Assisted Teleoperation Strategies for Aggressively Controlling a Robot Arm with 2D Input

This paper studies assisted teleoperation techniques for controlling a 6DOF robot arm using click-and-drag input from a computer mouse. Experiments were conducted to investigate how task performance and user preferences are affected by low-level motion control strategies, which must deal with collision avoidance, dynamics constraints, and erroneous input. Five strategies were implemented and compared. As baseline strategies we study direct joint control and Cartesian positioning via inverse kinematics. We also implemented three obstacle avoidance strategies, including a predictive safety filter, a reactive potential field, and a real-time sample-based motion planner. Blind experimental trials assigned 22 novice subjects to five subgroups corresponding to each strategy and asked them to control the arm in simulation on a variety of reaching tasks in cluttered environments. Unsurprisingly, the obstacle avoidance strategies achieve major safety improvements, although subjects felt noticeably less in control of the robot than those using the baseline methods. The motion planning strategy shows the most promise; it completed tasks twice as fast as any other method and received high ratings for perceived safety, cooperativeness, and overall satisfaction.