Robotics and Computer-integrated Manufacturing最新文献_第2页

Autonomous production unit: An architecture for blockchain-based shared manufacturing 自主生产单元：基于区块链的共享制造架构

IF 9.1 1区计算机科学

Robotics and Computer-integrated Manufacturing Pub Date : 2025-05-07 DOI: 10.1016/j.rcim.2025.103035

Nejc Rožman, Marko Corn, Dominik Kozjek, Rok Vrabič, Primož Podržaj

{"title":"Autonomous production unit: An architecture for blockchain-based shared manufacturing","authors":"Nejc Rožman, Marko Corn, Dominik Kozjek, Rok Vrabič, Primož Podržaj","doi":"10.1016/j.rcim.2025.103035","DOIUrl":"10.1016/j.rcim.2025.103035","url":null,"abstract":"<div><div>Driven by technological advancements and the increasing need for efficiency and customization, the manufacturing industry is shifting towards Shared Manufacturing. This strategy enhances global production flexibility and resource utilization by enabling diverse entities to collaboratively engage in distributed manufacturing activities. Expanded resource sharing across industries and society, along with the redefinition of manufacturing resources as marketable services, creates a complex, interconnected production network that demands autonomous production control for effective and flexible management. This study proposes an architectural design for Autonomous Production Units within a blockchain-based Shared Manufacturing system. The design enhances autonomy, allowing independent management and optimization of manufacturing processes while integrating with the global market. The architecture includes two key decision-making submodules: the Business Decisions Submodule, which handles operational activities and interactions with the blockchain network, and the Manufacturing Decisions Submodule, which oversees physical manufacturing processes. The concept is implemented and tested on a case study, demonstrating the Autonomous Production Unit’s capability to autonomously execute the entire manufacturing process, from negotiation to manufacturing service execution, while also handling malfunctions.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"96 ","pages":"Article 103035"},"PeriodicalIF":9.1,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143917307","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}

引用次数: 0

Edge device deployment for intelligent machine tools: A lightweight and interpretable tool wear monitoring method considering wear behavior 智能机床的边缘设备部署：考虑磨损行为的轻量级和可解释的工具磨损监测方法

IF 9.1 1区计算机科学

Robotics and Computer-integrated Manufacturing Pub Date : 2025-05-06 DOI: 10.1016/j.rcim.2025.103033

Yezhen Peng , Weimin Kang , Fengwen Yu , Zequan Ding , Wenhong Zhou , Jianzhong Fu , Songyu Hu

{"title":"Edge device deployment for intelligent machine tools: A lightweight and interpretable tool wear monitoring method considering wear behavior","authors":"Yezhen Peng , Weimin Kang , Fengwen Yu , Zequan Ding , Wenhong Zhou , Jianzhong Fu , Songyu Hu","doi":"10.1016/j.rcim.2025.103033","DOIUrl":"10.1016/j.rcim.2025.103033","url":null,"abstract":"<div><div>Tool wear condition monitoring is essential for reducing production costs and improving machining precision, serving as a key strategy for achieving machine tool intelligence. However, existing methods often depend on empirically designed complex networks to achieve high recognition accuracy, which results in high computational costs, poor performance during later wear stages, and limited interpretability. To address these challenges, a lightweight and interpretable tool wear recognition method is proposed. The feature self-adaptive reconstruction strategy based on wear behavior improves feature quality, while a nonlinear cumulative wear model provides physics guidance, ensuring the model remains lightweight and interpretable. To improve recognition accuracy and robustness during later wear stages, an adaptive loss adjustment mechanism driven by error uncertainty is proposed. Additionally, the influence of reconstructed features on model output is analyzed using shapley additive explanations (SHAP) values, while dependency graphs explore interactions between features across signals and domains, reinforcing physical interpretability. Results show reconstructed features in the y-direction have the greatest influence on model output during side milling. Time-domain and time-frequency domain features dominate, with frequency-domain features providing complementary information. Experiments show the proposed method reduces RMSE by 4.77 and 6.63, MAE by 2.89 and 5.17, and improves R² by 0.06 and 0.12 compared to models with different loss weights and feature processing methods. Recognition accuracy was further improved during later wear stages, achieving RMSE, MAE, and R² values of 3.58, 2.73, and 0.92, respectively. Moreover, the model uses only four fully connected layers, reducing parameters by over 9.32 times, demonstrating the feasibility of edge deployment.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"95 ","pages":"Article 103033"},"PeriodicalIF":9.1,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143906114","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}

