Due to the complex structures and heterogeneous information inherent in End-of-Life (EOL) products, determining optimal disassembly solutions based on Human-Robot Collaboration (HRC) remains a challenging task. As structural and functional uncertainties in EOL products increase, traditional disassembly approaches struggle to meet the practical disassembly demands. Although various algorithms have been proposed for optimizing disassembly processes, significant challenges persist. These include the limited adaptability of existing models and difficulties in representing dynamic structured information effectively. To address these challenges, this study proposes a novel method combining knowledge graph-driven neural networks with an information decomposition module. This mechanism enables the network to discover structural semantic information and relational connections, facilitating the prediction of optimal disassembly strategies and enhancing the process reasoning capability of EOL product data and knowledge. Similarly, the proposed method provides reliable decision support for HRC disassembly task allocations and tool selections, enabling efficient and safe disassembly operations within complex disassembly processes. Finally, we demonstrate the method’s efficacy by using an example of an EOL battery pack, reasoning optimal disassembly strategies and potential process relations in the complex HRC disassembly scenario.
{"title":"Knowledge graph-driven process reasoning of human-robot collaborative disassembly strategy for end-of-life products","authors":"Jinhua Xiao , Zhiwen Zhang , Yu Zheng , Peng Wu , Sergio Terzi , Marco Macchi","doi":"10.1016/j.rcim.2025.103211","DOIUrl":"10.1016/j.rcim.2025.103211","url":null,"abstract":"<div><div>Due to the complex structures and heterogeneous information inherent in End-of-Life (EOL) products, determining optimal disassembly solutions based on Human-Robot Collaboration (HRC) remains a challenging task. As structural and functional uncertainties in EOL products increase, traditional disassembly approaches struggle to meet the practical disassembly demands. Although various algorithms have been proposed for optimizing disassembly processes, significant challenges persist. These include the limited adaptability of existing models and difficulties in representing dynamic structured information effectively. To address these challenges, this study proposes a novel method combining knowledge graph-driven neural networks with an information decomposition module. This mechanism enables the network to discover structural semantic information and relational connections, facilitating the prediction of optimal disassembly strategies and enhancing the process reasoning capability of EOL product data and knowledge. Similarly, the proposed method provides reliable decision support for HRC disassembly task allocations and tool selections, enabling efficient and safe disassembly operations within complex disassembly processes. Finally, we demonstrate the method’s efficacy by using an example of an EOL battery pack, reasoning optimal disassembly strategies and potential process relations in the complex HRC disassembly scenario.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"99 ","pages":"Article 103211"},"PeriodicalIF":11.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145784996","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}
Pub Date : 2026-06-01Epub Date: 2025-12-13DOI: 10.1016/j.rcim.2025.103203
Hongquan Gui , Ming Li
Modeling human behavior is paramount in the process of human-robot interaction (HRI). Human motion during HRI is uncertain. Even when the same individual performs the same action, it is impossible to ensure that the motion trajectory will be identical every time. These factors make modeling human behavior extremely challenging. Beyond human uncertainty, there are dynamic temporal spatial dependencies in HRI. Effectively capturing uncertainty while fully integrating temporal spatial features presents a significant challenge. Moreover, representing human behavior solely through human skeleton is insufficient. Recently, human digital twins have been developed to represent human geometry. However, current human digital twins are not well-suited for dynamic HRI scenarios, as they struggle to accurately depict high-dimensional human parameters, leading to issues such as nonlinear mapping and joint drift. In summary, existing methods find it difficult to address the human uncertainty, the temporal spatial dependencies, and the high-dimensional human parameters. To address the above challenges, this study proposes a temporal spatial human digital twin (TSHDT) for modeling human behavior in HRI. The TSHDT is based on predicted human skeletons and integrates forward and inverse kinematics along with diffusion prior distribution to represent high-dimensional human parameters, thus preventing joint drift and nonlinear mapping between joints. In developing the TSHDT, we introduce the human robot temporal spatial (HRTS) diffusion model to mitigate the uncertainty in human motion. The unique diffusion and denoising processes of the HRTS diffusion model can effectively submerge uncertainty in noise and accurately predict human motion during subsequent denoising steps. To ensure that the denoising process favors accuracy over diversity, we propose the temporal spatial fusion graph convolutional network (TSFGCN) to capture temporal spatial features between humans and robots, embedding them into the HRTS diffusion model. Finally, the effectiveness of the TSHDT was validated via predictive collision detection in human-robot fabric cutting experiments. Results demonstrate that the proposed method accurately models human behavior in collision detection experiments, achieving outstanding F1 scores.
