Task-oriented cross-system design for Metaverse in 6G era

Meng, Zhen (2023) Task-oriented cross-system design for Metaverse in 6G era. PhD thesis, University of Glasgow.

Abstract

As an emerging concept, the Metaverse has the potential to revolutionize social interaction in the post-pandemic era by establishing a digital world for online education, remote healthcare, immersive business, intelligent transportation, and advanced manufacturing. The goal is ambitious, yet the methodologies and technologies to achieve the full vision of the Metaverse remain unclear. In this thesis, we first introduce the three pillars of infrastructure that lay the foundation of the Metaverse, i.e., Human-Computer Interfaces (HCIs), sensing and communication systems, and network architectures. Then, we depict the roadmap towards the Metaverse that consists of four stages with different applications. As one of the essential building blocks for the Metaverse, we also review the state-of-the-art Computer Vision for the Metaverse as well as the future scope. To support diverse applications in the Metaverse, we put forward a novel design methodology: task-oriented cross-system design, and further review the potential solutions and future challenges.

Specifically, we establish a task-oriented cross-system design for a simple case, where sampling, communications, and prediction modules are jointly optimized for the synchronization of the real-world devices and digital model in the Metaverse. We use domain knowledge to design a deep reinforcement learning (DRL) algorithm to minimize the communication load subject to an average tracking error constraint. We validate our framework on a prototype composed of a real-world robotic arm and its digital model. The results show that our framework achieves a better trade-off between the average tracking error and the average communication load compared to a communication system without sampling and prediction. For example, the average communication load can be reduced to 87% when the average track error constraint is 0.002◦ . In addition, our policy outperforms the benchmark with the static sampling rate and prediction horizon optimized by exhaustive search, in terms of the tail probability of the tracking error. Furthermore, with the assistance of expert knowledge, the proposed algorithm achieves a better convergence time, stability, communication load, and average tracking error.

Furthermore, we establish a task-oriented cross-system design framework for a general case, where the goal is to minimize the required packet rate for timely and accurate modeling of a real-world robotic arm in the Metaverse. Specifically, different modules including sensing, communications, prediction, control, and rendering are considered. To optimize a scheduling policy and prediction horizons, we design a Constraint Proximal Policy Optimization (CPPO) algorithm by integrating domain knowledge from relevant systems into the advanced reinforcement learning algorithm, Proximal Policy Optimization (PPO). Specifically, the Jacobian matrix for analyzing the motion of the robotic arm is included in the state of the CPPO algorithm, and the Conditional Value-at-Risk (CVaR) of the state-value function characterizing the long-term modeling error is adopted in the constraint. Besides, the policy is represented by a two-branch neural network determining the scheduling policy and the prediction horizons, respectively. To evaluate our algorithm, we build a prototype including a real-world robotic arm and its digital model in the Metaverse. The experimental results indicate that domain knowledge helps to reduce the convergence time and the required packet rate by up to 50%, and the cross-system design framework outperforms a baseline framework in terms of the required packet rate and the tail distribution of the modeling error.

• Item Type: Thesis (PhD)
• Qualification Level: Doctoral
• Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science; Q Science > QA Mathematics > QA76 Computer software; T Technology > T Technology (General); T Technology > TA Engineering (General). Civil engineering (General)
• Colleges/Schools: College of Science and Engineering > School of Engineering
• Supervisor's Name: Zhao, Dr. Guodong, Li, Dr. Liying and Imran, Professor Muhammad
• Date of Award: 2023
• Depositing User: Theses Team
• Unique ID: glathesis:2023-83985
• Copyright: Copyright of this thesis is held by the author.
• Date Deposited: 08 Dec 2023 15:28
• Last Modified: 08 Dec 2023 15:29
• Thesis DOI: 10.5525/gla.thesis.83985
• URI: https://theses.gla.ac.uk/id/eprint/83985

Related URLs

• Article DOI