引用次数: 0

The user experience in industrial human-robot interaction: A comparative analysis of Unimodal and Multimodal interfaces for disassembly tasks 工业人机交互中的用户体验：用于拆卸任务的单模态和多模态界面的比较分析

IF 9.1 1区计算机科学

Robotics and Computer-integrated Manufacturing Pub Date : 2025-05-02 DOI: 10.1016/j.rcim.2025.103045

Ainhoa Apraiz, Ganix Lasa, Maitane Mazmela, Nestor Arana-Arexolaleiba, Íñigo Elguea, Oscar Escallada, Nagore Osa, Amaia Etxabe

{"title":"The user experience in industrial human-robot interaction: A comparative analysis of Unimodal and Multimodal interfaces for disassembly tasks","authors":"Ainhoa Apraiz, Ganix Lasa, Maitane Mazmela, Nestor Arana-Arexolaleiba, Íñigo Elguea, Oscar Escallada, Nagore Osa, Amaia Etxabe","doi":"10.1016/j.rcim.2025.103045","DOIUrl":"10.1016/j.rcim.2025.103045","url":null,"abstract":"<div><div>In the Industry 5.0 context, ensuring effective Human-Robot Interaction (HRI) is key to supporting human involvement in production processes. Interfaces are the foundation of this collaboration and serve as vital communication channels which bridge the gap between users and robotic systems. This study compares unimodal and multimodal interfaces and their impact on user experience (UX) in an HRI context. Unimodal interfaces, while simplifying implementation, may restrict the richness of communication, while multimodal interfaces provide detailed and flexible interaction, enhancing the conveyance of complex information. However, designing effective multimodal interfaces presents challenges due to their inherent complexity in managing multiple modalities. This paper presents an HRI disassembly case study comparing the impact of these interfaces on the UX. A methodological approach was used to monitor operator performance, physiological responses, and perceptual responses. An electroencephalogram was employed to objectively record the operators’ emotional responses of operators without interrupting or hindering the process. Twenty participants (10 men and 10 women) were involved in the study. The results indicate that levels of memorization and mental workload are lower when using the multimodal interface, a finding consistent across men and women. These findings suggest that the multimodal interface is an appropriate choice, not only for reducing memorization and mental workload levels, but also for its inclusive approach. This aligns with the objectives of Industry 5.0, promoting the development of technology that meets diverse user preferences and abilities, thereby ensuring greater accessibility and a more user-centric technological landscape.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"95 ","pages":"Article 103045"},"PeriodicalIF":9.1,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143895948","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}

引用次数: 0

Enhancing reconfiguration of cloud manufacturing service composition under unexpected changes in service time availability by flexible splitting and intermingling strategies 通过灵活的分离和混合策略，增强在服务时间可用性意外变化下云制造服务组合的重构

IF 9.1 1区计算机科学

Robotics and Computer-integrated Manufacturing Pub Date : 2025-05-02 DOI: 10.1016/j.rcim.2025.103044

Zian Zhao , Hong Zhou , Xi Vincent Wang , Xia Hua

{"title":"Enhancing reconfiguration of cloud manufacturing service composition under unexpected changes in service time availability by flexible splitting and intermingling strategies","authors":"Zian Zhao , Hong Zhou , Xi Vincent Wang , Xia Hua","doi":"10.1016/j.rcim.2025.103044","DOIUrl":"10.1016/j.rcim.2025.103044","url":null,"abstract":"<div><div>Cloud manufacturing service composition reconfiguration (CMSCR) is an essential process for handling unpredictable service exceptions to ensure the smooth operation of the cloud manufacturing (CMfg) system in a dynamic environment. Considering the occupied status of service providers of a CMfg system (CMSPs) at the time of change occurrence, the reconfiguration can be organized only with the available time of CMSPs, i.e., a set of available service time windows (ASTWs). In traditional CMSCR studies, tasks are assumed to be processed in fixed size of batches, which will lead to the unavailability of some ASTWs. This inevitably results in the insufficient utilization of CMfg resources and leaves less room for reconfiguration. To handle this problem, we introduce flexible splitting and intermingling strategies in CMSCR, aiming to improve the reconfiguration capacity by increasing resource utilization. This paper first analyzes four typical types of unexpected changes in ASTWs and their response conditions for reconfiguration. Next, an enhanced CMSCR approach with flexible splitting and intermingling strategies (SCRTW-SI) is proposed to handle the unexpected changes in ASTWs. In addition, a novel slack-based insertion mechanism is developed to further improve the reconfiguration performance. The CMSCR problem under consideration is formulated with a multi-objective mixed integer programming model. And a multi-objective service composition reconfiguration algorithm based on memetic algorithm (MOSCRMA) is proposed, in which some problem-specific schemes are elaborated. The performance is validated through extensive numerical experiments. Finally, a real-world case is analyzed to demonstrate the applicability and superiority of the approach.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"95 ","pages":"Article 103044"},"PeriodicalIF":9.1,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143895947","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}

