Learning robotic milling strategies based on passive variable operational space interaction control

Abstract--This paper addresses the problem of robotic cutting a milling task online without user assistance. We develop a during disassembly of products for materials separation and framework for controlling a robot using this strategy that allows recycling. Waste handling applications differ from milling in the stiffness of the robot arm to be modulated over time to best manufacturing processes, as they engender considerable variety satisfy metrics of productivity (e.g. To address this challenge, we propose (e.g. by avoiding force limits), similarly to how a human operator a learning-based approach incorporating elements of interaction can vary muscular tension to accomplish different tasks. We control, in which the robot can adapt key parameters, such posit that the proposed method can substitute a trial-and-error as feed rate, depth of cut, and mechanical compliance during strategy of selecting process parameters for disassembly of novel task execution. We show how a mathematical model of cutting products, or integrated with existing planning approaches to mechanics, embedded in a simulation environment, can be used adjust the parameters of milling tasks online. The simulation approach control, passivity-based control, energy tank was validated on a real robot setup based on four case study materials with varying structural and mechanical properties.