Mariam Abed , Abdelkhalick Mohammad , Dragos Axinte , Andres Gameros , David Askew
{"title":"Digital-twin-assisted multi-stage machining of thin-wall structures using interchangeable robotic and human-assisted automation","authors":"Mariam Abed , Abdelkhalick Mohammad , Dragos Axinte , Andres Gameros , David Askew","doi":"10.1016/j.rcim.2025.103077","DOIUrl":"10.1016/j.rcim.2025.103077","url":null,"abstract":"<div><div>Interconnected intelligent systems in multi-stage smart machining environments are an advancing area of research, demonstrating many real-life opportunities that can benefit from the development and integration of cyber-physical systems into machining habitats, while different automation levels in industrial manufacturing sites call for flexibility of core strategies towards smart machining ecosystems. This article introduces a versatile and smart multi-stage machining environment for the controlled clamping and machining of low-rigidity structures in an interconnected cyber-physical factory. This is exemplified by a deformation-prone thin-wall workpiece, which undergoes controlled clamping, enabled by interchangeable robotic automation and automation via human-cyber-physical systems, as well as digital-twin-assisted corrective machining enabled by the swift estimation of workpiece deformations and multi-stage communication between machining habitats. The underlying digital twin presents a fast, lightweight simulation approach, based on a mass-spring-lattice model, allowing information flow from and to systems, which is utilized by the CNC machine as well as the interchangeable robot- and human-in-the-loop clamping enablers. By employing this controlled clamping approach workpiece deformations are aimed to be minimized. At the same time, a desired total clamping force is achieved in order to perform subsequent digital-twin-assisted machining corrections to reduce deformation-caused flatness errors. Ultimately, this article presents an intelligent multi-stage machining scenario where digital-twin enabled information moves along with thin-wall structures and branches out for knowledge-based control and corrections to robots, humans and CNC machines respectively, showcasing a real-life example for versatile, information-driven smart machining ecosystems.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"97 ","pages":"Article 103077"},"PeriodicalIF":9.1,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144296947","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wei Zhang , Yibing Li , Kaipu Wang , Wenjun Xu , Liang Gao
{"title":"A green and efficient disassembly line balancing with human-robot collaboration and destructive disassembly","authors":"Wei Zhang , Yibing Li , Kaipu Wang , Wenjun Xu , Liang Gao","doi":"10.1016/j.rcim.2025.103081","DOIUrl":"10.1016/j.rcim.2025.103081","url":null,"abstract":"<div><div>Human-robot collaboration combines the strengths of both humans and robots to enhance disassembly line efficiency. Considering the indivisibility and recovery value of certain components, this study incorporates destructive disassembly into a human-robot collaborative disassembly line. A mixed-integer linear programming model of the disassembly line balancing problem is constructed. The model accounts for task precedence relationships, task attributes, disassembly modes, human-robot collaboration, and the configuration of humans and robots. The objective is to minimize cycle time, smoothness index, and disassembly energy consumption while maximizing disassembly profit. The algorithm uses a three-layer encoding strategy based on task sequence, task operators, and disassembly modes, with an optimization-driven initialization to improve the initial solution quality. Five selection strategies and two neighborhood search strategies are designed, and during the iterative process, the strategy is dynamically adjusted through Q-learning to enhance both global search and local search capabilities. The effectiveness and superiority of the proposed algorithm are validated through three types of test case experiments, compared with the five latest algorithms. Finally, the model and algorithm are applied to a real-world laptop disassembly case. The results show that the introduction of collaborative robots in disassembly significantly reduces disassembly costs. Compared to manual disassembly, the cycle time of the disassembly line can be reduced by 24.39%, and idle time can be reduced by 33.64% in the human-robot collaborative disassembly mode. Compared to non-destructive disassembly, destructive disassembly can reduce energy consumption by 28.20%.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"97 ","pages":"Article 103081"},"PeriodicalIF":9.1,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144291028","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Bin Zi , Kai Tang , Yuan Li , Kai Feng , Yongkui Liu , Lihui Wang
