The lure of using motion vision as a fundamental element in the perception of space drives this effort to use flow features as the sole cues for robot mobility. Real-time estimates of image flow and flow divergence provide the robot's sense of space. The robot steers down a conceptual corridor, comparing left and right peripheral flows. Large central flow divergence warns the robot of impending collisions at "dead ends. " When this occurs, the robot turns around and resumes wandering. Behavior is generated by directly using flow-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 rotation. By combining corridorfollowing and dead-end deflection, the robot has wandered 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.

This article examines the problem of a moving robot tracking a moving object with its cameras, without requiring the ability to recognize the target to distinguish it from distracting surroundings. A novel aspect of the approach taken is the use of controlled camera movements to simplify the visual processing necessary to keep the cameras locked on the target. A gaze-holding system implemented on a robot's binocular head demonstrates this approach. Even while the robot is moving, the cameras are able to track an object that rotates and moves in three dimensions.The central idea is that localizing attention in 3-D space makes precategorical visual processing sufficient to hold gaze. Visual fixation can help separate the target object from distracting surroundings. Converged cameras produce a horopter (surface of zero stereo disparity) in the scene. Binocular features with no disparity can be located with a simple filter, showing the object's location in the image. Similarly, an object that is being tracked is imaged near the center of the field of view, so spatially localized processing helps concentrate visual attention on the target. Instead of requiring a way to recognize the target, the system relies on active control of camera movements and binocular fixation segmentation to locate the target.

In binocular systems, vergence is the process of adjusting the angle between the eyes (or cameras) so that both eyes are directed at the same world point. Its utility is most obvious for foveate systems such as the human visual system, but it is a useful strategy for non-foveate binocular robots as well. This paper discusses the vergence problem and outlines a general approach to vergence control, consisting of a control loop driven by an algorithm that estimates the vergence error. As a case study, this approach is used to verge the eyes of the Rochester Robot in real time. Vergence error is estimated with the cepstral disparity filter, The cepstral filter is analyzed, and it is shown in this application to be equivalent to correlation with an adaptive prefilter; carrying this idea to its logical conclusion converts the cepstral filter into phase correlation. The demonstration system uses a PD controller in cascade with the error estimator. An efficient real-time implementation of the error estimator is discussed, and empirical measurements of the performance of both the disparity estimator and the overal1 system are presented.

No abstract