Vision for autonomous mobile robot guidance

Abstract

In order for mobile robots to integrate into human active spaces and perform useful tasks, they must be capable of discriminating between traversable surfaces and obstacle regions in their surrounding environment. This research has focused on the development of a vision system for a mobile robot to autonomously guide itself in an previously unknown environment with a relatively low-quality monocular camera. Robots that make use of vision may be able to extract long-range information and high-level semantics from the environment and direct their movement accordingly, affording more intelligent robot guidance.