{"title":"Coating defect detection in intelligent manufacturing: Advances, challenges, and future trends","authors":"Bin Zi , Kai Tang , Yuan Li , Kai Feng , Yongkui Liu , Lihui Wang","doi":"10.1016/j.rcim.2025.103079","DOIUrl":"10.1016/j.rcim.2025.103079","url":null,"abstract":"<div><div>Spraying is a critical surface treatment process in intelligent manufacturing, and coating quality directly affects product performance. Therefore, efficient, accurate, and intelligent coating defect detection is an essential technique to ensure product reliability. The past decade has witnessed rapid progress in coating defect detection techniques. However, most existing studies have focused on specific methods or application scenarios, and there is a lack of systematic reviews that provide a comprehensive overview of this particular research area. To fill this research gap, this paper systematically reviews recent advances in coating defect detection, which covers methods from physical property-based non-destructive testing to deep learning-based approaches. Their fundamental principles, applicability in intelligent manufacturing, and current research progress are examined, and key challenges and potential solutions are discussed. Furthermore, integration of advanced intelligent manufacturing technologies into coating defect detection systems is analyzed to enhance system-level digitalization, automation, and efficiency. Finally, future development trends are explored and analyzed, including collaborative perception, cross-modal fusion, and autonomous decision-making. It is expected that this review will help to advance and accelerate theoretical research and engineering applications in coating defect detection by providing researchers with a comprehensive understanding.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"97 ","pages":"Article 103079"},"PeriodicalIF":9.1,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144288823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Large and small-scale models’ fusion-driven proactive robotic manipulation control for human-robot collaborative assembly in industry 5.0","authors":"Dongxu Ma , Chao Zhang , Qingfeng Xu , Guanghui Zhou","doi":"10.1016/j.rcim.2025.103078","DOIUrl":"10.1016/j.rcim.2025.103078","url":null,"abstract":"<div><div>Human-robot collaborative (HRC) assembly has been popular by combining human creativity and dexterity with robotic precision for higher assembly efficiency and resilience in industry 5.0. Nevertheless, current HRC assembly systems rely predefined codes, limiting robot adaptability to dynamic and unstructured assembly environments. To bridge the gap, this paper proposes a novel proactive robotic manipulation control method for HRC assembly, which fully utilizes large-scale model (LSM) in cognitive computing and reasoning for dynamic robotic control path planning, and small-scale models (SSMs) in efficiently computing for dynamic robotic control demand perception and control constraints verification. Specifically, LSM, namely ChatGPT 4o, is deployed on the cloud to proactively generate robotic control constraints according to the robotic control demand derived from SSMs on the edge. Here, two kinds of SSMs are developed, including robotic control demands perception model and robotic control constraints verification model. For robotic control demands perception, an ensemble encoder model is proposed for ongoing human assembly action detection, on which a vision model and fine-tuned assembly instruction generation model are designed for assembly manipulation keypoints image and robot control instruction generation, serving as the input for LSM. For robotic control constraints verification, a digital twin model is used to verify the control constraints derived from LSM, where verified constraints are used for robotic control during assembly process. Finally, the feasibility and effectiveness of the proposed approach are demonstrated through experiments on an HRC assembly process, where over 99 % accuracy for human assembly action detection and 80 % task execution accuracy are conducted.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"97 ","pages":"Article 103078"},"PeriodicalIF":9.1,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144271506","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cheng Ren , Ming Li , Cailian Chen , Xinping Guan , George Q. Huang
{"title":"Multi-modal digital twins for industrial anomaly detection: Framework, method, and application","authors":"Cheng Ren , Ming Li , Cailian Chen , Xinping Guan , George Q. Huang","doi":"10.1016/j.rcim.2025.103068","DOIUrl":"10.1016/j.rcim.2025.103068","url":null,"abstract":"<div><div>Anomaly detection plays a key role in maintaining the reliable and stable operation of industrial systems, especially in high-reliability fields. Conventional single-modal data cannot provide comprehensive information about the detected object, resulting in false or missed detection. To address the challenges of complex anomaly patterns and heterogeneous data in industrial scenarios, we propose MMDT-IAD, a multi-modal digital twin (DT)-based anomaly detection framework that integrates edge–cloud collaboration. By lever- aging physical, geometric, visual, and semantic modalities, MMDT-IAD constructs a comprehensive virtual representation of monitored objects and enables real-time, scalable detection across distributed industrial environments. Next, to enable efficient fusion of heterogeneous DT modalities, we propose a One-Primary- Three-Auxiliary (1P3A) cross-modal decision fusion strategy. Finally, we apply the MMDT-IAD frame-work to the anomaly detection of aviation electrical connector pins, and present a detailed application process. The experimental results prove the effectiveness of the MMDT-IAD framework in detecting abnormal pins. Moreover, we discuss the generality of MMDT-IAD framework considering several common industrial anomalies. These results highlight the potential of MMDT-IAD framework and 1P3A method to significantly improve anomaly detection in other complex industrial scenarios.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"97 ","pages":"Article 103068"},"PeriodicalIF":9.1,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264044","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Duidi Wu , Pai Zheng , Qianyou Zhao , Shuo Zhang , Jin Qi , Jie Hu , Guo-Niu Zhu , Lihui Wang
