Robotics and Computer-integrated Manufacturing最新文献_第3页

A disjunctive graph-based metaheuristic for flexible job-shop scheduling problems considering fixture shortages in customized manufacturing systems

IF 9.1 1区计算机科学

Robotics and Computer-integrated Manufacturing Pub Date : 2025-02-20 DOI: 10.1016/j.rcim.2025.102981

Jiahang Li , Qihao Liu , Cuiyu Wang , Xinyu Li

{"title":"A disjunctive graph-based metaheuristic for flexible job-shop scheduling problems considering fixture shortages in customized manufacturing systems","authors":"Jiahang Li , Qihao Liu , Cuiyu Wang , Xinyu Li","doi":"10.1016/j.rcim.2025.102981","DOIUrl":"10.1016/j.rcim.2025.102981","url":null,"abstract":"<div><div>Customized manufacturing systems represent a promising production paradigm capable of producing a variety of products to meet diverse customer needs. However, limited resources and complex processes complicate the optimization of production scheduling and resource allocation. In particular, fixture shortages frequently arise in a highly customized manufacturing enterprise, as multiple new jobs may require the same fixture simultaneously. Consequently, certain fixtures must be machined as part of production tasks in workshops. To derive high-quality scheduling solutions, this paper proposes an improved genetic algorithm with a disjunctive graph-based local search for flexible job-shop scheduling problems considering on-site machining fixtures. First, several problem-specific genetic operators are introduced to enhance exploration capabilities. Second, a disjunctive graph for total weighted tardiness is established to identify critical paths. Third, a critical path-based local search method is proposed, incorporating three knowledge-based neighborhood structures to improve exploitation capabilities. Finally, the proposed algorithm is evaluated in 20 instances and compared against five state-of-the-art algorithms. The experimental results demonstrate that the proposed algorithm significantly outperforms its competitors regarding convergence and statistical metrics. A daily order from the enterprise is examined as a case study to evaluate the practical benefits of the proposed algorithm. From this case study, the total weighted tardiness and makespan are reduced by 62.71% and 42.13%, respectively, compared to the original scheduling solution.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"95 ","pages":"Article 102981"},"PeriodicalIF":9.1,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143452840","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

Streamlined robotic hand–eye calibration of multiple 2D-profilers: A rapid, closed-form two-stage method via a single-plane artefact

IF 9.1 1区计算机科学

Robotics and Computer-integrated Manufacturing Pub Date : 2025-02-19 DOI: 10.1016/j.rcim.2025.102984

Subash Gautam , Hans Lohr , Alejandro Vargas-Uscategui , Peter C King , Alireza Bab-Hadiashar , Ivan Cole , Ehsan Asadi

{"title":"Streamlined robotic hand–eye calibration of multiple 2D-profilers: A rapid, closed-form two-stage method via a single-plane artefact","authors":"Subash Gautam , Hans Lohr , Alejandro Vargas-Uscategui , Peter C King , Alireza Bab-Hadiashar , Ivan Cole , Ehsan Asadi","doi":"10.1016/j.rcim.2025.102984","DOIUrl":"10.1016/j.rcim.2025.102984","url":null,"abstract":"<div><div>A 2D laser profiler is commonly utilized in high-precision robotic settings to capture detailed surface profiles for 3D scanning. By collecting and combining numerous such measurements from different viewpoints, it is possible to assemble a comprehensive 3D map. However, to effectively merge these individual 2D profiles into a singular global framework, the spatial relationship between the scanners and the robot’s reference frame is required. Traditional hand–eye calibration techniques typically necessitate specific calibration artifacts or extraneous positional sensors, and the process is either manually executed or only partially automated, demanding considerable time and effort. This paper introduces an innovative, closed-form approach to hand–eye calibration that can be applied to a single scanner or an array of multiple scanners. Our method circumvents the requirements for initial parameter estimates or specialized calibration implements, instead employing a flat plane for hand–eye calibration. This method paves the way for a fully automated calibration sequence comprising only three rotational and three translational poses, reducing the total calibration duration. This streamlined process has undergone strict experimental validation utilizing a calibrated sphere, proving its effectiveness not only with a solitary scanner setup but also with an ensemble of three scanners.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"95 ","pages":"Article 102984"},"PeriodicalIF":9.1,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143444818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Reinforcement Learning-based five-axis continuous inspection method for complex freeform surface

