A Multi-modal Behavior Planning Framework for Guide Robot

In this paper we propose a multi-modal behavior planning framework for guide robots, to better assist the visually impaired to select safe paths in a cluttered space. Most prior robotic guiding systems only use physical contact, limiting their ability from operating in narrow and cluttered environments. Our multi-modal behavior planning framework is based on the Social Force Model(SFM) and the Monte Carlo Tree Search(MCTS). The proposed framework extracts robot behaviors' impact as the social force on human and predicts human motion, then employs the MCTS to search best multi-modal behavior policy. The proposed approach is deployed on a humanoid robot to guide a blind-folded person to safely travel in a complicated space.