Reinforcement Learning on Variable Impedance Controller for High-Precision Robotic Assembly
This addresses the challenge of autonomous, precise manipulation in industrial robotics, though it is incremental by building on existing RL and control methods.
The paper tackled the problem of high-precision robotic assembly by incorporating force/torque information into reinforcement learning, achieving improved performance on a tight-fit gear assembly task with concrete gains in success rates.
Precise robotic manipulation skills are desirable in many industrial settings, reinforcement learning (RL) methods hold the promise of acquiring these skills autonomously. In this paper, we explicitly consider incorporating operational space force/torque information into reinforcement learning; this is motivated by humans heuristically mapping perceived forces to control actions, which results in completing high-precision tasks in a fairly easy manner. Our approach combines RL with force/torque information by incorporating a proper operational space force controller; where we also exploit different ablations on processing this information. Moreover, we propose a neural network architecture that generalizes to reasonable variations of the environment. We evaluate our method on the open-source Siemens Robot Learning Challenge, which requires precise and delicate force-controlled behavior to assemble a tight-fit gear wheel set.