{"title":"A temporal spatial human digital twin approach for modeling human behavior with uncertainty","authors":"Hongquan Gui , Ming Li","doi":"10.1016/j.rcim.2025.103203","DOIUrl":"10.1016/j.rcim.2025.103203","url":null,"abstract":"<div><div>Modeling human behavior is paramount in the process of human-robot interaction (HRI). Human motion during HRI is uncertain. Even when the same individual performs the same action, it is impossible to ensure that the motion trajectory will be identical every time. These factors make modeling human behavior extremely challenging. Beyond human uncertainty, there are dynamic temporal spatial dependencies in HRI. Effectively capturing uncertainty while fully integrating temporal spatial features presents a significant challenge. Moreover, representing human behavior solely through human skeleton is insufficient. Recently, human digital twins have been developed to represent human geometry. However, current human digital twins are not well-suited for dynamic HRI scenarios, as they struggle to accurately depict high-dimensional human parameters, leading to issues such as nonlinear mapping and joint drift. In summary, existing methods find it difficult to address the human uncertainty, the temporal spatial dependencies, and the high-dimensional human parameters. To address the above challenges, this study proposes a temporal spatial human digital twin (TSHDT) for modeling human behavior in HRI. The TSHDT is based on predicted human skeletons and integrates forward and inverse kinematics along with diffusion prior distribution to represent high-dimensional human parameters, thus preventing joint drift and nonlinear mapping between joints. In developing the TSHDT, we introduce the human robot temporal spatial (HRTS) diffusion model to mitigate the uncertainty in human motion. The unique diffusion and denoising processes of the HRTS diffusion model can effectively submerge uncertainty in noise and accurately predict human motion during subsequent denoising steps. To ensure that the denoising process favors accuracy over diversity, we propose the temporal spatial fusion graph convolutional network (TSFGCN) to capture temporal spatial features between humans and robots, embedding them into the HRTS diffusion model. Finally, the effectiveness of the TSHDT was validated via predictive collision detection in human-robot fabric cutting experiments. Results demonstrate that the proposed method accurately models human behavior in collision detection experiments, achieving outstanding F1 scores.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"99 ","pages":"Article 103203"},"PeriodicalIF":11.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145731184","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}
Pub Date : 2026-06-01Epub Date: 2025-12-22DOI: 10.1016/j.rcim.2025.103208
Duidi Wu , Qianyou Zhao , Yuliang Shen , Junlai Li , Pai Zheng , Jin Qi , Jie Hu
Industrial assembly represents a core of modern manufacturing but poses significant challenges to the reliability and adaptability of robot systems. As manufacturing shifts toward intelligent production, there is an urgent need for efficient human-to-robot skill transfer methods for mutual cognition. However, current embodied intelligence research has primarily focused on household tasks, while human-level performance in dexterous and long-horizon tasks remains largely unexplored within real-world industrial applications. To bridge this gap, we propose a skill transfer framework and establish a contact-rich assembly benchmark. It integrates an MR-assisted digital twin system for low-cost and diverse demonstrations, an end-to-end generative visuomotor imitation learning policy for continuous action, and primitive skills covering industrially-inspired tasks such as peg insertion, gear meshing, and disassembly. Experiments across six tasks demonstrate high success rates and robust positional generalization. This study explores a novel pathway, it is hoped that it will provide valuable insights for future human–robot collaboration, and serve as a critical precursor for the integration of physical intelligence with generative AI. The project website is available at: https://h2r-mrsta.github.io/.
