Lihui Wang Polyu Scholars Hub

Leo Migdal

-Dec 6, 2025, 9:20 PM

Select a country/territory to view shared publications and projects Research output: Journal article publication › Journal article › Academic research › peer-review Research output: Journal article publication › Journal article › Academic research › peer-review Research output: Journal article publication › Journal article › Academic research › peer-review Research output: Journal article publication › Journal article › Academic research › peer-review Research output: Journal article publication › Review article › Academic research › peer-review

To facilitate the personalized smart manufacturing paradigm with cognitive automation capabilities, Deep Reinforcement Learning (DRL) has attracted ever-increasing attention by offering an adaptive and flexible solution. DRL takes the advantages of both Deep Neural Networks (DNN) and Reinforcement Learning (RL), by embracing the power of representation learning, to make precise and fast decisions when facing dynamic and complex situations. Ever since the first paper of DRL was published in 2013, its applications have sprung up across the manufacturing field with exponential publication growth year by year. However, there still lacks any comprehensive review of the DRL in the field of smart manufacturing. To fill this gap, a systematic review process was conducted, with 261 relevant publications selected to date (20-Oct-2022), to gain a holistic understanding of the development, application, and challenges of DRL in smart manufacturing... First, the concept and development of DRL are summarized.

Then, the typical DRL applications are analyzed in the four engineering lifecycle stages: design, manufacturing, distribution, and maintenance. Finally, the challenges and future directions are illustrated, especially emerging DRL-related technologies and solutions that can improve the manufacturing system's deployment feasibility, cognitive capability, and learning efficiency, respectively. It is expected that this work can provide an insightful guide to the research of DRL in the smart manufacturing field and shed light on its future perspectives. Research output: Journal article publication › Review article › Academic research › peer-review T1 - Deep reinforcement learning in smart manufacturing: A review and prospects N1 - Funding Information: This work was partially supported by the grants from the Research Grants Council of the Hong Kong Special Administrative Region , China (Project No.

PolyU 15210222 ), National Natural Science Foundation of China (No. 52005424 ), and the Laboratory for Artificial Intelligence in Design (Project Code: RP2-1), Hong Kong Special Administrative Region, China. Publisher Copyright: © 2022 CIRP Research output: Journal article publication › Journal article › Academic research › peer-review Industry 5.0 blows the whistle on global industrial transformation. It aims to place humans’ well-being at the center of manufacturing systems, thereby achieving social goals beyond employment and growth to provide prosperity robustly for the sustainable development of all humanity.

However, the current exploration of Industry 5.0 is still in its infancy where research findings are relatively scarce and little systematic. This paper first reviews the evolutionary vein of Industry 5.0 and three leading characteristics of Industry 5.0: human-centricity, sustainability, and resiliency. The connotation system of Industry 5.0 is discussed, and its diversified essence is analyzed. Then, this paper constructs a tri-dimension system architecture for implementing Industry 5.0, namely, the technical dimension, reality dimension, and application dimension. The paper further discusses key enablers, the future implementation path, potential applications, and challenges of realistic scenarios of Industry 5.0. Finally, the limitations of the current research are discussed with potential future research directions highlighted.

It is expected that this review work will arouse lively discussions and debates, and bring together the strengths of all beings for building a comprehensive system of Industry 5.0. Research output: Journal article publication › Journal article › Academic research › peer-review T1 - Industry 5.0: Prospect and retrospect N1 - Funding Information: This work was supported by the National Natural Science Foundation of China under Grant No. 52075107 , No. 52205542 , and U20A6004 ; Outstanding Youth Fund of Guangdong Province under Grant No.

2022B1515020006 ; and the Shenzhen Special Fund for the Development of Strategic Emerging Industries under Grant No. JCYJ20170818100156260 . The first author also wants to express gratitude to Dr. Yuqian Lu for providing valuable comments to improve this paper. Publisher Copyright: © 2022 The Society of Manufacturing Engineers Research output: Journal article publication › Review article › Academic research › peer-review

With the continuous development of human-centric, resilient, and sustainable manufacturing towards Industry 5.0, Artificial Intelligence (AI) has gradually unveiled new opportunities for additional functionalities, new features, and tendencies in the industrial landscape. On the other hand, the technology-driven Industry 4.0 paradigm is still in full swing. However, there exist many unreasonable designs, configurations, and implementations of Industrial Artificial Intelligence (IndAI) in practice before achieving either Industry 4.0 or Industry 5.0 vision, and a significant gap between the individualized requirement and... To provide insights for designing appropriate models and algorithms in the upgrading process of the industry, this perspective article classifies IndAI by rating the intelligence levels and presents four principles of implementing IndAI. Three significant opportunities of IndAI, namely, collaborative intelligence, self-learning intelligence, and crowd intelligence, towards Industry 5.0 vision are identified to promote the transition from a technology-driven initiative in Industry 4.0 to the coexistence and... Then, pathways for implementing IndAI towards Industry 5.0 together with key empowering techniques are discussed.

