Coping with uncertainty in control and planning for a mobile robot

This paper describes a decision theoretic approach to real-time obstacle avoidance and path planning for a mobile robot. The mobile robot navigates in a semistructured environment in which unexpected obstacles may appear at random locations. Twelve sonar sensors are currently used to report the presence and location of the obstacles. To handle the uncertainty of an obstacle’s appearance, we adopt a Bayesian approach by assuming a prior distribution for the presence of unknown obstacles. The distribution is changed dynamically according to the information accumulated by sensors. When we search for an optimal path using Dynamic Programming, we take the probability into account in making a decision. Based on prior information and sensor data, we show that the proposed method allows our mobile robot to avoid unexpected obstacles and finds an optimal path to the goal in real time.