FORGE: Force-Guided Exploration for Robust Contact-Rich Manipulation Under Uncertainty
Michael Noseworthy, Bingjie Tang, Bowen Wen, Ankur Handa, Chad C. Kessens, Nicholas Roy, Dieter Fox, Fabio Ramos
Abstract
We present FORGE, a method for sim-to-real transfer of force-aware manipulation policies in the presence of significant pose uncertainty. During simulation-based policy learning, FORGE combines a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">force threshold</i> mechanism with a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">dynamics randomization</i> scheme to enable robust transfer of the learned policies to the real robot. At deployment, FORGE policies, conditioned on a maximum allowable force, adaptively perform contact-rich tasks while avoiding aggressive and unsafe behaviour, regardless of the controller gains. Additionally, FORGE policies predict task success, enabling efficient termination and autonomous tuning of the force threshold. We show that FORGE can be used to learn a variety of robust contact-rich policies, including the forceful insertion of snap-fit connectors. We further demonstrate the multistage assembly of a planetary gear system, which requires success across three assembly tasks: nut threading, insertion, and gear meshing.
BibTeX
@inproceedings{ral2025_forgeforceguided,
title = {FORGE: Force-Guided Exploration for Robust Contact-Rich Manipulation Under Uncertainty},
author = {Michael Noseworthy and Bingjie Tang and Bowen Wen and Ankur Handa and Chad C. Kessens and Nicholas Roy and Dieter Fox and Fabio Ramos and Yashraj Narang and Iretiayo Akinola},
booktitle = {RA-L 2025},
year = {2025}
}