FORGE: Force-Guided Exploration for Robust Contact-Rich Manipulation under Uncertainty

TL;DR

FORGE introduces a force-aware manipulation method that enhances the robustness of contact-rich tasks in robots, effectively transferring policies from simulation to real-world scenarios despite pose uncertainties.

Contribution

The paper presents a novel approach combining force thresholds with dynamics randomization for sim-to-real transfer of contact-rich manipulation policies under uncertainty.

Findings

Successfully learned contact-rich policies like connector insertion.

Demonstrated multistage assembly of planetary gear systems.

Enabled autonomous force threshold tuning and task success prediction.

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 force threshold mechanism with a dynamics randomization 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. Project website can be accessed at https://noseworm.github.io/forge/.