Sliding Touch-based Exploration for Modeling Unknown Object Shape with Multi-fingered Hands

TL;DR

This paper introduces a novel tactile exploration method using multi-fingered hands and Bayesian optimization to efficiently and accurately reconstruct the shape of unknown objects from partial views, suitable for unstructured environments.

Contribution

It proposes a new sliding touch strategy combined with a multi-finger perception approach for improved 3D shape reconstruction of unknown objects.

Findings

Successful shape reconstruction with few sliding touches

Effective in simulation and real robot experiments

Accurate modeling of objects from partial views

Abstract

Efficient and accurate 3D object shape reconstruction contributes significantly to the success of a robot's physical interaction with its environment. Acquiring accurate shape information about unknown objects is challenging, especially in unstructured environments, e.g. the vision sensors may only be able to provide a partial view. To address this issue, tactile sensors could be employed to extract local surface information for more robust unknown object shape estimation. In this paper, we propose a novel approach for efficient unknown 3D object shape exploration and reconstruction using a multi-fingered hand equipped with tactile sensors and a depth camera only providing a partial view. We present a multi-finger sliding touch strategy for efficient shape exploration using a Bayesian Optimization approach and a single-leader-multi-follower strategy for multi-finger smooth local surface perception. We evaluate our proposed method by estimating the 3D shape of objects from the YCB and OCRTOC datasets based on simulation and real robot experiments. The proposed approach yields successful reconstruction results relying on only a few continuous sliding touches. Experimental results demonstrate that our method is able to model unknown objects in an efficient and accurate way.