Decision Making for a Mobile Robot Using Potential Function

摘要

We discuss decision making for a behavior-based robot with modules which determining robot action. The subsumption architecture (SA) arranges modules in layers, giving upper-layer module action priority over lower-layer modules. Although implementation is easy, results in many inefficient actions because upper-layer module are used regardless of other modules. We solve this problem by representing actions by Potential Function (PF), in which maximum votes are collected from modules. Using event-driven state transition, the robot decides its action with appropriate sets of modules changed based on the situation. We apply this to navigation tasks in a corridor and show simulation results. When we give a map and path designation to the robot, we use a handwriting map interface. We compare object-oriented design SA and PMF with our proposal and show how inefficient actions are reduced using our proposal.