Goal-Oriented Behaviour-Based Visual Navigation

Abstract

In this paper we describe a mobile robot system that performs goal-oriented visual navigation using a behaviour-based architecture. The system was constructed as a resulif of our previous research into behaviour-based mobile robot systems. Since the system is implemented using real-time vision it is able to navigate in dynamic and unknown environments. The most important feature of this navigation system is that the mobile robot can learn to resolve conflicts between its own internal behaviours, such as moving to a goal whale avoiding obstacles. Our robot is able to eficiently avoid obstacles while trying to reach a goal. Experimental results of an implementation on a Yamabico mobile robot are presented. vision-guided mobile robots Cheng et al. [3] [4], multiple cooperating robots for cleaning Jung et al. [5] and a soccer playing robot Cheng et al. [SI. In this paper we describe an architecture that ties together the various components that we have developed in our previous systems to achieve our research objectives. This paper begins by reviewing related work in Section 2. An outline of what problems must be addressed is presented. We present solutions to these problems. In Section 3 we describe our experimental setup. Section 4 describes our vision processing scheme. Section 5 describes how our algorithms are implemented. In Section 6 experimental results are provided to verify the correctness of the navigation scheme in unknown dynamic environments. 2 Related Work

DOI: 10.1109/ROBOT.1998.680968

Cite this paper

@inproceedings{Cheng1998GoalOrientedBV, title={Goal-Oriented Behaviour-Based Visual Navigation}, author={Gordon Cheng and Alexander Zelinsky}, booktitle={ICRA}, year={1998} }