Avoidance of moving obstacles through behavior fusion and motion prediction

We propose a novel approach of fusing the fuzzy control actions of the obstacle avoidance, goal seeking and steering behaviors, in which the steering behavior is derived from motion prediction. As such, the navigator is more capable to steer clear of the zone of high collision probability. Through simulation, it has been confirmed that the navigator having this steering behavior can tackle multiple moving obstacles successfully at much higher speed compared with those without. Furthermore, it does not require any a priori knowledge of the obstacle motion