{"title":"A mixed reality-assisted human-to-robot skill transfer approach for contact-rich assembly via visuomotor primitives","authors":"Duidi Wu , Qianyou Zhao , Yuliang Shen , Junlai Li , Pai Zheng , Jin Qi , Jie Hu","doi":"10.1016/j.rcim.2025.103208","DOIUrl":"10.1016/j.rcim.2025.103208","url":null,"abstract":"<div><div>Industrial assembly represents a core of modern manufacturing but poses significant challenges to the reliability and adaptability of robot systems. As manufacturing shifts toward intelligent production, there is an urgent need for efficient human-to-robot skill transfer methods for mutual cognition. However, current embodied intelligence research has primarily focused on household tasks, while human-level performance in dexterous and long-horizon tasks remains largely unexplored within real-world industrial applications. To bridge this gap, we propose a skill transfer framework and establish a contact-rich assembly benchmark. It integrates an MR-assisted digital twin system for low-cost and diverse demonstrations, an end-to-end generative visuomotor imitation learning policy for continuous action, and primitive skills covering industrially-inspired tasks such as peg insertion, gear meshing, and disassembly. Experiments across six tasks demonstrate high success rates and robust positional generalization. This study explores a novel pathway, it is hoped that it will provide valuable insights for future human–robot collaboration, and serve as a critical precursor for the integration of physical intelligence with generative AI. The project website is available at: <span><span>https://h2r-mrsta.github.io/</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"99 ","pages":"Article 103208"},"PeriodicalIF":11.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145813784","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}
As an advanced manufacturing paradigm, 3D printing offers significant opportunities for smart manufacturing (SM). However, the prevalence of data silos in its production lines frequently hinders effective process analysis and decision-making. While large language models (LLMs) possess powerful analytical capabilities, their reliability in industrial scenarios is constrained by hallucinations and a disconnection from real-time operational data. Dynamic manufacturing knowledge graphs (MKGs), functioning as structured databases, can integrate structured and unstructured manufacturing data while providing LLMs with real-time data support. Meanwhile, the development of retrieval-augmented generation (RAG) and AI-Agent technologies provides a feasible pathway for the industrial application of LLMs. This study proposes an end-to-end framework ranging from knowledge integration to 3D printing production line applications to enable reliable LLM-driven SM. Firstly, leveraging the semantic analysis capabilities of LLMs, production data and manufacturing knowledge are integrated into a dynamic MKG. Subsequently, an advanced temporal graph network (TGN) model is developed for representation learning on the dynamic MKG, forming the retrieval foundation of an RAG system. A closed-loop manufacturing logic tailored to 3D printing production lines and a “semantic-to-structured” workflow for anomaly analysis were proposed. Finally, an AI-Agent system and a prototype software platform have been developed, and a case study on a laboratory 3D printing production line has been conducted to evaluate the TGN model’s performance and the AI-Agent system’s effectiveness. The results indicate that the dynamic MKG enables continuous learning for SM and provides industries with robust AI-driven data support. The TGN model significantly outperforms baseline models, yielding higher-quality dynamic embeddings for downstream knowledge retrieval tasks. Moreover, the AI-Agent system offers SM reliable intelligent analysis and decision support in 3D printing production lines.
{"title":"3DprintMIND: An AI-Agent system using large language models and dynamic manufacturing knowledge graphs for smart manufacturing","authors":"Laiyi Li, Yongwen Zhang, Inno Lorren Désir Makanda, Pingyu Jiang","doi":"10.1016/j.rcim.2025.103214","DOIUrl":"10.1016/j.rcim.2025.103214","url":null,"abstract":"<div><div>As an advanced manufacturing paradigm, 3D printing offers significant opportunities for smart manufacturing (SM). However, the prevalence of data silos in its production lines frequently hinders effective process analysis and decision-making. While large language models (LLMs) possess powerful analytical capabilities, their reliability in industrial scenarios is constrained by hallucinations and a disconnection from real-time operational data. Dynamic manufacturing knowledge graphs (MKGs), functioning as structured databases, can integrate structured and unstructured manufacturing data while providing LLMs with real-time data support. Meanwhile, the development of retrieval-augmented generation (RAG) and AI-Agent technologies provides a feasible pathway for the industrial application of LLMs. This study proposes an end-to-end framework ranging from knowledge integration to 3D printing production line applications to enable reliable LLM-driven SM. Firstly, leveraging the semantic analysis capabilities of LLMs, production data and manufacturing knowledge are integrated into a dynamic MKG. Subsequently, an advanced temporal graph network (TGN) model is developed for representation learning on the dynamic MKG, forming the retrieval foundation of an RAG system. A closed-loop manufacturing logic tailored to 3D printing production lines and a “semantic-to-structured” workflow for anomaly analysis were proposed. Finally, an AI-Agent system and a prototype software platform have been developed, and a case study on a laboratory 3D printing production line has been conducted to evaluate the TGN model’s performance and the AI-Agent system’s effectiveness. The results indicate that the dynamic MKG enables continuous learning for SM and provides industries with robust AI-driven data support. The TGN model significantly outperforms baseline models, yielding higher-quality dynamic embeddings for downstream knowledge retrieval tasks. Moreover, the AI-Agent system offers SM reliable intelligent analysis and decision support in 3D printing production lines.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"99 ","pages":"Article 103214"},"PeriodicalIF":11.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145883838","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}
