End-Effector-Elbow: A New Action Space for Robot Learning

Pietro Mazzaglia, Nicholas Backshall, Xiao Ma, Stephen James

Primary Area: applications to robotics, autonomy, planning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: robot learning, robotics, action representation

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: A novel action space for robot learning that addresses the limitations of existing control paradigms by enabling control both over the end-effector and the elbow pose of the robot.

Abstract:

Joint control and end-effector control are the two most dominant control methods for robot arms within the robot learning literature. Joint control, while precise, often suffers from inefficient training; end-effector control boasts data-efficient training but sacrifices the ability to perform tasks in confined spaces due to limited control over the robot joint configuration. This paper introduces a novel action space formulation: End-Effector-Elbow (E3), which addresses the limitations of existing control paradigms by allowing the control of both the end-effector and elbow of the robot. E3 combines the advantages of both joint and end-effector control, offering fine-grained comprehensive control with overactuated robot arms whilst achieving highly efficient robot learning. E3 systematically outperforms other action spaces, when precise control over the robot configuration is required, both in simulated and real environments.

Project website: https://doubleblind-repos.github.io/

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 6452