Obstacle Avoidance Via Depth From Focus

Abstract

A critical challenge in the creation of autonomous mobile robots is the reliable detection of moving and static obstacles. In this paper, we present a passive vision system that recovers coarse depth information reliably and e ciently. This system is based on the concept of depth from focus, and robustly locates static and moving obstacles as well as stairs and dropo s with adequate accuracy for navigation. We describe an implementation of this vision system on a mobile robot as well as real-world experiments both indoors and outdoors. These experiments have involved several hours of continuous and fully autonomous operation in crowded, natural settings. 1