Deep Reinforcement Learning for High Precision Assembly Tasks
This addresses the problem of tedious manual tuning in manufacturing for high precision assembly, though it appears incremental as it applies existing deep reinforcement learning methods to a specific robotic task.
The paper tackled high precision assembly tasks by training a recurrent neural network with reinforcement learning, enabling a robot to perform a tight clearance peg-in-hole task with robustness against position and angle errors.
High precision assembly of mechanical parts requires accuracy exceeding the robot precision. Conventional part mating methods used in the current manufacturing requires tedious tuning of numerous parameters before deployment. We show how the robot can successfully perform a tight clearance peg-in-hole task through training a recurrent neural network with reinforcement learning. In addition to saving the manual effort, the proposed technique also shows robustness against position and angle errors for the peg-in-hole task. The neural network learns to take the optimal action by observing the robot sensors to estimate the system state. The advantages of our proposed method is validated experimentally on a 7-axis articulated robot arm.