Synergistic human-robot shared control via human goal estimation

In this paper, we propose and implement a synergistic human-robot collaboration framework, where the robotic system estimates the intent or goal of the human operator while being controlled by the human in real-time. Having an estimate of the goal of the human operator, the system augments the human control signals by its own autonomous control output based on the goal estimate. Consequently, the net control command that drives the robot becomes a mixture of human and robot commands. The motivation for such a collaborative system is to obtain an improved task execution to surpass the performance levels that each party could achieve in solo. This is possible if the developed system can take advantage of the individual skills so as to cover the weakness of the other party. To test and validate the proposed system we realized the framework by using the `ball balancing task' where an anthropomorphic robot arm was required to bring a ball on a tray attached to its end effector to a desired position. Task execution performance was quantified with completion time and positional accuracy. To test the validity of the framework, experiments were conducted in three conditions: full autonomous control, human-in-the-loop control, and shared control. Full autonomous control did not require any human subjects; whereas for the latter two conditions, 10 subjects for each condition were employed to measure task performance of naive solo operators and naive human-robot partners. The performance results indicate that the task can be completed more effectively by the human-robot system compared to human alone or autonomous robot execution in different performance measures.