{"title":"Empowering natural human–robot collaboration through multimodal language models and spatial intelligence: Pathways and perspectives","authors":"Duidi Wu , Pai Zheng , Qianyou Zhao , Shuo Zhang , Jin Qi , Jie Hu , Guo-Niu Zhu , Lihui Wang","doi":"10.1016/j.rcim.2025.103064","DOIUrl":"10.1016/j.rcim.2025.103064","url":null,"abstract":"<div><div>Industry 5.0 advocates human-centric smart manufacturing (HSM), with growing attention to proactive human-machine collaboration (HRC). Meanwhile, the rapid development of Multimodal large language models (MLLMs) and embodied intelligence is driving an unprecedented evolution. This work aims to leverage these opportunities to enhance robots’ learning and cognitive capabilities, enabling seamless and natural interaction. However, current research often overlooks human–robot symbiosis and lacks attention to specialized models and practical applications. This review adheres to a human-centric vision, taking language as the pivot to connect humans with large models. To our best knowledge, this is the first attempt to integrate HRC, MLLMs and embodied intelligence into a holistic view. The review first introduces representative foundation models to provide a comprehensive summary of state-of-the-art methods in the ”Perception-Cognition-Actuation” loop. It then discusses pathways and platforms for efficient spatial skills learning, followed by an analysis of four key questions from the ”Why, How, What, Where” perspectives. Finally, it highlights future challenges and potential research directions. It is hoped that this work can help fill the research gap between HRC and MLLMs, offering a systematic pathway for developing human-centered collaborative systems and promoting further exploration and innovation in this exciting and crucial field. The resources are available at: <span><span>https://github.com/WuDuidi/MLLM-HRC-Survey</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"97 ","pages":"Article 103064"},"PeriodicalIF":9.1,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144255301","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jiewu Leng , Keyou Zheng , Rongjie Li , Chong Chen , Baicun Wang , Qiang Liu , Xin Chen , Weiming Shen
{"title":"AIGC-empowered smart manufacturing: Prospects and challenges","authors":"Jiewu Leng , Keyou Zheng , Rongjie Li , Chong Chen , Baicun Wang , Qiang Liu , Xin Chen , Weiming Shen","doi":"10.1016/j.rcim.2025.103076","DOIUrl":"10.1016/j.rcim.2025.103076","url":null,"abstract":"<div><div>Generative AI (GenAI), the technology behind Artificial Intelligence Generated Content (AIGC), has emerged as a transformative technology in smart manufacturing. However, its full potential and integration within manufacturing processes remain unexplored. This paper presents a comprehensive framework that aligns a GenAI-centered approach with Product Lifecycle Management (PLM), systematically examining the AIGC landscape and its applications across various manufacturing phases. To ensure accuracy and relevance, a human-in-the-loop pipeline is employed to curate and analyze cutting-edge research. Key contributions of this study include: 1) a holistic perspective on AIGC-empowered smart manufacturing, 2) an in-depth analysis of the current technological landscape, and 3) the identification of critical research challenges and future directions. Additionally, the paper considers Industry 5.0 principles, emphasizing human-centricity, sustainability, and resilience. By fostering discussion and collaboration, this review aims to advance innovation and unlock the full potential of AIGC in smart manufacturing.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"97 ","pages":"Article 103076"},"PeriodicalIF":9.1,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144240880","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shengpeng Fu , Zhiliang Chen , Jibin Zhao , Renbo Xia , Tao Zhang
