A Navigation and Obstacle Avoidance Algorithm for Mobile Robots Operating in Unknown, Maze-Type Environments

This paper describes two complementary algorithms developed for mobile robots operating within unknown, maze-type environments. The first is an environmental mapping and navigation algorithm which ensures complete coverage of a maze with apriori unknown wall locations, and the second a stochastic learning automaton approach for general obstacle avoidance within the maze. The environmental mapping and navigation algorithm employs a modified, wall following type scheme for exploring the maze and a variation of a flood-fill strategy for path planning to ensure complete coverage of the maze. A stochastic learning automaton provides a means of avoiding collisions with unstructured obstacles in the maze based upon a reward and penalty system which is used to adapt action probabilities. Both approaches are implemented within the UMBRA modular simulation and visualization framework in order to validate the algorithms prior to implementation in a RTLinux-based hardware platform. Index Terms – mobile robot, navigation, obstacle avoidance, path planning.