Tactile-RL for Insertion: Generalization to Objects of Unknown Geometry

by   Siyuan Dong, et al.

Object insertion is a classic contact-rich manipulation task. The task remains challenging, especially when considering general objects of unknown geometry, which significantly limits the ability to understand the contact configuration between the object and the environment. We study the problem of aligning the object and environment with a tactile-based feedback insertion policy. The insertion process is modeled as an episodic policy that iterates between insertion attempts followed by pose corrections. We explore different mechanisms to learn such a policy based on Reinforcement Learning. The key contribution of this paper is to demonstrate that it is possible to learn a tactile insertion policy that generalizes across different object geometries, and an ablation study of the key design choices for the learning agent: 1) the type of learning scheme: supervised vs. reinforcement learning; 2) the type of learning schedule: unguided vs. curriculum learning; 3) the type of sensing modality: force/torque (F/T) vs. tactile; and 4) the type of tactile representation: tactile RGB vs. tactile flow. We show that the optimal configuration of the learning agent (RL + curriculum + tactile flow) exposed to 4 training objects yields an insertion policy that inserts 4 novel objects with over 85.0 tactile sensing, shows that while an F/T-based policy learns more efficiently, a tactile-based policy provides better generalization.


page 1

page 4

page 5


Visual-Tactile Multimodality for Following Deformable Linear Objects Using Reinforcement Learning

Manipulation of deformable objects is a challenging task for a robot. It...

Manipulation via Membranes: High-Resolution and Highly Deformable Tactile Sensing and Control

Collocated tactile sensing is a fundamental enabling technology for dext...

Tactile-Based Insertion for Dense Box-Packing

We study the problem of using high-resolution tactile sensors to control...

Active Extrinsic Contact Sensing: Application to General Peg-in-Hole Insertion

We propose a method that actively estimates the location of contact betw...

Learning Purely Tactile In-Hand Manipulation with a Torque-Controlled Hand

We show that a purely tactile dextrous in-hand manipulation task with co...

Tactile-ViewGCN: Learning Shape Descriptor from Tactile Data using Graph Convolutional Network

For humans, our "senses of touch" have always been necessary for our abi...

Extrinsic Contact Sensing with Relative-Motion Tracking from Distributed Tactile Measurements

This paper addresses the localization of contacts of an unknown grasped ...