Sensor-based probabilistic roadmaps: experiments with an eye-in-hand system

We present a real implemented eye-in-hand test-bed system for sensor-based collision-free motion planning for articulated robot arms. The system consi sts of a PUMA 560 with a triangulation-based area-scan laser range finder ( the eye) mounted on its wrist. The framework for our planning approach is i nspired by recent motion planning research for the classical model-based ca se (known environment) and incrementally builds a roadmap that represents t he connectivity of the free configuration space, as the robot senses the ph ysical environment. We present some experimental results with our sensor-ba sed planner running on this real test-bed. The robot is started in complete ly unknown and cluttered environments. Typically, the planner is able to re ach (planning as it senses) the goal configuration in about 7-25 scans (dep ending on the scene complexity), while avoiding collisions with the obstacl es throughout.