Hidden Markov model for dynamic obstacle avoidance of mobile robot navigation

Abstract

Models and control strategies for dynamic obstacle avoidance in visual guidance of mobile robots are presented. Characteristics that distinguish the visual computation and motion control requirements in dynamic environments from that in static environments are discussed. Objectives of the vision and motion planning are formulated, such as finding a collision-free trajectory that takes account of any possible motions of obstacles in the local environments. Such a trajectory should be consistent with a global goal or plan of the motion and the robot should move at as high a speed as possible, subject to its kinematic constraints. A stochastic motion-control algorithm based on a hidden Markov model is developed. Obstacle motion prediction applies a probabilistic evaluation scheme. Motion planning of the robot implements a trajectory-guided parallel-search strategy in accordance with the obstacle motion prediction models. The approach simplifies the control process of robot motion. >