IF 9.1 1区计算机科学

Robotics and Computer-integrated Manufacturing Pub Date : 2025-02-18 DOI: 10.1016/j.rcim.2025.102990

Xiaoke Deng , Pengcheng Hu , Zhaoyu Li , Wenze Zhang , Dong He , Yuanzhi Chen

{"title":"Reinforcement Learning-based five-axis continuous inspection method for complex freeform surface","authors":"Xiaoke Deng , Pengcheng Hu , Zhaoyu Li , Wenze Zhang , Dong He , Yuanzhi Chen","doi":"10.1016/j.rcim.2025.102990","DOIUrl":"10.1016/j.rcim.2025.102990","url":null,"abstract":"<div><div>Five-axis continuous inspection is an innovative technology that allows for the efficient and precise inspection of freeform surfaces. Traditional methods for planning the five-axis inspection path rely on manually defined objective functions, which are heavily dependent on the expertise of professionals and often result in suboptimal paths. To overcome these challenges, we have developed a Reinforcement Learning (RL)-based approach for generating inspection paths. This method replaces the explicit objective function with an RL model that incorporates comprehensive geometric metrics of inspection surface, resulting in a high-performing head trajectory for the five-axis inspection path. Additionally, we have introduced a beam search-based method to generate a set of optimal head trajectories that cover the entire inspection surface. Our proposed method enables the automatic generation of short and smooth inspection paths without human intervention. Physical inspection experiments conducted on a five-axis inspection machine have demonstrated that our approach significantly improves inspection efficiency and automation compared to traditional benchmarks.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"94 ","pages":"Article 102990"},"PeriodicalIF":9.1,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143429928","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

Generalizing kinematic skill learning to energy efficient dynamic motion planning using optimized Dynamic Movement Primitives

IF 9.1 1区计算机科学

Robotics and Computer-integrated Manufacturing Pub Date : 2025-02-18 DOI: 10.1016/j.rcim.2025.102983

Tian Xu , Siddharth Singh , Qing Chang

{"title":"Generalizing kinematic skill learning to energy efficient dynamic motion planning using optimized Dynamic Movement Primitives","authors":"Tian Xu , Siddharth Singh , Qing Chang","doi":"10.1016/j.rcim.2025.102983","DOIUrl":"10.1016/j.rcim.2025.102983","url":null,"abstract":"<div><div>In manufacturing, automating the generation of dynamic trajectories for diverse robots and loads in response to kinematic task requirements presents a significant challenge. Previous research has primarily addressed kinematic trajectory generation and dynamic motion planning as separate endeavors, with integrated solutions rarely explored. This paper presents a novel methodology that combines reinforcement learning (RL)-based kinematic skill learning, dynamic modeling and an enhanced version of Dynamic Movement Primitives (DMP). Utilizing a pre-established skill library, the RL-enabled method generates multiple kinematic trajectories that fulfill the specific task requirements. These trajectories are further refined by dynamic modeling, selecting paths that minimize energy consumption tailored to specific robot types and loads. The newly proposed Optimized Normalized Dynamic Motion Primitive (ON-DMP) enhances obstacle avoidance with minimal energy consumption, remaining effective in novel environments. Validated through both simulated and real-world experiments, this methodology shows robust results in improving task completion in dynamic real-world environments without the need of reprogramming.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"94 ","pages":"Article 102983"},"PeriodicalIF":9.1,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143429926","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

A step-driven framework of digital twin model for product assembly precision based on polychromatic sets

IF 9.1 1区计算机科学

Robotics and Computer-integrated Manufacturing Pub Date : 2025-02-18 DOI: 10.1016/j.rcim.2025.102989

