Just Add Force for Contact-Rich Robot Policies

TL;DR

This paper introduces a new dataset of force feedback trajectories and demonstrates that policies trained with force information outperform position-only policies in delicate grasping tasks, enabling more contact-rich robot manipulation.

Contribution

The paper provides a publicly available dataset of force feedback trajectories and shows that incorporating force data improves grasping performance and generalization in robot policies.

Findings

Forceful policies outperform position-only policies in delicate grasping.

Force-based policies generalize better to unseen delicate objects.

Inclusion of force feedback reduces grasp policy latency by nearly 4x.

Abstract

Robot trajectories used for learning end-to-end robot policies typically contain end-effector and gripper position, workspace images, and language. Policies learned from such trajectories are unsuitable for delicate grasping, which require tightly coupled and precise gripper force and gripper position. We collect and make publically available 130 trajectories with force feedback of successful grasps on 30 unique objects. Our current-based method for sensing force, albeit noisy, is gripper-agnostic and requires no additional hardware. We train and evaluate two diffusion policies: one with (forceful) the collected force feedback and one without (position-only). We find that forceful policies are superior to position-only policies for delicate grasping and are able to generalize to unseen delicate objects, while reducing grasp policy latency by near 4x, relative to LLM-based methods. With our promising results on limited data, we hope to signal to others to consider investing in collecting force and other such tactile information in new datasets, enabling more robust, contact-rich manipulation in future robot foundation models. Our data, code, models, and videos are viewable at https://justaddforce.github.io/.