Pub Date : 2026-06-01Epub Date: 2025-11-29DOI: 10.1016/j.rcim.2025.103188
Baicheng Bian , Long Chen , Zongwang Han , Shiqing Wu , WeiDong Li , Hongguang Chen
Real-time surface defect detection in steel strips requires high accuracy under computational constraints. Existing methods often struggle to detect low-contrast defects in complex backgrounds while maintaining computational efficiency. This paper proposes MSR-Det, a lightweight network built on a multi-scale semantic refinement framework to address this challenge. The core innovations include: a Hierarchical Texture Enhancement Module (HTEM) that strengthens discriminative textural patterns, a Specific Cross-Level Interaction Module (SCLIM) that facilitates granular feature fusion across network depths, and a Feature Enhancement Module (FEM) that refines defect representations through deep-to-shallow semantic guidance. The architecture further incorporates two key modules: a Lightweight Large-Kernel Bottleneck Module (LLKBM) for efficient receptive field expansion, and an Adaptive Gating Spatial Pyramid Pooling (AGSPP) for dynamic multi-scale context integration. Extensive experiments on NEU-DET, GC10-DET, and our industrial SS-DET dataset demonstrate that MSR-Det achieves state-of-the-art performance of 86.6% Mean Average Precision at 50% Intersection over Union () on SS-DET with only 5.0M parameters, also attaining a real-time speed of 180 FPS. This work provides a robust and practical solution for automated visual inspection in industrial settings, effectively balancing high precision with operational efficiency.
{"title":"A lightweight detection network integrating multi-scale semantic refinement for steel strip defects","authors":"Baicheng Bian , Long Chen , Zongwang Han , Shiqing Wu , WeiDong Li , Hongguang Chen","doi":"10.1016/j.rcim.2025.103188","DOIUrl":"10.1016/j.rcim.2025.103188","url":null,"abstract":"<div><div>Real-time surface defect detection in steel strips requires high accuracy under computational constraints. Existing methods often struggle to detect low-contrast defects in complex backgrounds while maintaining computational efficiency. This paper proposes MSR-Det, a lightweight network built on a multi-scale semantic refinement framework to address this challenge. The core innovations include: a Hierarchical Texture Enhancement Module (HTEM) that strengthens discriminative textural patterns, a Specific Cross-Level Interaction Module (SCLIM) that facilitates granular feature fusion across network depths, and a Feature Enhancement Module (FEM) that refines defect representations through deep-to-shallow semantic guidance. The architecture further incorporates two key modules: a Lightweight Large-Kernel Bottleneck Module (LLKBM) for efficient receptive field expansion, and an Adaptive Gating Spatial Pyramid Pooling (AGSPP) for dynamic multi-scale context integration. Extensive experiments on NEU-DET, GC10-DET, and our industrial SS-DET dataset demonstrate that MSR-Det achieves state-of-the-art performance of 86.6% Mean Average Precision at 50% Intersection over Union (<span><math><msub><mrow><mtext>mAP</mtext></mrow><mrow><mn>50</mn></mrow></msub></math></span>) on SS-DET with only 5.0M parameters, also attaining a real-time speed of 180 FPS. This work provides a robust and practical solution for automated visual inspection in industrial settings, effectively balancing high precision with operational efficiency.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"99 ","pages":"Article 103188"},"PeriodicalIF":11.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145614038","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}
Pub Date : 2026-06-01Epub Date: 2025-12-23DOI: 10.1016/j.rcim.2025.103213
Ruihao Kang , Junshan Hu , Zhengping Li , Liangxiang Wang , Jincheng Yang , Wei Tian
Digital Twin (DT) technology is pushing manufacturing toward higher intelligence and adaptability. However, existing DT modeling methods still rely heavily on customization, lacking universality and scalability for assembly-oriented manufacturing systems. To address this limitation, this paper proposes a modular DT control framework that couples graphical interaction with reusable functional modules. Based on the classical five-dimensional DT model, the virtual entity is refined into geometric and physical models, and the service system is expanded into behavior and task models, enabling a clearer description and direct correspondence between system structure and operational logic. A behavior-oriented modeling workflow and a data-mapping mechanism are established to enhance scenario adaptability and reduce modeling effort. A graphical DT modeling platform is developed on top of this framework. Multiple robotic manufacturing prototypes, including robotic drilling, robotic gluing, and hybrid drilling systems, are constructed to assess the generality and reconfigurability of the proposed approach. A drilling experiment is performed on the robotic drilling system to validate the DT-based control execution mechanism. The resulting holes exhibit an average positioning error of 0.23 mm and a diameter error of 0.012 mm, both meeting aerospace drilling requirements. This confirms that virtual task commands can be accurately executed on physical system under the proposed DT framework. Overall, the DT prototype implementations and drilling experiment jointly verify the scalability of the framework and its DT-based control capability, providing a practical approach for the rapid development and deployment of DT prototypes in aircraft assembly systems.