Kang Jia , Dongxu Ren , Hao Wang , Qiangqiang Zhao , Jun Hong

{"title":"A step-driven framework of digital twin model for product assembly precision based on polychromatic sets","authors":"Kang Jia , Dongxu Ren , Hao Wang , Qiangqiang Zhao , Jun Hong","doi":"10.1016/j.rcim.2025.102989","DOIUrl":"10.1016/j.rcim.2025.102989","url":null,"abstract":"<div><div>The integration of digital twin technology into the assembly process of complex precision mechanical products has become a significant and feasible means to improve product assembly quality and consistency by performing dynamic assembly precision prediction and henceforth assembly process optimization. Most current research predominantly focuses on modeling the actual machining error of components and their subsequent error propagation, with limited attention given to the methods driving the precision models of digital twins in the product assembly process. In this paper, an assembly operation-driven framework for synchronizing digital twin models dedicated to product assembly precision prediction is proposed based on the polychromic sets theory. Firstly, taking the assembly feature as the core of digital twins for assembly precision, homogenous coordinate transformation matrix is adopted to establish connections between assembly hierarchy objects and conduct assembly deviation propagation calculations. Secondly, the association relationship among product parts, assembly features, and assembly feature pairs is constructed in the form of the polychromatic sets matrix. Further, by linking the assembly sequence, a general enabling framework that can be used for automatic inference in constructing and updating assembly precision prediction models for the assembly process is established. Finally, a data model associated with the instantiation of the assembly precision prediction model is provided, and the assembly process of the high-pressure compressor rotor is taken as a case study to verify the effectiveness of the framework model in practical applications.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"94 ","pages":"Article 102989"},"PeriodicalIF":9.1,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143429927","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

Proposing a model based on deep reinforcement learning for real-time scheduling of collaborative customization remanufacturing

IF 9.1 1区计算机科学

Robotics and Computer-integrated Manufacturing Pub Date : 2025-02-18 DOI: 10.1016/j.rcim.2025.102980

Seyed Ali Yazdanparast , Seyed Hessameddin Zegordi , Toktam Khatibi

{"title":"Proposing a model based on deep reinforcement learning for real-time scheduling of collaborative customization remanufacturing","authors":"Seyed Ali Yazdanparast , Seyed Hessameddin Zegordi , Toktam Khatibi","doi":"10.1016/j.rcim.2025.102980","DOIUrl":"10.1016/j.rcim.2025.102980","url":null,"abstract":"<div><div>The mass production of products in recent decades has led to the excessive exploitation of global resources and environmental degradation. Researchers tackle this challenge by proposing methods for reusing end-of-life products, including remanufacturing strategies. On the other hand, today's consumers seek products that completely fulfill their needs. For this reason, leading manufacturers prioritize customization to improve consumer satisfaction. In contrast to previous studies, this research investigates the real-time scheduling problem of intelligent systems in remanufacturing collaboratively customized products. To address this problem, the multi-agent deep Q-network method is proposed and designed. The elements of this method are defined for each remanufacturing department, including disassembly, cleaning-repair, and assembly stations. The experimental data is simulated to evaluate the proposed method based on a realistic smartphone assembly environment that can produce 46,656 unique products. Despite the disruption caused by the arrival of new jobs, the proposed method's results outperform those of the combined genetic algorithm. They can reduce factory costs by >6 %.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"94 ","pages":"Article 102980"},"PeriodicalIF":9.1,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143429925","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

VLM-MSGraph: Vision Language Model-enabled Multi-hierarchical Scene Graph for robotic assembly

IF 9.1 1区计算机科学

Robotics and Computer-integrated Manufacturing Pub Date : 2025-02-16 DOI: 10.1016/j.rcim.2025.102978

Shufei Li , Zhijie Yan , Zuoxu Wang , Yiping Gao

{"title":"VLM-MSGraph: Vision Language Model-enabled Multi-hierarchical Scene Graph for robotic assembly","authors":"Shufei Li , Zhijie Yan , Zuoxu Wang , Yiping Gao","doi":"10.1016/j.rcim.2025.102978","DOIUrl":"10.1016/j.rcim.2025.102978","url":null,"abstract":"<div><div>Intelligent robotic assembly is becoming a pivotal component of the manufacturing sector, driven by growing demands for flexibility, sustainability, and resilience. Robots in manufacturing environments need perception, decision-making, and manipulation skills to support the flexible production of diverse products. However, traditional robotic assembly systems typically rely on time-consuming training processes specific to fixed settings, lacking generalization and zero-shot learning capabilities. To address these challenges, this paper introduces a Vision Language Model-enabled Multi-hierarchical Scene Graph (VLM-MSGraph) approach for robotic assembly, featuring generalized assembly sequence learning and 3D manipulation in open scenarios. The MSGraph incorporates high-level task planning structured as triplets, organized by multiple VLM agents. At a low level, the MSGraph retains 3D spatial relationships between industrial parts, enabling the robot to perform assembly tasks while accounting for object geometry for effective manipulation. Assembly drawings, physics simulations, and assembly tasks in a laboratory setting are used to evaluate the proposed system, advancing flexible automation in robotics.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"94 ","pages":"Article 102978"},"PeriodicalIF":9.1,"publicationDate":"2025-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143419256","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

