End-to-end Reinforcement Learning of Robotic Manipulation with Robust Keypoints Representation

Page view(s)
71
Checked on Dec 02, 2024
End-to-end Reinforcement Learning of Robotic Manipulation with Robust Keypoints Representation
Title:
End-to-end Reinforcement Learning of Robotic Manipulation with Robust Keypoints Representation
Journal Title:
2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
Keywords:
Publication Date:
21 December 2022
Citation:
Wang, T., Puang, E. Y., Lee, M., Jing, W., & Wu, Y. (2022). End-to-end Reinforcement Learning of Robotic Manipulation with Robust Keypoints Representation. 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). https://doi.org/10.23919/apsipaasc55919.2022.9980136
Abstract:
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. In addition to the robust keypoints representation, we further apply domain randomization and adversarial training examples to achieve zero-shot sim-to-real transfer in real-world robotic manipulation tasks.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the A*STAR - AME Programmatic Funding Scheme
Grant Reference no. : A18A2b0046

Alibaba Group through Alibaba Innovative Research (AIR) Program
Description:
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
2640-0103
Files uploaded:

File Size Format Action
m18348-wang-final.pdf 4.92 MB PDF Request a copy