Iterative Closest Labeled Point for Tactile Object Shape Recognition

TL;DR

This paper introduces iCLAP, a novel algorithm that combines tactile and kinesthetic data into a 4D point cloud for improved robot object recognition, demonstrating significant accuracy gains over single-modality methods.

Contribution

The paper presents a new algorithm that merges tactile and kinesthetic sensing into a 4D point cloud for enhanced object recognition in robotics.

Findings

iCLAP outperforms single-modality methods in recognition accuracy

Recognition rate improved by up to 18%

Effective integration of tactile and kinesthetic data

Abstract

Tactile data and kinesthetic cues are two important sensing sources in robot object recognition and are complementary to each other. In this paper, we propose a novel algorithm named Iterative Closest Labeled Point (iCLAP) to recognize objects using both tactile and kinesthetic information.The iCLAP first assigns different local tactile features with distinct label numbers. The label numbers of the tactile features together with their associated 3D positions form a 4D point cloud of the object. In this manner, the two sensing modalities are merged to form a synthesized perception of the touched object. To recognize an object, the partial 4D point cloud obtained from a number of touches iteratively matches with all the reference cloud models to identify the best fit. An extensive evaluation study with 20 real objects shows that our proposed iCLAP approach outperforms those using either of the separate sensing modalities, with a substantial recognition rate improvement of up to 18%.