A real time controller for human-machine cooperative telerobotics

In this paper, a methodology to integrate sensor and model based computer assistance into a class of human controlled teleoperator systems called human machine cooperative telerobotics (HMCTR) is presented. In this strategy, the human operator is retained at all phases of the operation, and is assisted, but never superseded, with sensor and model information. This strategy is presented along with the task planner that connects the system to the results of the task space scene modeling. A controller using this strategy in its three control modes: pure teleoperation, autonomous operation, and teleoperation with assistance, was built for use with a Titan II/spl trade/ manipulator that is often used in remote operations at radioactive sites. An experiment was performed that demonstrates the shorter execution times using HMCTR over standard teleoperation procedures are achievable.