ACTIVE DYNAMIC STEREO VISION (VOL 17, PG 868, 1995)

Visual navigation is a challenging issue in automated robot control, I n many robot applications, like object manipulation in hazardous envir onments or autonomous locomotion, it is necessary to automatically det ect and avoid obstacles while planning a safe trajectory. In this cont ext the detection of corridors of free space along the robot trajector y is a very important capability which requires nontrivial visual proc essing, In most cases it is possible to take advantage of the active c ontrol of the cameras. In this paper we propose a cooperative schema i n which motion and stereo vision are used to infer scene structure and determine free space areas, Binocular disparity, computed on several stereo images over time, is combined with optical flow from the same s equence to obtain a relative-depth map of the scene. Both the time-to- impact and depth scaled by the distance of the camera from the fixatio n point in space are considered as good, relative measurements which a re based on the viewer, but centered on the environment. The need for calibrated parameters is considerably reduced by using an active contr ol strategy. The cameras track a point in space independently of the r obot motion and the full rotation of the head, which includes the unkn own robot motion, is derived from binocular image data. The feasibilit y of the approach in real robotic applications is demonstrated by seve ral experiments performed on real image data acquired from an autonomo us vehicle and a prototype camera head.