ONLINE MANIPULATION PLANNING FOR 2 ROBOT ARMS IN A DYNAMIC ENVIRONMENT

In a constantly changing and partially unpredictable environment, robo t-motion planning mast be art-line. The planner receives a continuous flow of information about occurring events and generates new plans whi le previously planned motions are being executed. This article describ es an on-line planner for two cooperating arms whose task is to grab p arts of various types on a conveyor belt and transfer them to their re spective goals, while avoiding collisions with obstacles. Parts arrive on the belt in random order, at any time. Both goals and obstacles ma y be dynamically changed. This scenario is typical of manufacturing ce lls serving machine tools, assembling products, or packaging objects. The proposed approach breaks the overall planning problem into subprob lems, each involving a low-dimensional configuration or configuration x time space, and orchestrates very fast primitives solving these subp roblems. The resulting planner has been implemented and extensively te sted in a simulated environment, as well as with a real dual-arm syste m. Its competitiveness has been evaluated against an oracle making (al most) the best decision at any one time; the results shaw that the pla nner compares extremely well.