引用次数: 0

Efficient positioning error compensation for robots in wire arc hybrid manufacturing systems 线弧混合制造系统中机器人定位误差的有效补偿

IF 9.1 1区计算机科学

Robotics and Computer-integrated Manufacturing Pub Date : 2025-05-02 DOI: 10.1016/j.rcim.2025.103040

Jianlong Zhang , Jiarui Lin , Yang Gao , Zheng Wang , Fangda Xu , Jigui Zhu

{"title":"Efficient positioning error compensation for robots in wire arc hybrid manufacturing systems","authors":"Jianlong Zhang , Jiarui Lin , Yang Gao , Zheng Wang , Fangda Xu , Jigui Zhu","doi":"10.1016/j.rcim.2025.103040","DOIUrl":"10.1016/j.rcim.2025.103040","url":null,"abstract":"<div><div>Wire arc additive manufacturing is a promising technology but is still limited by insufficient manufacturing accuracy. Despite numerous studies on process parameters to enhance manufacturing precision, the errors introduced by robot in hybrid manufacturing systems have not been effectively addressed. Unique on-site conditions such as varying robot poses and large working spaces have rendered many previous methods ineffective, making error compensation a challenging task. To solve this issue, an efficient compensation method for robots in wire arc hybrid manufacturing systems is proposed. A similarity-Radial Basis Function Neural Network is proposed to tackle pose variation issues that hinder error compensation methods, guaranteeing accuracy despite robot pose variations. However, the process of sampling to train neural networks is arduous. Arbitrarily reducing the number of sampling points is not feasible. Instead, optimizing the sampling process is a more effective approach. In this paper, we adopt the workspace Measurement and Positioning System and design a novel target based on circumferential constraints, presenting a comprehensive measurement optimization solution. This solution makes the arduous sampling process for training no longer difficult, significantly reducing the sampling time. Experimental verification shows that after using the proposed method for compensation, the positioning error decreased to 0.20 mm, and the compensation efficiency also significantly increased over 60%. To further validate the practical application of the method, real manufacturing tests are conducted in practical manufacturing scenarios. The results demonstrate good compensation effects, proving the feasibility of the compensation method.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"95 ","pages":"Article 103040"},"PeriodicalIF":9.1,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143900073","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}

引用次数: 0

Digital twin driven dynamic scheduling of discrete manufacturing workshop with transportation resource constraint using multi-agent deep reinforcement learning 基于多智能体深度强化学习的运输资源约束下离散制造车间动态调度

IF 9.1 1区计算机科学

Robotics and Computer-integrated Manufacturing Pub Date : 2025-05-01 DOI: 10.1016/j.rcim.2025.103042

Sai Geng , Shaohua Huang , Yu Guo , Weiwei Qian , Weiguang Fang , Litong Zhang , Shengbo Wang

{"title":"Digital twin driven dynamic scheduling of discrete manufacturing workshop with transportation resource constraint using multi-agent deep reinforcement learning","authors":"Sai Geng , Shaohua Huang , Yu Guo , Weiwei Qian , Weiguang Fang , Litong Zhang , Shengbo Wang","doi":"10.1016/j.rcim.2025.103042","DOIUrl":"10.1016/j.rcim.2025.103042","url":null,"abstract":"<div><div>In discrete manufacturing workshop where disturbances occur frequently, the dynamic scheduling problem that considers transportation resource constraint is complex and challenging. Additionally, rescheduling without evaluating the impact of disturbances may adversely affect production stability of workshop. To address these issues, this paper proposes a dynamic scheduling framework based on digital twin and deep reinforcement learning. Specifically, the digital twin environment is constructed to provide a high-fidelity training environment for scheduling agents and serve as a simulation means for evaluating the impact of disturbances. Furthermore, a rescheduling trigger discriminator mechanism is designed to dynamically determine the necessity of rescheduling. In particular, the multi-agent proximal policy optimization with multiple critics (MAPPO-MC) is proposed to efficiently solve the discrete manufacturing workshop dynamic scheduling problem with transportation resource constraint. The innovation of MAPPO-MC lies in using the global critic to facilitate collaboration among scheduling agents from a global perspective, while employing individual critics to guide corresponding agents to learn their specialized scheduling knowledge from a local perspective, thereby achieving optimal scheduling decisions. Finally, extensive experiments have demonstrated the effectiveness of the proposed framework and the superiority of the MAPPO-MC. Under this framework, MAPPO-MC can respond promptly and effectively to disturbances in the workshop while ensuring stable production.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"95 ","pages":"Article 103042"},"PeriodicalIF":9.1,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143891521","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}

