Related references
Note: Only part of the references are listed.
Article
Computer Science, Information Systems
Kunyu Peng et al.
Summary: This paper focuses on occlusion problem in skeleton action recognition and proposes a benchmark for partially occluded body poses in one-shot skeleton-based action recognition. It also introduces a new transformer-based model, Trans4SOAR, which leverages three data streams and mixed attention fusion mechanism to alleviate the adverse effects caused by occlusions.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Engineering, Industrial
Chao Zhang et al.
Summary: Developing intelligent machine tools is crucial for manufacturing enterprises to achieve intelligent manufacturing in Industry 4.0. However, most current approaches focus on single digital twin machine tools with limited intelligence. This paper proposes a novel framework that integrates digital twin with multi-access edge computing (MEC) to construct a knowledge-sharing intelligent machine tool swarm with secure and ultra-low latency performance.
JOURNAL OF MANUFACTURING SYSTEMS
(2023)
Review
Computer Science, Artificial Intelligence
Chao Zhang et al.
Summary: Industry 5.0 complements Industry 4.0 by emphasizing research and innovation as drivers towards a sustainable and human-centric industry. Human-centric smart manufacturing (HSM) utilizes human flexibility, machine precision, and new-generation information technologies to construct a super smart and resilient manufacturing system. This paper conducts a systematic literature review to identify promising research topics and highlights the key enablers, applications, and challenges of HSM.
ADVANCED ENGINEERING INFORMATICS
(2023)
Article
Computer Science, Interdisciplinary Applications
Chao Zhang et al.
Summary: This paper proposes a novel human-cyber-physical assembly system (HCPaS) framework, which combines the powerful perception and control capacity of digital twin with the virtual-reality interaction capacity of augmented reality (AR) to achieve a safe and efficient HRC environment. The framework utilizes a deep learning-enabled fusion method to recognize robot poses and part information, providing smart guidance for manual work to avoid human errors.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2023)
Review
Engineering, Industrial
Alexandre Dolgui et al.
Summary: Assembly systems are facing challenges in the era of mass customization and Industry 4.0, but the adoption of I4.0 technologies is seen as a solution. However, there is a lack of understanding on how these technologies impact decision-making areas within assembly systems.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2022)
Article
Engineering, Manufacturing
Sichao Liu et al.
Summary: This article investigates multimodal data-driven robot control for human-robot collaborative assembly. A programming-free human-robot interface is designed to fuse multimodal human commands, and deep learning is explored for accurate translation of brainwave command phrases into robot commands. Event-driven function blocks are used for high-level robot control, and a case study is conducted to demonstrate the effectiveness of the system.
JOURNAL OF MANUFACTURING SCIENCE AND ENGINEERING-TRANSACTIONS OF THE ASME
(2022)
Article
Engineering, Industrial
Jinfeng Liu et al.
Summary: The construction method of digital twin process model (DTPM) proposed in this paper addresses the inefficiency of existing process design methods in handling machining plan changes induced by unpredictable events. A case study on a complex machined part showed a 7% reduction in processing time and a 40% improvement in processing stability, demonstrating the effectiveness of the proposed method.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2022)
Article
Computer Science, Interdisciplinary Applications
Rong Zhang et al.
Summary: The assembly process of high precision products requires human-robot collaboration to optimize efficiency, but the unpredictability of human behavior poses a challenge. A human-robot collaborative reinforcement learning algorithm has been proposed and validated through experimental analysis to optimize task allocation in assembly processes.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2022)
Article
Engineering, Industrial
Pai Zheng et al.
Summary: This paper proposes a visual reasoning-based approach for mutual-cognitive human-robot collaboration (HRC), which integrates robotic and human cognitions efficiently. It establishes a domain-specific HRC knowledge graph and perceives the holistic manufacturing scene as a temporal graph using visual sensors. Collaborative modes with similar instructions can be inferred by graph embedding, and mutual-cognitive decisions are implemented in the Augmented Reality execution loop for intuitive HRC support.
CIRP ANNALS-MANUFACTURING TECHNOLOGY
(2022)
Review
Engineering, Industrial
Anil Kumar Inkulu et al.
Summary: The paper discusses the application of human-robot collaboration in manufacturing automation in the Industry 4.0 era, analyzing various HRC techniques and key challenges, and classifying and discussing different modes of collaboration.
INDUSTRIAL ROBOT-THE INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH AND APPLICATION
(2022)
Article
Engineering, Industrial
Rong Zhang et al.
Summary: This research presents a method for human-robot collaborative assembly, representing the assembly task of complex products using part-behavior assembly and/or graph based on process requirements. In dynamic scenes, the combination of a human behavior prediction network based on self-attention and the robustness of Soft Actor-Critic algorithm enhances the robot's autonomous decision-making ability. Experimental analysis verifies the effectiveness of the method and demonstrates the feasibility of reinforcement learning for adaptive decision-making in human-robot collaboration environments.
JOURNAL OF MANUFACTURING SYSTEMS
(2022)
Article
Computer Science, Information Systems
Xiaoguang Zhu et al.