Optimizing the performance of serial robots for milling tasks: A review

IF 9.1 1区计算机科学

Robotics and Computer-integrated Manufacturing Pub Date : 2025-02-14 DOI: 10.1016/j.rcim.2025.102977

Yuhang Gao, Tianyang Qiu, Ci Song, Senjie Ma, Zhibing Liu, Zhiqiang Liang, Xibin Wang

引用次数: 0

A human-robot collaborative assembly framework with quality checking based on real-time dual-hand action segmentation

IF 9.1 1区计算机科学

Robotics and Computer-integrated Manufacturing Pub Date : 2025-02-13 DOI: 10.1016/j.rcim.2025.102976

Hao Zheng, Wanqing Xia, Xun Xu

{"title":"A human-robot collaborative assembly framework with quality checking based on real-time dual-hand action segmentation","authors":"Hao Zheng, Wanqing Xia, Xun Xu","doi":"10.1016/j.rcim.2025.102976","DOIUrl":"10.1016/j.rcim.2025.102976","url":null,"abstract":"<div><div>This paper presents a human-robot collaborative assembly (HRCA) framework, addressing key challenges in real-time dual-hand action understanding, adaptive robot assistance, and in-process quality checking. At its core is DuHa-v2, a real-time dual-hand action segmentation algorithm that efficiently segments assembly actions of two hands by integrating object interaction and action features. DuHa-v2 enables robots to proactively assist human workers by utilising either next-task prediction or indicative action recognition, both informed by the segmented action sequences. An in-process quality checking mechanism is proposed to ensure high assembly quality and efficiency by identifying errors immediately after critical assembly steps. The framework's effectiveness is validated through experiments on both the HA-ViD dataset and a real-world case study, demonstrating superior dual-hand action segmentation performance, timely robot assistance, and effective quality checking. The proposed HRCA framework enables robots to collaborate with humans in a more intuitive and reliable way by providing timely assistance, whether or not the overall task is known, and performing in-time assembly quality checks. More information can be found in <span><span>https://github.com/hao-zheng-research/A-human-robot-collaborative-assembly-framework-with-quality-checking</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"94 ","pages":"Article 102976"},"PeriodicalIF":9.1,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143394086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Intelligent robot gripper using embedded AI sensor for box re-sequencing system integrated with spatial layout optimization

IF 9.1 1区计算机科学

Robotics and Computer-integrated Manufacturing Pub Date : 2025-02-13 DOI: 10.1016/j.rcim.2025.102979

Shokhikha Amalana Murdivien, Jumyung Um

{"title":"Intelligent robot gripper using embedded AI sensor for box re-sequencing system integrated with spatial layout optimization","authors":"Shokhikha Amalana Murdivien, Jumyung Um","doi":"10.1016/j.rcim.2025.102979","DOIUrl":"10.1016/j.rcim.2025.102979","url":null,"abstract":"<div><div>The integration of artificial intelligence into robotic systems has resulted in a significant revolution in various industrial procedures, particularly impacting logistics and warehouse management. This impact is particularly notable due to the increasing need for automated and flexible logistics systems. A crucial factor to consider during the loading phase is the precise measurement of the weight of loaded boxes and their optimal spatial arrangement. Moreover, the possibility of boxes remaining undisturbed for extended periods underscores the significance of correctly arranging and stacking them. Incorrect stacking could result in damaged boxes, particularly if heavier boxes are placed atop lighter ones. This study presents a solution incorporating a sensory gripper with artificial intelligence to tackle the challenges of weight-based box re-sequencing and spatial optimization through Deep Reinforcement Learning. The integrated system proposed facilitates the dynamic re-sequencing of boxes based on weight during palletization. The proposed model successfully arranged eight boxes of the same size, weighing between 62 and 326 g. The arrangement of the stacked boxes also varied according to weight, from the heaviest to the lightest, demonstrating the effectiveness of the re-sequencing algorithm utilizing both fundamental and embedded artificial intelligence models. The embedded artificial intelligence model provides similar accuracy levels while emphasizing its advantage of being 88.6 % smaller compared to the basic model.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"94 ","pages":"Article 102979"},"PeriodicalIF":9.1,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143402987","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