ABSTRACT. This paper draws on a substantial body of theoretical and empirical research on metaverse and digital twin technologies, industrial artificial Internet of Things and mobile edge computing networks, 3D image modeling and realistic virtual simulation tools, and spatial cognition and robotic motion planning algorithms. A quantitative literature review of ProQuest, Scopus, and the Web of Science was carried out throughout February 2023, with search terms including “digital twin industrial metaverse” + “image-based visual computing and deep learning-based 6G data-driven network technologies,” “deep reinforcement learning-based and bio-inspired robotic navigation algorithms,” and “multimodal generative artificial intelligence and context-aware augmented reality systems.” As research published in 2022 and 2023 was inspected, only 165 articles satisfied the eligibility criteria, and 20 mainly empirical sources were selected. Data visualization tools: Dimensions (bibliometric mapping) and VOSviewer (layout algorithms). Reporting quality assessment tool: PRISMA. Methodological quality assessment tools include: BIBOT, CASP, Eppi-Reviewer, Litstream, ROBIS, and SluRp.
JEL codes: D53; E22; E32; E44; G01; G41

Keywords: visual computing; 6G data-driven network; bio-inspired robotic navigation; multimodal generative artificial intelligence; digital twin industrial metaverse

How to cite: Poliak, M., Marica, M. E., and Sedlarski, T. (2023). “Image-based Visual Computing and Deep Learning-based 6G Data-driven Network Technologies, Deep Reinforcement Learning-based and Bio-inspired Robotic Navigation Algorithms, and Multimodal Generative Artificial Intelligence and Context-aware Augmented Reality Systems in Digital Twin Industrial Metaverse,” Journal of Self-Governance and Management Economics 11(3): 85–99. doi: 10.22381/jsme11320234.

Received 24 March 2023 • Received in revised form 25 September 2023
Accepted 27 September 2023 • Available online 30 September 2023