-detection behavior. Fuzzy logic is used to implement the behavior design and coordination. The fast map update and path planning (i.e. the exploration method) make our approach a candidate for real-time implementation on mobile robots. The results are demonstrated by simulated experiments based on a Pioneer robot with eight forward sonar sensors.