{"title":"A digital twin modeling framework with graphical software for rapid development of aircraft assembly systems","authors":"Ruihao Kang , Junshan Hu , Zhengping Li , Liangxiang Wang , Jincheng Yang , Wei Tian","doi":"10.1016/j.rcim.2025.103213","DOIUrl":"10.1016/j.rcim.2025.103213","url":null,"abstract":"<div><div>Digital Twin (DT) technology is pushing manufacturing toward higher intelligence and adaptability. However, existing DT modeling methods still rely heavily on customization, lacking universality and scalability for assembly-oriented manufacturing systems. To address this limitation, this paper proposes a modular DT control framework that couples graphical interaction with reusable functional modules. Based on the classical five-dimensional DT model, the virtual entity is refined into geometric and physical models, and the service system is expanded into behavior and task models, enabling a clearer description and direct correspondence between system structure and operational logic. A behavior-oriented modeling workflow and a data-mapping mechanism are established to enhance scenario adaptability and reduce modeling effort. A graphical DT modeling platform is developed on top of this framework. Multiple robotic manufacturing prototypes, including robotic drilling, robotic gluing, and hybrid drilling systems, are constructed to assess the generality and reconfigurability of the proposed approach. A drilling experiment is performed on the robotic drilling system to validate the DT-based control execution mechanism. The resulting holes exhibit an average positioning error of 0.23 mm and a diameter error of 0.012 mm, both meeting aerospace drilling requirements. This confirms that virtual task commands can be accurately executed on physical system under the proposed DT framework. Overall, the DT prototype implementations and drilling experiment jointly verify the scalability of the framework and its DT-based control capability, providing a practical approach for the rapid development and deployment of DT prototypes in aircraft assembly systems.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"99 ","pages":"Article 103213"},"PeriodicalIF":11.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145823074","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}
Pub Date : 2026-06-01Epub Date: 2025-12-13DOI: 10.1016/j.rcim.2025.103206
Weimin Jing , Yong Yan , Yonghui Zhang , Xiang Ji , Wen Huang , Youling Chen , Huan Zhang
In the context of cloud manufacturing service, scheduling manufacturing tasks is a crucial area of research because it directly influences service quality and efficiency. As intelligent manufacturing technologies advance, edge manufacturing service providers have gained increasingly flexible ability, enabling them to adjust local production schedules to adapt cloud manufacturing tasks. However, because local manufacturing information is private, traditional centralized cloud manufacturing scheduling methods cannot fully leverage edge flexibility to collaboratively schedule multi-source manufacturing tasks (including both cloud manufacturing tasks and local tasks of edge service providers) without risking the disclosure of sensitive information, thereby limiting improvements in both performance and efficiency of cloud manufacturing service. Therefore, we propose a privacy-preserving cloud-edge collaborative decision-making approach based on auction theory to schedule multi-source manufacturing tasks. First, a mathematical model that accounts for the objectives of both service providers and demanders is established to characterize the collaborative scheduling of multi-sourced tasks. Subsequently, a cloud-edge collaborative scheduling decision framework is introduced. Building upon this, a multi-stage scheduling method based on combinatorial iterative auctions is proposed, featuring novel bidding with a flexible execution timeline and distributed winner determination process incorporating bid consolidation mechanisms to enhance the efficiency of cloud-edge collaborative decision. Finally, to validate the superiority of the proposed method, computational experiments are conducted, comparing it with traditional centralized manufacturing task scheduling methods. The results present that the proposed method not only completes cloud manufacturing tasks within a relatively shorter makespan but also provides higher-value manufacturing services to demanders. Moreover, as the cloud manufacturing task load increases, this advantage becomes even more pronounced.
