期刊: [Institute of Electrical and Electronics Engineers] 日期:2018-10-01卷期号:: 2062-2069被引量:105
标识
DOI:10.1109/iros.2018.8594353
摘要
Reinforcement learning for assembly tasks can yield powerful robot control algorithms for applications that are challenging or even impossible for “conventional” feedback control methods. Insertion of a rigid peg into a deformable hole of smaller diameter is such a task. In this contribution we solve this task with Deep Reinforcement Learning. Force-torque measurements from a robot arm wrist sensor are thereby incorporated two-fold; they are integrated into the policy learning process and they are exploited in an admittance controller that is coupled to the neural network. This enables robot learning of contact-rich assembly tasks without explicit joint torque control or passive mechanical compliance. We demonstrate our approach in experiments with an industrial robot.