HUMAN-MACHINE COLLABORATION IN ROBOTICS - INTEGRATING VIRTUAL TOOLS WITH A COLLISION-AVOIDANCE CONCEPT USING CONGLOMERATES OF SPHERES

This paper describes how virtual tools that represent real robot end-e ffecters are used in conjunction with a generalized conglomerate-of-sp heres approach to collision avoidance in such a way that telerobotic t rajectory planning can be accomplished using simple gesture phrases su ch as 'put that there while avoiding that'. In this concept, an operat or (or set of collaborators) need not train for cumbersome telemanipul ation on several multiple-link robots, nor do robots need a priori kno wledge of operator intent and exhaustive algorithms for evaluating eve ry aspect of a detailed environment model. The human does what humans do best during task specification, while the robot does what machines do best during trajectory planning and execution. Four telerobotic sta ges were implemented to demonstrate this strategic supervision concept that will facilitate collaborative control between humans and machine s. In the first stage, virtual reality tools are selected from a 'tool box' by the operator(s) and then these virtual tools are computational ly interwoven into the live video scene with depth correlation. Each v irtual tool is a graphic representation of a robot end-effector (gripp er, cutter, or other robot tool) that carries tool-use attributes on h ow to perform a task. An operator uses an instrumented glove to virtua lly retrieve the disembodied tool, in the shared scene, and place it n ear objects and obstacles while giving key-point gesture directives, s uch as 'cut there while avoiding that'. Collaborators on a network may alter the plan by changing tools or tool positioning to achieve prefe rred results from their own perspectives. When parties agree, from whe rever they reside geographically, the robot(s) create and execute appr opriate trajectories suitable to their own particular Links and joints . Stage two generates standard joint-interpolated trajectories, and la ter creates potential field trajectories if necessary. Stage three tes ts for collisions with obstacles identified by the operator and modele d as conglomerates of spheres. Stage four involves automatic grasping (or cutting etc.) once the robot camera acquires a close-up view of th e object during approach. In this paper particular emphasis is placed on the conglomerate-of-spheres approach to collision detection as inte grated with the virtual tools concept for a Puma 560 robot by the Virt ual Tools and Robotics Group in the Computer Integrated Manufacturing Laboratory at The Pennsylvania State University (Penn State).