Bi-Touch: Bimanual Tactile Manipulation with Sim-to-Real Deep Reinforcement Learning

TL;DR

This paper introduces Bi-Touch, a dual-arm tactile robotic system utilizing deep reinforcement learning for bimanual manipulation tasks, demonstrating successful sim-to-real transfer and robustness with unseen objects and perturbations.

Contribution

The paper presents a novel dual-arm tactile robot system with a new suite of bimanual tasks, a goal-update RL mechanism, and insights into sim-to-real transfer challenges.

Findings

Effective policies learned for bimanual tasks using deep RL.

Successful sim-to-real transfer with robustness to unseen objects.

Identification of challenges like squeezing due to sim-to-real gap.

Abstract

Bimanual manipulation with tactile feedback will be key to human-level robot dexterity. However, this topic is less explored than single-arm settings, partly due to the availability of suitable hardware along with the complexity of designing effective controllers for tasks with relatively large state-action spaces. Here we introduce a dual-arm tactile robotic system (Bi-Touch) based on the Tactile Gym 2.0 setup that integrates two affordable industrial-level robot arms with low-cost high-resolution tactile sensors (TacTips). We present a suite of bimanual manipulation tasks tailored towards tactile feedback: bi-pushing, bi-reorienting and bi-gathering. To learn effective policies, we introduce appropriate reward functions for these tasks and propose a novel goal-update mechanism with deep reinforcement learning. We also apply these policies to real-world settings with a tactile sim-to-real approach. Our analysis highlights and addresses some challenges met during the sim-to-real application, e.g. the learned policy tended to squeeze an object in the bi-reorienting task due to the sim-to-real gap. Finally, we demonstrate the generalizability and robustness of this system by experimenting with different unseen objects with applied perturbations in the real world. Code and videos are available at https://sites.google.com/view/bi-touch/.