Collecting Trash: A Test of Purposive Vision

The purposive approach to computer vision has been much discussed in recent years, but there have been few tests of the viability of the paradigm in a working vision system. We have tested the approach in the context of vision for a mobile robot performing tasks in a typical, unaltered o ce environment. In particular, we examine the approach in the context of a trash collection task; the task that was the subject of the 1994 AAAI Robot Competition. Our experience demonstrates that the approach is viable for solving such a task, and we show how our design for the visual system takes advantage of tight integration between the perception and action systems. In particular, we demonstrate that because of the constraints inherent in the task, it is possible to e ciently perform a search over the scene and over viewpoint for the object of interest. We address particular concerns with the purposive approach, such as how purposive systems can be adapted to new situations.