{"title":"Robotic hand–eye calibration utilizing limited geometric features object","authors":"Shengpeng Fu , Zhiliang Chen , Jibin Zhao , Renbo Xia , Tao Zhang","doi":"10.1016/j.rcim.2025.103066","DOIUrl":"10.1016/j.rcim.2025.103066","url":null,"abstract":"<div><div>Hand–eye calibration is essential for intelligent robots to accurately perceive their environment, primarily focused on determining the transformation matrix between the robot flange coordinate system and the 3D sensor coordinate system. However, current robot hand–eye calibration methods heavily depend on costly specialized calibration objects, such as calibration boards and spheres, which complicate the calibration process and hinder the robot’s ability to perform self-calibration at any time and in any location. To address this issue, this paper proposes a novel robot hand–eye calibration method that utilizes the reconstruction of common objects with limited geometric features. Specifically, a point cloud feature description method that integrates eigenvalue entropy is introduced to extract feature points from multi-pose point clouds of these objects. Subsequently, a registration strategy based on the random sampling consensus of partitioned point clouds is employed for the coarse registration of the point cloud, estimating the initial hand–eye relationship, followed by iterative optimization through fine registration to determine precise hand–eye parameters. Extensive experimental results demonstrate that the proposed method offers a simple and efficient calibration process, eliminates reliance on specialized calibration objects, and achieves calibration accuracy comparable to that of high-precision calibration boards, thereby showcasing the advantages of the proposed approach.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"97 ","pages":"Article 103066"},"PeriodicalIF":9.1,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144240881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A study on the predictive capabilities of digital twins for object transfers in a remanufacturing demonstration environment","authors":"Jan-Felix Klein, Kai Furmans","doi":"10.1016/j.rcim.2025.103063","DOIUrl":"10.1016/j.rcim.2025.103063","url":null,"abstract":"<div><div>Remanufacturing processes are characterized by high uncertainty due to the variable conditions of returned cores, which makes automation challenging and necessitates considerable process flexibility. Industry 4.0 methods are often proposed to mitigate this uncertainty, yet real-world demonstrations that validate their effectiveness remain limited. This study addresses this research gap by presenting a flexible, digital-twin driven object transfer system implemented in a remanufacturing demonstration environment. The system under consideration involves an autonomous mobile robot that docks at multiple stationary transfer points to transfer unique starter motor cores without the use of load carriers. Since the object transfer process is probabilistic, virtual models are employed in a physics-simulated environment to predict object-specific pre-transfer states, defined as the state an object before the transfer is executed. The predictive capabilities of the digital twins are evaluated through an extensive experimental study, involving a series of physical and virtual experiments conducted on 37 unique starter motor cores.</div><div>The study includes calibration experiments to tune the virtual models, followed by large-scale virtual experiments to estimate the probability of successful transfer for a fixed set of pre-transfer states. A custom method is applied to determine the most promising pre-transfer state for each starter motor core. Final validation results highlight the effectiveness of the approach and indicate that increased modeling efforts reveal inherent limitations in the predictive accuracy of the virtual models. Sources of error, including mass distribution approximations and simulation inaccuracies, are discussed, and directions for future improvements are outlined.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"97 ","pages":"Article 103063"},"PeriodicalIF":9.1,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144221679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Evan Rolland , Yasser Krim , Ahmed Joubair , Ilian A. Bonev , Evan Jones , Pengpeng Zhang , Cheng Sun , Nanzhu Zhao
{"title":"Novel calibration method for robotic bottom-up vat polymerization additive manufacturing systems","authors":"Evan Rolland , Yasser Krim , Ahmed Joubair , Ilian A. Bonev , Evan Jones , Pengpeng Zhang , Cheng Sun , Nanzhu Zhao","doi":"10.1016/j.rcim.2025.103059","DOIUrl":"10.1016/j.rcim.2025.103059","url":null,"abstract":"<div><div>This article presents a new affordable calibration method for a 7-axis robotic system used for vat polymerization 3D printing. The method employs three metrology elements: a calibration robot end-effector with three precision balls, a measurement probe composed of three linear gauges, and, notably, a kinematic coupling allowing the precise positioning of the probe onto the resin tank in three locations. The robotic system comprises a Mecademic Meca500 6-axis industrial robot mounted on a Zaber X-LRQ300AP linear guide. The calibration method consists of automatically aligning the centers of each of the three precision balls with the probe origin. This alignment is performed with different robot joint angles and linear guide displacements, and for all three locations of the probe. After calibration, the relative accuracy of the 7-axis robotic system with respect to the resin tank, as validated using a laser tracker, is improved from 1.272 mm to 0.271 mm, which is comparable to what can be achieved with significantly more expensive metrology equipment.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"97 ","pages":"Article 103059"},"PeriodicalIF":9.1,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144212585","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}