Excerpt from Real-Time Obstacle Avoidance Using Central Flow Divergence and Peripheral Flow
The lure of using motion vision as a fundamental element in the perception of space drives this ejfort to use ?ow features as the sole cues for robot mobility. Real-time estimates of image flow and ?ow divergence provide the robot's sense of space. The robot steers down a conceptual corridor; comparing left and right peripheral ?ows. Large central ?ow divergence warns the robot of impending col lisions at dead ends. When this occurs, the robot turns around and resumes wandering. Behavior is generated by directly using ?ow-based information in the 2-d image sequence; no 3-d reconstruction is attempted. Active mechanical gaze stabilization simplifies the visual interpretation problems by reducing camera rota tion. By combining corridor following and dead-end de?ection, the robot has wan dered around the lab at 30 cm/s for as long as 20 minutes without collision. The ability to support this behavior in real-time with current equipment promises expanded capabilities as computational power increases in the future.