English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We present an end-to-end Reinforcement Learning(RL) framework for roboticmanipulation tasks, using a robust and efficient keypoints representation. Theproposed method learns keypoints from camera images as the staterepresentation, through a self-supervised autoencoder architecture. Thekeypoints encode the geometric information, as well as the relationship of thetool and target in a compact representation to ensure efficient and robustlearning. After keypoints learning, the RL step then learns the robot motionfrom the extracted keypoints state representation. The keypoints and RLlearning processes are entirely done in the simulated environment. Wedemonstrate the effectiveness of the proposed method on robotic manipulationtasks including grasping and pushing, in different scenarios. We alsoinvestigate the generalization capability of the trained model. In addition tothe robust keypoints representation, we further apply domain randomization andadversarial training examples to achieve zero-shot sim-to-real transfer inreal-world robotic manipulation tasks.

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