DexForce: Extracting Force-informed Actions from Kinesthetic Demonstrations for Dexterous Manipulation

TL;DR

DexForce introduces a method to extract force-informed actions from kinesthetic demonstrations, significantly improving policy success rates in contact-rich dexterous manipulation tasks by leveraging contact force data.

Contribution

The paper presents DexForce, a novel approach that uses contact force measurements during demonstrations to enhance imitation learning for dexterous manipulation.

Findings

Policies trained with force-informed actions achieve 76% success rate.

Using force data improves performance especially in precision tasks.

Force data inclusion never degrades policy performance.

Abstract

Imitation learning requires high-quality demonstrations consisting of sequences of state-action pairs. For contact-rich dexterous manipulation tasks that require dexterity, the actions in these state-action pairs must produce the right forces. Current widely-used methods for collecting dexterous manipulation demonstrations are difficult to use for demonstrating contact-rich tasks due to unintuitive human-to-robot motion retargeting and the lack of direct haptic feedback. Motivated by these concerns, we propose DexForce. DexForce leverages contact forces, measured during kinesthetic demonstrations, to compute force-informed actions for policy learning. We collect demonstrations for six tasks and show that policies trained on our force-informed actions achieve an average success rate of 76% across all tasks. In contrast, policies trained directly on actions that do not account for contact forces have near-zero success rates. We also conduct a study ablating the inclusion of force data in policy observations. We find that while using force data never hurts policy performance, it helps most for tasks that require advanced levels of precision and coordination, like opening an AirPods case and unscrewing a nut.