Ken Naka

Human-Centered Adaptive Mobile Robot Based on On-Line Dialogue and Stochastic Experience Representation

Abstract In this paper, we propose a novel method for personal robots to acquire autonomous behaviors gradually based on interaction between human and robots. In this method, behavior decision models and dialogue control models are integrated using Bayesian Networks. This model can treat interaction experiences using statistical processes, and sureness of decision making is represented by certainty factors. The robots not only decide behavior, but also make suggestions to the user. We investigate the feasibility of this method with a delivery task. We have confirmed that the mobile robot acquires robust obstacle avoidance behavior and personal information against changes of environment through interaction between users.