Using Partial Sensor Information to Orient Parts

Submitted to the International Journal of Robotics Research, December 1997

Srinivas Akella and Matthew T. Mason

Abstract

Parts orienting, the process of bringing parts in initially unknown orientations to a goal orientation, is an important aspect of automated assembly. The most common industrial orienting systems are vibratory bowl feeders, which use the geometry and mass properties of parts to orient them. Bowl feeders rely on a sequence of mechanical operations, and typically do not use sensors. In this paper, we describe the use of partial information sensors along with a sequence of pushing operations to eliminate uncertainty in the orientations of parts. We characterize the shorter execution lengths of sensor-based plans and the ability of a single plan to orient and recognize multiple part shapes. Further, we show that differences in part shape do not always lead to differences in part behavior under linear normal pushes. We have implemented several planners and demonstrated generated plans in experiments.