End-to-end reinforcement learning of robotic manipulation with robust keypoints representation
Published in 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2022
We present an end-to-end Reinforcement Learning (RL) framework for robotic manipulation tasks, using a robust and efficient keypoints representation. The proposed method learns keypoints from camera images as the state representation, through a self-supervised autoencoder architecture. The key-points encode the geometric information, as well as the relationship of the tool and target in a compact representation to ensure efficient and robust learning. After keypoints learning, the RL step then learns the robot motion from the extracted keypoints state representation. The keypoints and RL learning processes are entirely done in the simulated environment. We demonstrate the effectiveness of the proposed method on robotic manipulation tasks including grasping and pushing, in different scenarios. We also investigate the generalization capability of the trained model.
Recommended citation: Wang, T., Puang, E. Y., Lee, M., Jing, W., & Wu, Y. (2022, November). End-to-end reinforcement learning of robotic manipulation with robust keypoints representation. In 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) (pp. 01-08). IEEE.