Summary: Action recognition is a highly relevant topic in computer vision with wide applications in vision systems. In this study, a multi-modality feature fusion network is proposed to combine the modalities of skeleton sequence and RGB frame, which reduces the complexity while retaining complementary information. The network employs a two-stage fusion framework to explore the correspondence between the two modalities. Experimental results on two benchmarks demonstrate competitive performance compared with state-of-the-art methods.
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
(2022)
Article
Automation & Control Systems
Shufei Li et al.
Summary: This article proposes a multimodal transfer-learning-enabled action prediction approach, serving as a prerequisite for achieving proactive human-robot collaborative assembly. By leveraging intelligent action recognition and transfer-learning models, ongoing human actions can be predicted and rapidly converted into industrial assembly operations. A dynamic decision-making mechanism allows mobile robots to assist operators in a proactive manner. Experimental results demonstrate that the proposed approach outperforms other state-of-the-art methods in efficient action prediction.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2022)
Article
Computer Science, Interdisciplinary Applications
Chengxi Li et al.
Summary: This research proposes a novel multi-robot collaborative manufacturing system that combines augmented reality and digital twin techniques. The system visualizes digital twins of industrial robots and incorporates a multi-robot communication mechanism to enable human-in-the-loop control. Experimental results demonstrate that the system can efficiently handle multi-robot teleoperation tasks and has the potential to be applied in other complex manufacturing scenarios.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2022)
Article
Computer Science, Artificial Intelligence
Yaqian Zhang et al.
Summary: This paper proposes a human-object integrated approach for context-aware assembly intention recognition in human-robot collaborative (HRC) assembly. By integrating assembly action recognition and assembly part recognition, the accuracy of operator's intention recognition is improved. Experimental results show the feasibility and effectiveness of the proposed approach in accurately recognizing operator's intentions in complex and flexible assembly environments.
ADVANCED ENGINEERING INFORMATICS
(2022)
Article
Computer Science, Interdisciplinary Applications
Jianjing Zhang et al.
Summary: This paper presents a hybrid approach to context-aware human action recognition and prediction based on the integration of a convolutional neural network (CNN) and variable-length Markov modeling (VMM) to improve operational flexibility and productivity in human-robot collaboration.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2021)
Article
Computer Science, Interdisciplinary Applications
Hongyi Liu et al.
Summary: Recent advancements in human-robot collaboration have led to the development of a context awareness-based collision-free system that ensures both human safety and assembly efficiency. This system can plan robotic paths to avoid collisions with human operators while reaching target positions in a timely manner, and can also recognize human operators' poses with low computational costs to further improve assembly efficiency. The system incorporates a collision sensing module with sensor calibration algorithms and a transfer learning-based human pose recognition algorithm to enhance overall system performance.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2021)
Article
Robotics
H. Abdelkawy et al.
Summary: This paper proposes a novel hybrid framework for a robotic system to recognize human daily activities in the environment. The low-level utilizes a Spatio-Temporal Joint based Convolutional Neural Network, while the high-level employs representation and inference services based on Narrative Knowledge Representation Language. Experimental results validate the effectiveness of this approach.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2021)
Article
Engineering, Electrical & Electronic
Xu Weiyao et al.
Summary: This paper proposes a multi-modal action recognition model based on Bilinear Pooling and Attention Network, which effectively fuses RGB and skeleton features, leading to improved performance in RGB-D action recognition compared to state-of-the-art methods.
IEEE SENSORS JOURNAL
(2021)
Article
Automation & Control Systems
Xianhe Wen et al.
ASSEMBLY AUTOMATION
(2020)
Article
Engineering, Industrial
Qianqian Xiong et al.
JOURNAL OF MANUFACTURING SYSTEMS
(2020)
Article
Engineering, Industrial
Chengjun Chen et al.
JOURNAL OF MANUFACTURING SYSTEMS
(2020)
Article
Computer Science, Information Systems
Yang Xiao et al.
INFORMATION SCIENCES
(2019)
Article
Engineering, Industrial
L. Wang et al.
CIRP ANNALS-MANUFACTURING TECHNOLOGY
(2019)
Article
Engineering, Industrial
Peng Wang et al.
CIRP ANNALS-MANUFACTURING TECHNOLOGY
(2018)
Article
Computer Science, Artificial Intelligence
Jun Liu et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2018)
Article
Computer Science, Artificial Intelligence
Gul Varol et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2018)
Article
Engineering, Industrial
Jinjiang Wang et al.
JOURNAL OF MANUFACTURING SYSTEMS
(2018)
Article
Computer Science, Interdisciplinary Applications
Panagiota Tsarouchi et al.
INTERNATIONAL JOURNAL OF COMPUTER INTEGRATED MANUFACTURING
(2017)
Article
Engineering, Industrial
Hongyi Liu et al.
JOURNAL OF MANUFACTURING SYSTEMS
(2017)
Article
Engineering, Industrial
Xi Vincent Wang et al.
CIRP ANNALS-MANUFACTURING TECHNOLOGY
(2017)
Review
Computer Science, Interdisciplinary Applications
Panagiota Tsarouchi et al.
INTERNATIONAL JOURNAL OF COMPUTER INTEGRATED MANUFACTURING
(2016)
Article
Computer Science, Hardware & Architecture
Zhengyou Zhang
Article
Computer Science, Artificial Intelligence
Stefan Hinterstoisser et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2012)
