Human-Supervised Semi-Autonomous Mobile Manipulators for Safely and\n Efficiently Executing Machine Tending Tasks

Abstract

Mobile manipulators can be used for machine tending and material handling\ntasks in small volume manufacturing applications. These applications usually\nhave semi-structured work environment. The use of a fully autonomous mobile\nmanipulator for such applications can be risky, as an inaccurate model of the\nworkspace may result in damage to expensive equipment. On the other hand, the\nuse of a fully teleoperated mobile manipulator may require a significant amount\nof operator time. In this paper, a semi-autonomous mobile manipulator is\ndeveloped for safely and efficiently carrying out machine tending tasks under\nhuman supervision. The robot is capable of generating motion plans from the\nhigh-level task description and presenting simulation results to the human for\napproval. The human operator can authorize the robot to execute the\nautomatically generated plan or provide additional input to the planner to\nrefine the plan. If the level of uncertainty in some parts of the workspace\nmodel is high, then the human can decide to perform teleoperation to safely\nexecute the task. Our preliminary user trials show that non-expert operators\ncan quickly learn to use the system and perform machine tending tasks.\n