AnyRotate: Gravity-Invariant In-Hand Object Rotation with Sim-to-Real Touch

TL;DR

AnyRotate introduces a gravity-invariant in-hand object rotation system that leverages dense tactile sim-to-real transfer, enabling robots to manipulate unseen objects with robustness and arbitrary orientation control.

Contribution

The paper presents a novel sim-to-real tactile policy for gravity-invariant multi-axis in-hand object rotation, capable of handling unseen objects and arbitrary axes.

Findings

Dense tactile sensing improves grasp stability detection.

Rich contact information enhances policy robustness.

Zero-shot transfer enables manipulation of unseen objects.

Abstract

Human hands are capable of in-hand manipulation in the presence of different hand motions. For a robot hand, harnessing rich tactile information to achieve this level of dexterity still remains a significant challenge. In this paper, we present AnyRotate, a system for gravity-invariant multi-axis in-hand object rotation using dense featured sim-to-real touch. We tackle this problem by training a dense tactile policy in simulation and present a sim-to-real method for rich tactile sensing to achieve zero-shot policy transfer. Our formulation allows the training of a unified policy to rotate unseen objects about arbitrary rotation axes in any hand direction. In our experiments, we highlight the benefit of capturing detailed contact information when handling objects of varying properties. Interestingly, we found rich multi-fingered tactile sensing can detect unstable grasps and provide a reactive behavior that improves the robustness of the policy. The project website can be found at https://maxyang27896.github.io/anyrotate/.