{"title":"Auction-based privacy-preserving cloud-edge collaborative scheduling considering flexible service ability for multi-source manufacturing tasks","authors":"Weimin Jing , Yong Yan , Yonghui Zhang , Xiang Ji , Wen Huang , Youling Chen , Huan Zhang","doi":"10.1016/j.rcim.2025.103206","DOIUrl":"10.1016/j.rcim.2025.103206","url":null,"abstract":"<div><div>In the context of cloud manufacturing service, scheduling manufacturing tasks is a crucial area of research because it directly influences service quality and efficiency. As intelligent manufacturing technologies advance, edge manufacturing service providers have gained increasingly flexible ability, enabling them to adjust local production schedules to adapt cloud manufacturing tasks. However, because local manufacturing information is private, traditional centralized cloud manufacturing scheduling methods cannot fully leverage edge flexibility to collaboratively schedule multi-source manufacturing tasks (including both cloud manufacturing tasks and local tasks of edge service providers) without risking the disclosure of sensitive information, thereby limiting improvements in both performance and efficiency of cloud manufacturing service. Therefore, we propose a privacy-preserving cloud-edge collaborative decision-making approach based on auction theory to schedule multi-source manufacturing tasks. First, a mathematical model that accounts for the objectives of both service providers and demanders is established to characterize the collaborative scheduling of multi-sourced tasks. Subsequently, a cloud-edge collaborative scheduling decision framework is introduced. Building upon this, a multi-stage scheduling method based on combinatorial iterative auctions is proposed, featuring novel bidding with a flexible execution timeline and distributed winner determination process incorporating bid consolidation mechanisms to enhance the efficiency of cloud-edge collaborative decision. Finally, to validate the superiority of the proposed method, computational experiments are conducted, comparing it with traditional centralized manufacturing task scheduling methods. The results present that the proposed method not only completes cloud manufacturing tasks within a relatively shorter makespan but also provides higher-value manufacturing services to demanders. Moreover, as the cloud manufacturing task load increases, this advantage becomes even more pronounced.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"99 ","pages":"Article 103206"},"PeriodicalIF":11.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145753457","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}
Pub Date : 2026-06-01Epub Date: 2025-12-16DOI: 10.1016/j.rcim.2025.103204
Yusen Wan, Xu Chen
A critical capability for intelligent manufacturing is the ability for robotic systems to understand the spatial operation environment – the ability for robots to precisely recognize and estimate the spatial positions and orientations of objects in industrial scenes. Existing scene reconstruction methods are designed for general settings with low precision needs of objects and abundant data. However, manufacturing hinges on high object precision and operates with limited data. Addressing such challenges and limitations, we propose a novel Learning-based Scene Point-cloud Registration framework for automatic industrial scene reconstruction (iLSPR). The proposed iLSPR framework leverages point cloud representation and integrates three key innovations: (i) a Multi-Feature Robust Point Matching Network (MF-RPMN) that learns from both raw data and deep features of the objects to accurately align point clouds, (ii) a Geometric-Primitive-based Data Generation (GPDG) method for efficient synthetic data generation, and (iii) a digital model library of industrial target objects. During operation, vision sensors capture point clouds in the scenes, and the iLSPR method registers high-fidelity object models in the scenes using MF-RPMN, pre-trained with GPDG-generated data. We introduce an Industrial Scene Object Point-cloud Registration (ISOPR) dataset in IsaacSim to benchmark performance. Experimental results demonstrate that iLSPR significantly outperforms existing methods in accuracy and robustness. We further validate the approach on a real-world robotic manufacturing system, demonstrating reliable digital reconstruction of industrial scenes.
