Sim2Real for Peg-Hole Insertion with Eye-in-Hand Camera
This addresses the problem of flexibility and generalization in robotic manipulation for researchers and practitioners, but it is incremental as it applies an existing method to a specific task.
The paper tackled the challenge of peg-hole insertion in robotics by learning an end-to-end policy in simulation using Deep Reinforcement Learning and transferring it to a real robot without fine-tuning, achieving successful performance on the real robot.
Even though the peg-hole insertion is one of the well-studied problems in robotics, it still remains a challenge for robots, especially when it comes to flexibility and the ability to generalize. Successful completion of the task requires combining several modalities to cope with the complexity of the real world. In our work, we focus on the visual aspect of the problem and employ the strategy of learning an insertion task in a simulator. We use Deep Reinforcement Learning to learn the policy end-to-end and then transfer the learned model to the real robot, without any additional fine-tuning. We show that the transferred policy, which only takes RGB-D and joint information (proprioception) can perform well on the real robot.