引用次数: 0

Towards Human Modeling for Human-Robot Collaboration and Digital Twins in Industrial Environments: Research Status, Prospects, and Challenges 面向工业环境中人机协作和数字孪生的人类建模：研究现状、展望与挑战

IF 9.1 1区计算机科学

Robotics and Computer-integrated Manufacturing Pub Date : 2025-04-30 DOI: 10.1016/j.rcim.2025.103043

Guoyi Xia , Zied Ghrairi , Thorsten Wuest , Karl Hribernik , Aaron Heuermann , Furui Liu , Hui Liu , Klaus-Dieter Thoben

{"title":"Towards Human Modeling for Human-Robot Collaboration and Digital Twins in Industrial Environments: Research Status, Prospects, and Challenges","authors":"Guoyi Xia , Zied Ghrairi , Thorsten Wuest , Karl Hribernik , Aaron Heuermann , Furui Liu , Hui Liu , Klaus-Dieter Thoben","doi":"10.1016/j.rcim.2025.103043","DOIUrl":"10.1016/j.rcim.2025.103043","url":null,"abstract":"<div><div>Human-Robot Collaboration (HRC) and Digital Twins (DT) have significantly advanced industrial development and digital transformation. Human representations and models are essential in Industry 5.0, where human-centric is one of the key features. Despite the growing interest in human models for HRC and DT, a comprehensive overview of these models and enabling technologies currently needs to be provided. This paper aims to present the research status, prospects, applications, and challenges of human modeling for HRC and DT in industrial environments. This paper adopts a Systematic Literature Review (SLR) approach. Moreover, a framework is proposed to systematize human modeling aspects, the technologies used by robots for modeling, and the applications of human models throughout various lifecycle stages. The modeled aspects are categorized into physical and behavior models, with behavior models further divided into perception, cognition, and execution models. The technology is structured hierarchically into input, process, and output layers. Applications of the models are discussed across design, manufacturing, and service phases. The research status is examined in terms of human aspects and relevant technologies, identifying current limitations. Based on this, future prospects to address these limitations are discussed. Furthermore, the challenges in advancing current research towards these prospects are identified, focusing on model fidelity, individual-specific models, sensing, and computation. This research aims to support future human modeling in HRC and DT, contributing to safety, efficiency, and human well-being in industrial environments.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"95 ","pages":"Article 103043"},"PeriodicalIF":9.1,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143891528","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}

引用次数: 0

Robotic system for automated disassembly of electronic waste: Unscrewing 自动拆卸电子废物的机器人系统：旋开

IF 9.1 1区计算机科学

Robotics and Computer-integrated Manufacturing Pub Date : 2025-04-29 DOI: 10.1016/j.rcim.2025.103032

Iñaki Díaz , Diego Borro , Olatz Iparraguirre , Martxel Eizaguirre , Frank A. Ricardo , Nicolás Muñoz , Jorge Juan Gil

{"title":"Robotic system for automated disassembly of electronic waste: Unscrewing","authors":"Iñaki Díaz , Diego Borro , Olatz Iparraguirre , Martxel Eizaguirre , Frank A. Ricardo , Nicolás Muñoz , Jorge Juan Gil","doi":"10.1016/j.rcim.2025.103032","DOIUrl":"10.1016/j.rcim.2025.103032","url":null,"abstract":"<div><div>The increasing volume of electronic Waste from Electrical and Electronic Equipment (WEEE) presents significant environmental and economic challenges. Efficient recycling requires the disassembly of electronic devices, a process that is currently labor-intensive and costly. In this paper, we present a robotic system designed to automate the disassembly process, focusing on the task of unscrewing fasteners commonly found in electronic devices. The system integrates a Universal Robots UR10e robotic arm, an Intel RealSense D405 vision camera, and a custom-designed mechatronic screwdriver. The vision system trains several object detection models to assist robotic control and identify four different types of screw heads. The robot employs force-sensing techniques to align the screwdriver tip with the screw head before unscrewing. Validation is carried out on a real recycled hoverboard, demonstrating the system’s efficiency in automating unscrewing processes. The results can be generalized to other unscrewing operations in various industries.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"95 ","pages":"Article 103032"},"PeriodicalIF":9.1,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143881782","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}

