CaltechAUTHORS
  A Caltech Library Service

OSCAR: Data-Driven Operational Space Control for Adaptive and Robust Robot Manipulation

Wong, Josiah and Makoviychuk, Viktor and Anandkumar, Anima and Zhu, Yuke (2021) OSCAR: Data-Driven Operational Space Control for Adaptive and Robust Robot Manipulation. . (Unpublished) https://resolver.caltech.edu/CaltechAUTHORS:20220714-224711626

[img] PDF - Submitted Version
See Usage Policy.

5MB

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20220714-224711626

Abstract

Learning performant robot manipulation policies can be challenging due to high-dimensional continuous actions and complex physics-based dynamics. This can be alleviated through intelligent choice of action space. Operational Space Control (OSC) has been used as an effective task-space controller for manipulation. Nonetheless, its strength depends on the underlying modeling fidelity, and is prone to failure when there are modeling errors. In this work, we propose OSC for Adaptation and Robustness (OSCAR), a data-driven variant of OSC that compensates for modeling errors by inferring relevant dynamics parameters from online trajectories. OSCAR decomposes dynamics learning into task-agnostic and task-specific phases, decoupling the dynamics dependencies of the robot and the extrinsics due to its environment. This structure enables robust zero-shot performance under out-of-distribution and rapid adaptation to significant domain shifts through additional finetuning. We evaluate our method on a variety of simulated manipulation problems, and find substantial improvements over an array of controller baselines. For more results and information, please visit this https URL https://cremebrule.github.io/oscar-web/.


Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription
https://doi.org/10.48550/arXiv.2110.00704arXivDiscussion Paper
https://cremebrule.github.io/oscar-web/Related Itemmore results and information8
Additional Information:We would like to thank Jim Fan and the NVIDIA AI-ALGO team for their insightful feedback and discussion, and the NVIDIA IsaacGym simulation team for providing technical support.
Record Number:CaltechAUTHORS:20220714-224711626
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20220714-224711626
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:115611
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:15 Jul 2022 22:56
Last Modified:15 Jul 2022 22:56

Repository Staff Only: item control page