Hybrid Collaborative XR Environment Operated with Digital Twin in Edge-Cloud.
Ing./MSc.
Intership Proposal in Computer Science Scientific Fields:
Human-Computer Interaction, Edge/Cloud Computing, Extended Reality and Digital Twin Technologies Keywords:
Augmented Reality, Cloud, Docker, Data compression, Edge, Extended Reality, Digital Twins, IIoT, Machine Learning, Unity, OPCUA, Virtual Reality Supervisors:
â?¢ Hugues M.
KAMDJOU, Researcher at CESI-LINEACT â?¢ Havard Vincent, Associate Professor at CESI-LINEACT Research Work Internship Description EXtended Reality (XR) alongside the Digital Twin (DT) in Industrial Internet of Things (IIoT) emerges as a promising next-generation technology.
This project centers around advancing collaborative XR experiences by seamlessly integrating Virtual Reality (VR) and/or Augmented Reality (AR), fostering a cohesive experience for both location-based and remote users.
In the initial phase of the project, we have already developed an environment integrating VR with DT.
The current aim is to extend this immersive experience by integrating AR within the framework of an Edge-Cloud architecture.
This includes maintaining consistency in the hybrid collaborative environment while incorporating the unique features of AR.
Building upon the developed environment, the internship will also explore how data compression can be further utilized to enhance the realism and dynamism of both VR and AR elements within the XR space coupled with DT.
Previous Work in the Laboratory:
JENII project, is a remote learning initiative for the future industry, built upon immersive and collaborative environments centered around digital twins of real industrial systems.
Work Program/Objectives:
The main aim of this Master's thesis is to enhance Quality of Service (QoS) of hybrid collaborative XR experiences through synchronized DT in Edge-Cloud.
The objectives/program include:
1.
Implementation of an Edge-Cloud architecture to optimize performance and reduce latency of the existing XR environment.
2.
Integration of automated monitoring using the camera-equipped robotic arm to capture the state object conditions and transmit data to the DT; integration of multi-user and augmented reality into the existing XR environment.
3.
Test a multi-user collaboration scenario on a specific use case and evaluate the QoS.
4.
Propose potential solutions to integrate data compression into the framework for reducing latency.
5.
Propose potential solutions to establish common ground among co-located and remote users with heterogeneous devices.
Expected Scientific/Technical Output:
This internship project bridges research and industry, driving progress in immersive technologies and industrial efficiency.
The purpose is to investigate performance optimisation techniques for hybrid collaborative XR environments.
The expected outcomes include a comprehensive documentation report delineating the research, experiments, and evaluations conducted during the proof-of-concept development phase.
These contributions serve to propel advancements in XR and DT technologies, enriching the academic community's knowledge base and catalyzing innovation.
Industrial partners stand to reap operational advantages from enhanced performance in real-world XR applications.
Context Laboratory Presentation:
CESI LINEACT (Laboratoire d'Innovation Num´erique pour les Entreprises et les Apprentissages au service de la Comp´etitivit´e des Territoires) Tools and Digital Engineering (TDN) team conducts research activities in human-machine interactions, XR, applied robotics, digital twins, fusion of information and decision in cyber physical production system.
Recent works are interested in human activity/action recognition based on deep learning approaches for human-robot collaboration applications.
The approaches explored also the generation of data for human action recognition from the digital twin associated with virtual or augmented environments allowing to simulate industrial scenario involving human robot interaction.
CESI LINEACT also have various research facilities like flexible manufacturing assembly with cobotic or dual-arm TIAGO mobile robot associated to their digital twins which could be used in these experiments.
Positioning in Laboratory Research thematics:
The project aims to harness the synergies between Modeling, desing and architecture of CPS, and Collaborative processes and digital tools.
Thesis/Internship Organization â?¢ Workplace:
CESI LINEACT, Campus PAU, 8 rue des Fr`eres d'Orbigny 64000 Pau, France.
â?¢ Start Date:
As soon as possible until it is filled.
2 â?¢ Duration:
5/6 months References [1] Kamdjou Hugues M., Baudry David, Havard Vincent, and Ouchani Samir.
Resource-constrained extended reality operated with digital twin in industrial internet of things.
IEEE Open Journal of the Communications Society, 5:
928-950, 2024.
[2] Vincent Havard, Alexandre Courallet, David Baudry, and Hugues Delalin.
Virtual reality and opcua-based architecture for pedagogical scenarios in manufacturing and computer sciences curriculum.
in Proceedings of the 13th Conference on Learning Factories (CLF 2023), 2023.
3 [3] Shakarami A., Ghobaei-Arani M., and et al.
Masdari M.
A survey on the computation offloading approaches in mobile edge/cloud computing environment:
A stochastic-based perspective.
J Grid Computing, 18:
639-671, 2020.
[4] Yi Ding, Weiwei Fang, and et al.
Mengran Liu.
Jmdc:
A joint model and data compression system for deep neural networks collaborative computing in edge-cloud networks.
Journal of Parallel and Distributed Computing, 173:
83-93, 2023.
[5] Yu S., Sun S., Yan W., Liu G., and X.
Li.
A method based on curvature and hierarchical strategy for dynamic point cloud compression in augmented and virtual reality system.
Sensors, 22:
1262, 2022.
[6] Joseph Azar, Abdallah Makhoul, Mahmoud Barhamgi, and Raphael Couturier.
An energy efficient iot data compression approach for edge machine learning.
Future Generation Computer Systems, 96:
168-175, 2019.
[7] Wang Y., Chakravarthula P., Sun Q., and Chen B.
Joint neural phase retrieval and compression for energy - and computation-efficient holography on the edge.