{"title":"iLSPR: A Learning-based Scene Point-cloud Registration method for robotic spatial awareness in intelligent manufacturing","authors":"Yusen Wan, Xu Chen","doi":"10.1016/j.rcim.2025.103204","DOIUrl":"10.1016/j.rcim.2025.103204","url":null,"abstract":"<div><div>A critical capability for intelligent manufacturing is the ability for robotic systems to understand the spatial operation environment – the ability for robots to precisely recognize and estimate the spatial positions and orientations of objects in industrial scenes. Existing scene reconstruction methods are designed for general settings with low precision needs of objects and abundant data. However, manufacturing hinges on high object precision and operates with limited data. Addressing such challenges and limitations, we propose a novel <strong>L</strong>earning-based <strong>S</strong>cene <strong>P</strong>oint-cloud <strong>R</strong>egistration framework for automatic <strong>i</strong>ndustrial scene reconstruction (iLSPR). The proposed iLSPR framework leverages point cloud representation and integrates three key innovations: (i) a <strong>M</strong>ulti-<strong>F</strong>eature <strong>R</strong>obust <strong>P</strong>oint <strong>M</strong>atching <strong>N</strong>etwork (MF-RPMN) that learns from both raw data and deep features of the objects to accurately align point clouds, (ii) a <strong>G</strong>eometric-<strong>P</strong>rimitive-based <strong>D</strong>ata <strong>G</strong>eneration (GPDG) method for efficient synthetic data generation, and (iii) a digital model library of industrial target objects. During operation, vision sensors capture point clouds in the scenes, and the iLSPR method registers high-fidelity object models in the scenes using MF-RPMN, pre-trained with GPDG-generated data. We introduce an <strong>I</strong>ndustrial <strong>S</strong>cene <strong>O</strong>bject <strong>P</strong>oint-cloud <strong>R</strong>egistration (ISOPR) dataset in IsaacSim to benchmark performance. Experimental results demonstrate that iLSPR significantly outperforms existing methods in accuracy and robustness. We further validate the approach on a real-world robotic manufacturing system, demonstrating reliable digital reconstruction of industrial scenes.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"99 ","pages":"Article 103204"},"PeriodicalIF":11.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145785000","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}
Pub Date : 2026-06-01Epub Date: 2025-11-27DOI: 10.1016/j.rcim.2025.103177
C.L. Li , Y.C. Jiao , K. Ren , N. Liu , Y.F. Zhang
Robot-assisted additive manufacturing (AM) has been gaining increasing popularity due to its great flexibility and reachability. Moreover, an AM system with dual deposition-heads held by robot manipulators would significantly shorten the building time, especially for large-scale parts. However, motion planning (MP) for the dual robot manipulators AM is highly challengeable due to various constraints imposed by the setup and the AM process aiming to improve the qualities of the component, e.g., maintaining travelling speed and posture of the deposition head and avoiding collision. In this paper, a novel pivot-move strategy is proposed for MP in AM with dual robot manipulators. Given the sequenced deposition toolpath segments to each deposition head, an initial MP solution including robot configuration at each time sample waypoint is firstly generated for each robot manipulator, respectively. This is followed by conducting a check-and-correct process at each waypoint, where the collision among the links of two robot manipulators is identified and corrected. Specially, the robot manipulator is designed to simultaneously pivot and move to avoid the collision while maintaining the traveling speed unchanged. Numerical simulation, physical implementation, and benchmarking were conducted to exhibit a 78.295% deposition time reduction and high-quality deposition with the developed strategy. To the best of the authors' knowledge, this study represents the pioneering effort in addressing the collision issue in dual robot manipulators depositing on the same heated bed, achieving collision avoidance without interrupting the ongoing deposition process. It can be a valuable supplement to the state of the art in this area.
