THE DEICTICALLY CONTROLLED WHEELCHAIR

We are developing a 'gopher' wheelchair robot which can be used as an aid for disabled individuals. The robot uses a shared control architec ture where the robot and the human user share the responsibility for a retrieve and replace task. The medium of the interactive interface be tween the robot and the user is stereo video images. In addition, the stereo cameras serve as a primary sensor to detect and track targets w hich guide the robot's low-level servoing. The person is responsible f or selecting objects or targets in the environment and then instructin g the robot how to move relative to these targets. This paper first de scribes the hardware and the control interface of this human-robot sys tem. The description here focuses on the system's video algorithms for tracking and evaluating targets. The system builds a binary shape mod el for each target selected by the user. It also forms a color mapping used to highlight the target in the image. This mapping is used on su bsequent images to create a binary image which can be quickly matched with the target's shape model. We have tested this tracking algorithm on videotaped image sequences and on some runs with our wheelchair mob ile robot. Our initial results show that this algorithm is reasonably robust for various types of edge and corner targets necessary for navi gation. (C) 1998 Elsevier Science B.V.