引用次数: 0

Large vision-language models enabled novel objects 6D pose estimation for human-robot collaboration 大型视觉语言模型为人机协作提供了新的物体6D姿态估计

IF 9.1 1区计算机科学

Robotics and Computer-integrated Manufacturing Pub Date : 2025-04-26 DOI: 10.1016/j.rcim.2025.103030

Wanqing Xia, Hao Zheng, Weiliang Xu, Xun Xu

{"title":"Large vision-language models enabled novel objects 6D pose estimation for human-robot collaboration","authors":"Wanqing Xia, Hao Zheng, Weiliang Xu, Xun Xu","doi":"10.1016/j.rcim.2025.103030","DOIUrl":"10.1016/j.rcim.2025.103030","url":null,"abstract":"<div><div>Six-Degree-of-Freedom (6D) pose estimation is essential for robotic manipulation tasks, especially in human-robot collaboration environments. Recently, 6D pose estimation has been extended from seen objects to novel objects due to the frequent encounters with unfamiliar items in real-life scenarios. This paper presents a three-stage pipeline for 6D pose estimation of previously unseen objects, leveraging the capabilities of large vision-language models. Our approach consists of vision-language model-based object detection and segmentation, mask selection with pose hypothesis generated from CAD models, and refinement and scoring of pose candidates. We evaluate our method on the YCB-Video dataset, achieving a state-of-the-art Average Recall (AR) score of 75.8 with RGB-D images, demonstrating its effectiveness in accurately estimating 6D poses for a diverse range of objects. The effectiveness of each operation stage is investigated in the ablation study. To validate the practical applicability of our approach, we conduct case studies on a real-world robotic platform, focusing on object pick-up tasks by integrating our 6D pose estimation pipeline with human intention prediction and task analysis algorithms. Results show that the proposed method can effectively handle novel objects in our test environments, as demonstrated through the YCB dataset evaluation and case studies. Our work contributes to the field of human-robot collaboration by introducing a flexible, generalizable approach to 6D pose estimation, enabling robots to adapt to new objects without requiring extensive retraining—a vital capability for advancing human-robot collaboration in dynamic environments. More information can be found in the project GitHub page: <span><span>https://github.com/WanqingXia/HRC_DetAnyPose</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"95 ","pages":"Article 103030"},"PeriodicalIF":9.1,"publicationDate":"2025-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143874159","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}

引用次数: 0

Real-time response to machine failures in self-organizing production execution using multi-agent reinforcement learning with effective samples 基于有效样本的多智能体强化学习对自组织生产执行中机器故障的实时响应

IF 9.1 1区计算机科学

Robotics and Computer-integrated Manufacturing Pub Date : 2025-04-25 DOI: 10.1016/j.rcim.2025.103038

Yong Gui , Dunbing Tang , Yuqian Lu , Haihua Zhu , Zequn Zhang , Changchun Liu

{"title":"Real-time response to machine failures in self-organizing production execution using multi-agent reinforcement learning with effective samples","authors":"Yong Gui , Dunbing Tang , Yuqian Lu , Haihua Zhu , Zequn Zhang , Changchun Liu","doi":"10.1016/j.rcim.2025.103038","DOIUrl":"10.1016/j.rcim.2025.103038","url":null,"abstract":"<div><div>With the growing demand for personalized production, multi-agent technology has been introduced to facilitate rapid self-organizing production execution. The application of communication protocols and dynamic scheduling algorithms supports multi-agent negotiation and real-time scheduling decisions in response to conventional production events. To address machine failures, real-time response strategies have been developed to manage jobs affected by the disruptions. However, the performance of existing strategies varies significantly depending on the real-time production state. In this paper, we propose a real-time response strategy using multi-agent reinforcement learning (MARL) that provides an appropriate response strategy for each job affected by machine failures, considering the real-time production state. Specifically, we establish a self-organizing production execution process with machine failures to specify the real-time response problem. Subsequently, a Markov game involving multiple buffer agents is constructed, transforming the real-time response problem into a MARL task. Furthermore, a continuous variable ranging from 0 to 1 is defined as the action space for each buffer agent, allowing it to select a response strategy for each affected job. Finally, a modified multi-agent deep deterministic policy gradient (MADDPG) algorithm is introduced, leveraging effective samples to train buffer agents at each failure moment. This enables the selection of an optimal response strategy for each affected job. Experimental results indicate that the proposed real-time response strategy outperforms both existing response strategies and the original MADDPG-based strategy across 54 distinct production configurations.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"95 ","pages":"Article 103038"},"PeriodicalIF":9.1,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143868269","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}

引用次数: 0