{"title":"A Novel Pivot-Move Strategy for Dual-Robot Manipulator Additive Manufacturing: Enabling Collision Avoidance without Halting Deposition","authors":"C.L. Li , Y.C. Jiao , K. Ren , N. Liu , Y.F. Zhang","doi":"10.1016/j.rcim.2025.103177","DOIUrl":"10.1016/j.rcim.2025.103177","url":null,"abstract":"<div><div>Robot-assisted additive manufacturing (AM) has been gaining increasing popularity due to its great flexibility and reachability. Moreover, an AM system with dual deposition-heads held by robot manipulators would significantly shorten the building time, especially for large-scale parts. However, motion planning (MP) for the dual robot manipulators AM is highly challengeable due to various constraints imposed by the setup and the AM process aiming to improve the qualities of the component, e.g., maintaining travelling speed and posture of the deposition head and avoiding collision. In this paper, a novel pivot-move strategy is proposed for MP in AM with dual robot manipulators. Given the sequenced deposition toolpath segments to each deposition head, an initial MP solution including robot configuration at each time sample waypoint is firstly generated for each robot manipulator, respectively. This is followed by conducting a check-and-correct process at each waypoint, where the collision among the links of two robot manipulators is identified and corrected. Specially, the robot manipulator is designed to simultaneously pivot and move to avoid the collision while maintaining the traveling speed unchanged. Numerical simulation, physical implementation, and benchmarking were conducted to exhibit a 78.295% deposition time reduction and high-quality deposition with the developed strategy. To the best of the authors' knowledge, this study represents the pioneering effort in addressing the collision issue in dual robot manipulators depositing on the same heated bed, achieving collision avoidance without interrupting the ongoing deposition process. It can be a valuable supplement to the state of the art in this area.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"99 ","pages":"Article 103177"},"PeriodicalIF":11.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145611798","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}
Human-robot collaboration (HRC) offers promising solutions in industrial assembly by combining human dexterity and robot efficiency. However, the proximity of the human and robot raises safety concerns that can limit efficiency. Previous studies have typically addressed safety or efficiency separately, relying on incomplete models of human behavior, which has led to robot control strategies with limited adaptability. To bridge this gap, this paper proposes a hierarchical human behavior modeling framework that integrates human motion prediction (HMP) and human action segmentation. The proposed model captures both the fine-grained motion dynamics and the higher-level task structure, enabling a more complete and context-aware understanding of human behavior. The model can enhance robot decision-making for both proactive safety mechanisms and dynamic task allocation. HMP compares three predictive models (Convolutional Neural Networks - Long Short-Term Memory (CNN-LSTM), Spatial-Temporal Graph Convolutional Networks (ST-GCN), Transformer). CNN-LSTM and ST-GCN outperformed Transformer, demonstrating better short-term predictive accuracy. Human action segmentation includes feature extraction, dimensionality reduction, clustering, and two-stage temporal segmentation. The HMP (CNN-LSTM) based features achieve the highest clustering performance. Two-stage segmentation demonstrates high accuracy, achieving normalized edit distances (NED) of 0.029 and 0.07 for task-level and sub-task-level segmentation, respectively. Evaluation results show that proactive collision avoidance using predicted motions increased safety distance (from 0.4633 m to 0.4717 m), while dynamic task allocation based on action segmentation improves robot efficiency (from 84.95 % to 98.56 %). These results validate the effectiveness of the proposed hierarchical human behavior modeling framework in simultaneously enhancing safety and efficiency in HRC assembly.
{"title":"A hierarchical human behavior modeling framework for safe and efficient human-robot collaborative assembly","authors":"Guoyi Xia , Zied Ghrairi , Aaron Heuermann , Klaus-Dieter Thoben","doi":"10.1016/j.rcim.2025.103202","DOIUrl":"10.1016/j.rcim.2025.103202","url":null,"abstract":"<div><div>Human-robot collaboration (HRC) offers promising solutions in industrial assembly by combining human dexterity and robot efficiency. However, the proximity of the human and robot raises safety concerns that can limit efficiency. Previous studies have typically addressed safety or efficiency separately, relying on incomplete models of human behavior, which has led to robot control strategies with limited adaptability. To bridge this gap, this paper proposes a hierarchical human behavior modeling framework that integrates human motion prediction (HMP) and human action segmentation. The proposed model captures both the fine-grained motion dynamics and the higher-level task structure, enabling a more complete and context-aware understanding of human behavior. The model can enhance robot decision-making for both proactive safety mechanisms and dynamic task allocation. HMP compares three predictive models (Convolutional Neural Networks - Long Short-Term Memory (CNN-LSTM), Spatial-Temporal Graph Convolutional Networks (ST-GCN), Transformer). CNN-LSTM and ST-GCN outperformed Transformer, demonstrating better short-term predictive accuracy. Human action segmentation includes feature extraction, dimensionality reduction, clustering, and two-stage temporal segmentation. The HMP (CNN-LSTM) based features achieve the highest clustering performance. Two-stage segmentation demonstrates high accuracy, achieving normalized edit distances (NED) of 0.029 and 0.07 for task-level and sub-task-level segmentation, respectively. Evaluation results show that proactive collision avoidance using predicted motions increased safety distance (from 0.4633 m to 0.4717 m), while dynamic task allocation based on action segmentation improves robot efficiency (from 84.95 % to 98.56 %). These results validate the effectiveness of the proposed hierarchical human behavior modeling framework in simultaneously enhancing safety and efficiency in HRC assembly.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"99 ","pages":"Article 103202"},"PeriodicalIF":11.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145731795","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号