Social barriers, technology challenges, and future research directions of IndAI are concluded, respectively. We believe that our effort can lay a foundation for unlocking the power of IndAI in futuristic Industry 5.0 research and engineering practice. This output contributes to the following UN Sustainable Development Goals (SDGs) Research output: Journal article publication › Review article › Academic research › peer-review T1 - Unlocking the power of industrial artificial intelligence towards Industry 5.0: Insights, pathways, and challenges Research output: Journal article publication › Journal article › Academic research › peer-review

Human-Robot Collaboration (HRC) has played a pivotal role in today's human-centric smart manufacturing scenarios. Nevertheless, limited concerns have been given to HRC uncertainties. By integrating both human and artificial intelligence, this paper proposes a Collaborative Intelligence (CI)-based approach for handling three major types of HRC uncertainties (i.e., human, robot and task uncertainties). A fine-grained human digital twin modelling method is introduced to address human uncertainties with better robotic assistance. Meanwhile, a learning from demonstration approach is offered to handle robotic task uncertainties with human intelligence. Lastly, the feasibility of the proposed CI has been demonstrated in an illustrative HRC assembly task.

Research output: Journal article publication › Journal article › Academic research › peer-review T1 - A collaborative intelligence-based approach for handling human-robot collaboration uncertainties N1 - Publisher Copyright: © 2023 The Authors Research output: Journal article publication › Review article › Academic research › peer-review human-robot collaboration (HRC) is set to transform the manufacturing paradigm by leveraging the strengths of human flexibility and robot precision. The recent breakthrough of Large Language Models (LLMs) and Vision-Language Models (VLMs) has motivated the preliminary explorations and adoptions of these models in the smart manufacturing field.

However, despite the considerable amount of effort, existing research mainly focused on individual components without a comprehensive perspective to address the full potential of VLMs, especially for HRC in smart manufacturing scenarios. To fill the gap, this work offers a systematic review of the latest advancements and applications of VLMs in HRC for smart manufacturing, which covers the fundamental architectures and pretraining methodologies of LLMs and... Lastly, the paper discusses current limitations and future research directions in VLM-based HRC, highlighting the trend in fully realizing the potential of these technologies for smart manufacturing. Research output: Journal article publication › Review article › Academic research › peer-review T1 - Vision-language model-based human-robot collaboration for smart manufacturing: A state-of-the-art survey N1 - Publisher Copyright: © The Author(s) 2024.

Professor and Chair of Sustainable Manufacturing, Director of Centre of Excellence in Production Research Member of International Advisory Committee PolyU Scholars Hub PolyU Scholars Hub is a platform where you can explore researchers, activities and achievements of our University. Leveraging its world-class academic and research excellence, as well as its state-of-the-art research centres and facilities, PolyU develops innovative solutions for a more sustainable tomorrow. With a strong interdisciplinary focus, PolyU actively addresses complex global problems that require collaboration across disciplines. The Scholars Hub serves as a one-stop platform where you can find out about PolyU scholars, including their biographies, research output and achievements.

Find out some patented technologies here. For eligible PolyU users to manage your profile: 🤵 Login 2. PolyU Scholars Hub Content Management for Researcher 2a. PolyU Scholars Hub workspace interface

2c. Set task and messages alert for pending task/notification 2d-1. Auto-import from Scopus using PolyU Scholars Hub’ curation feature

Lihui Wang Polyu Scholars Hub

People Also Search

Select A Country/territory To View Shared Publications And Projects Research

To Facilitate The Personalized Smart Manufacturing Paradigm With Cognitive Automation

Then, The Typical DRL Applications Are Analyzed In The Four

PolyU 15210222 ), National Natural Science Foundation Of China (No.

However, The Current Exploration Of Industry 5.0 Is Still In