Real-Time Single-Workstation Obstacle Avoidance Using Only Wide-Field Flow Divergence

Ted Camus
Sensar, Inc.
Moorestown, NJ 08057

David Coombs
National Institute of Standards
Intelligent Systems Division

Martin Herman
National Institute of Standards
Information Accessand User Interfaces Division

Tsai-Hong Hong
National Institute of Standards
Intelligent Systems Division



Abstract

This paper describes a real-time robot vision system that uses only the divergence of the optical flow field for both steering control and collision detection. The robot has wandered about the lab at 20 cm/s for as long as 26 min. without collision. The entire system is implemented on a single ordinary UNIX workstation. Dense optical flow data are calculated in real time across the entire wide-angle image. The divergence of this optical flow field is calculated everywhere and used to control steering and collision-avoidance behavior. Divergence alone has proven sufficient for steering past objects and detecting imminent collision. The major contribution is the demonstration of a simple, robust, minimal system that uses flow-derived measures to control steering and speed to avoid collision in real time for extended periods.

Keywords: real-time, robotic vision, obstacle avoidance, optical flow, flow divergence, time-to-contact, low-level perception, RCS