Local path planning: a brute force approach

The issues involved in providing a generic and domain-independent local planning module for the mobile robot called TURNIP (Turing's navigation and image processing system) are discussed, focusing on the role of local planning as a prerequisite to modularity and autonomy. The problem of obstacle avoidance as a low-level, nonintellectual task that should operate in complex, noisy, dynamic, and 3-D domains is considered. Two algorithms are presented, each generating qualitatively different solutions. The first generates the shortest path between two locations; the second generates the clearest path between two locations. Both are based on the distance transform.<<ETX>>