D-SPDH: Improving 3D Robot Pose Estimation in Sim2Real Scenario via Depth Data

In recent years, there has been a notable surge in the significance attributed to technologies facilitating secure and efficient cohabitation and collaboration between humans and machines, with a particular interest in robotic systems. A pivotal element in actualizing this novel and challenging coll...

Full description

Saved in:
Bibliographic Details
Main Authors: Alessandro Simoni, Guido Borghi, Lorenzo Garattoni, Gianpiero Francesca, Roberto Vezzani
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10745501/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846150414452391936
author Alessandro Simoni
Guido Borghi
Lorenzo Garattoni
Gianpiero Francesca
Roberto Vezzani
author_facet Alessandro Simoni
Guido Borghi
Lorenzo Garattoni
Gianpiero Francesca
Roberto Vezzani
author_sort Alessandro Simoni
collection DOAJ
description In recent years, there has been a notable surge in the significance attributed to technologies facilitating secure and efficient cohabitation and collaboration between humans and machines, with a particular interest in robotic systems. A pivotal element in actualizing this novel and challenging collaborative paradigm involves different technical tasks, including the comprehension of 3D poses exhibited by both humans and robots through the utilization of non-intrusive systems, such as cameras. In this scenario, the availability of vision-based systems capable of detecting in real-time the robot’s pose is needed as a first step towards a safe and effective interaction to, for instance, avoid collisions. Therefore, in this work, we propose a vision-based system, referred to as D-SPDH, able to estimate the 3D robot pose. The system is based on double-branch architecture and depth data as a single input; any additional information regarding the state of the internal encoders of the robot is not required. The working scenario is the Sim2Real, i.e., the system is trained only with synthetic data and then tested on real sequences, thus eliminating the time-consuming acquisition and annotation procedures of real data, common phases in deep learning algorithms. Moreover, we introduce SimBa++, a dataset featuring both synthetic and real sequences with new real-world double-arm movements, and that represents a challenging setting in which the proposed approach is tested. Experimental results show that our D-SPDH method achieves state-of-the-art and real-time performance, paving the way a possible future non-invasive systems to monitor human-robot interactions.
format Article
id doaj-art-bcda3121d1304ac6a9c69c97fde65f85
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-bcda3121d1304ac6a9c69c97fde65f852024-11-29T00:01:17ZengIEEEIEEE Access2169-35362024-01-011216666016667310.1109/ACCESS.2024.349281210745501D-SPDH: Improving 3D Robot Pose Estimation in Sim2Real Scenario via Depth DataAlessandro Simoni0https://orcid.org/0000-0003-3095-3294Guido Borghi1https://orcid.org/0000-0003-2441-7524Lorenzo Garattoni2https://orcid.org/0000-0002-6382-0335Gianpiero Francesca3Roberto Vezzani4https://orcid.org/0000-0002-1046-6870Department of Engineering “Enzo Ferrari,”, University of Modena and Reggio Emilia, Reggio Emilia, ItalyDipartimento di Educazione e Scienze Umane, University of Modena and Reggio Emilia, Reggio Emilia, ItalyToyota Motor Europe, Brussels, BelgiumToyota Motor Europe, Brussels, BelgiumDepartment of Engineering “Enzo Ferrari,”, University of Modena and Reggio Emilia, Reggio Emilia, ItalyIn recent years, there has been a notable surge in the significance attributed to technologies facilitating secure and efficient cohabitation and collaboration between humans and machines, with a particular interest in robotic systems. A pivotal element in actualizing this novel and challenging collaborative paradigm involves different technical tasks, including the comprehension of 3D poses exhibited by both humans and robots through the utilization of non-intrusive systems, such as cameras. In this scenario, the availability of vision-based systems capable of detecting in real-time the robot’s pose is needed as a first step towards a safe and effective interaction to, for instance, avoid collisions. Therefore, in this work, we propose a vision-based system, referred to as D-SPDH, able to estimate the 3D robot pose. The system is based on double-branch architecture and depth data as a single input; any additional information regarding the state of the internal encoders of the robot is not required. The working scenario is the Sim2Real, i.e., the system is trained only with synthetic data and then tested on real sequences, thus eliminating the time-consuming acquisition and annotation procedures of real data, common phases in deep learning algorithms. Moreover, we introduce SimBa++, a dataset featuring both synthetic and real sequences with new real-world double-arm movements, and that represents a challenging setting in which the proposed approach is tested. Experimental results show that our D-SPDH method achieves state-of-the-art and real-time performance, paving the way a possible future non-invasive systems to monitor human-robot interactions.https://ieeexplore.ieee.org/document/10745501/Human-machine interactionhuman-robot interactioncollaborative robots (Cobots)robot pose estimationdeep learningcomputer vision
spellingShingle Alessandro Simoni
Guido Borghi
Lorenzo Garattoni
Gianpiero Francesca
Roberto Vezzani
D-SPDH: Improving 3D Robot Pose Estimation in Sim2Real Scenario via Depth Data
IEEE Access
Human-machine interaction
human-robot interaction
collaborative robots (Cobots)
robot pose estimation
deep learning
computer vision
title D-SPDH: Improving 3D Robot Pose Estimation in Sim2Real Scenario via Depth Data
title_full D-SPDH: Improving 3D Robot Pose Estimation in Sim2Real Scenario via Depth Data
title_fullStr D-SPDH: Improving 3D Robot Pose Estimation in Sim2Real Scenario via Depth Data
title_full_unstemmed D-SPDH: Improving 3D Robot Pose Estimation in Sim2Real Scenario via Depth Data
title_short D-SPDH: Improving 3D Robot Pose Estimation in Sim2Real Scenario via Depth Data
title_sort d spdh improving 3d robot pose estimation in sim2real scenario via depth data
topic Human-machine interaction
human-robot interaction
collaborative robots (Cobots)
robot pose estimation
deep learning
computer vision
url https://ieeexplore.ieee.org/document/10745501/
work_keys_str_mv AT alessandrosimoni dspdhimproving3drobotposeestimationinsim2realscenarioviadepthdata
AT guidoborghi dspdhimproving3drobotposeestimationinsim2realscenarioviadepthdata
AT lorenzogarattoni dspdhimproving3drobotposeestimationinsim2realscenarioviadepthdata
AT gianpierofrancesca dspdhimproving3drobotposeestimationinsim2realscenarioviadepthdata
AT robertovezzani dspdhimproving3drobotposeestimationinsim2realscenarioviadepthdata