Touch if it's transparent! ACTOR: Active Tactile-based Category-Level Transparent Object Reconstruction

TL;DR

ACTOR introduces a novel active tactile-based framework for accurate shape reconstruction and pose estimation of transparent objects, overcoming vision limitations through self-supervised learning and efficient exploration strategies.

Contribution

The paper presents ACTOR, a new framework combining self-supervised learning and active tactile exploration for category-level transparent object reconstruction and pose estimation.

Findings

Outperforms state-of-the-art methods in tactile-based reconstruction

Effective in reconstructing unknown transparent objects

Improves pose estimation accuracy for transparent objects

Abstract

Accurate shape reconstruction of transparent objects is a challenging task due to their non-Lambertian surfaces and yet necessary for robots for accurate pose perception and safe manipulation. As vision-based sensing can produce erroneous measurements for transparent objects, the tactile modality is not sensitive to object transparency and can be used for reconstructing the object's shape. We propose ACTOR, a novel framework for ACtive tactile-based category-level Transparent Object Reconstruction. ACTOR leverages large datasets of synthetic object with our proposed self-supervised learning approach for object shape reconstruction as the collection of real-world tactile data is prohibitively expensive. ACTOR can be used during inference with tactile data from category-level unknown transparent objects for reconstruction. Furthermore, we propose an active-tactile object exploration strategy as probing every part of the object surface can be sample inefficient. We also demonstrate tactile-based category-level object pose estimation task using ACTOR. We perform an extensive evaluation of our proposed methodology with real-world robotic experiments with comprehensive comparison studies with state-of-the-art approaches. Our proposed method outperforms these approaches in terms of tactile-based object reconstruction and object pose estimation.