Robotics and Computer-integrated Manufacturing最新文献_第9页

Generalizing kinematic skill learning to energy efficient dynamic motion planning using optimized Dynamic Movement Primitives 利用优化的动态运动原语将运动学技能学习推广到节能动态运动规划中

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 基于多色集的产品装配精度数字孪生模型步进驱动框架

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 提出了一种基于深度强化学习的协同定制再制造实时调度模型

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 支持视觉语言模型的机器人装配多层次场景图

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 优化铣削任务系列机器人的性能：综述

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 基于实时双手动作分割的人机协作装配质量检测框架

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 基于嵌入式AI传感器的智能机器人抓手箱重排序系统集成空间布局优化

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

A high-precision digital twin modeling approach for the serial-parallel hybrid drilling robot in aircraft assembly 飞机装配中串并联混合钻井机器人的高精度数字孪生建模方法

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.2025.102986

Ruihao Kang , Junshan Hu , Zhanghu Shi , Jiawei Zhang , Zhengping Li , Zhihao Li , Wei Tian

{"title":"A high-precision digital twin modeling approach for the serial-parallel hybrid drilling robot in aircraft assembly","authors":"Ruihao Kang , Junshan Hu , Zhanghu Shi , Jiawei Zhang , Zhengping Li , Zhihao Li , Wei Tian","doi":"10.1016/j.rcim.2025.102986","DOIUrl":"10.1016/j.rcim.2025.102986","url":null,"abstract":"<div><div>Digital twin (DT) models with high-fidelity could map physical entity states precisely, raise the credibility of simulation, enhance the accuracy of processing decisions and improve feedback control precision in intelligent manufacturing, while the modeling process is frequently constrained by the complexity of the physical entity structure. This paper aims to propose a high-precision DT modeling method for aircraft assembly equipment and a drilling robot system with complex structures is taken as the research object. A physical model detailing the structure of the hybrid drilling robot is developed via the combination of Denavit-Hartenberg (D-H) and the virtual mechanism methods. A logical model is established based on the kinematic model of the hybrid drilling robot to express its behavior for drilling. The Levenberg-Marquardt (L-M) least-squares method is applied for calibration of DT model, which reduces the influence of geometric errors by identifying structural parameters in the physical model. The average position and normal errors have decreased to 1/10 and 1/8 respectively compared to before calibration, leading to enhanced accuracy in DT modeling. DT control software is developed to integrate physical model and logical model and is combined with hybrid drilling robot to construct DT system. The drilling quality experiment of DT system for flat and single curvature plates is designed and the results showed that the average positioning errors after the DT model calibrated are reduced by 39.29 % and 49.25 %, respectively. In addition, these drilling quality meets the drilling requirements of large aircraft body fastener assemblies.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"94 ","pages":"Article 102986"},"PeriodicalIF":9.1,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143402988","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

3D curve weld seam path and posture planning based on line laser sensors 基于直线激光传感器的三维曲线焊缝路径与姿态规划

IF 9.1 1区计算机科学

Robotics and Computer-integrated Manufacturing Pub Date : 2025-02-11 DOI: 10.1016/j.rcim.2025.102985

Hui Wang , Youmin Rong , Songming Xiang , Jiajun Xu , Yifan Peng , Yu Huang

{"title":"3D curve weld seam path and posture planning based on line laser sensors","authors":"Hui Wang , Youmin Rong , Songming Xiang , Jiajun Xu , Yifan Peng , Yu Huang","doi":"10.1016/j.rcim.2025.102985","DOIUrl":"10.1016/j.rcim.2025.102985","url":null,"abstract":"<div><div>The range of welding scenarios is expanding and becoming more complex in line with the development of manufacturing, which has led to increased demand for automatic and intelligent welding solutions. Line laser sensors are a crucial tool and technology in achieving intelligent welding. However, with the rise in the diversity of weld types and welding parts, the increasingly complex welded components pose challenges to point cloud construction. In contrast, the fixed posture of the welding torch in conventional digital welding makes it difficult to meet the welding needs of 3D curve weld seam. Therefore, this paper proposed a point cloud construction method based on robot pose. Firstly, the multi coordinate system transformation relationship was solved, and precise coordinate transformation between multi frame point clouds was achieved through coordinate transformation matrix, constructing a complex weld seam point cloud model. Furthermore, the point cloud was processed to extract weld seam information with the Ransac algorithm. Based on this, considering the characteristics of robot motion, the welding torch posture is divided into three components: deflection angle, elevation angle, and rotation angle, each of which is calculated separately to achieve welding posture planning. Experimental results have shown that the accuracy of the point cloud construction method proposed in this paper is better than 0.2mm, and the planning errors of the three posture angles are 0.75°, 1.2°, and 0.28°, which aligns well with the requirements of practical welding operations.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"94 ","pages":"Article 102985"},"PeriodicalIF":9.1,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143378528","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

Integrating large language model and digital twins in the context of industry 5.0: Framework, challenges and opportunities 工业5.0背景下大型语言模型与数字孪生的集成：框架、挑战与机遇

IF 9.1 1区计算机科学

Robotics and Computer-integrated Manufacturing Pub Date : 2025-02-10 DOI: 10.1016/j.rcim.2025.102982

Chong Chen , Kuanhong Zhao , Jiewu Leng , Chao Liu , Junming Fan , Pai Zheng

{"title":"Integrating large language model and digital twins in the context of industry 5.0: Framework, challenges and opportunities","authors":"Chong Chen , Kuanhong Zhao , Jiewu Leng , Chao Liu , Junming Fan , Pai Zheng","doi":"10.1016/j.rcim.2025.102982","DOIUrl":"10.1016/j.rcim.2025.102982","url":null,"abstract":"<div><div>In Industry 5.0, where human ingenuity is combined with cutting-edge technologies such as artificial intelligence (AI) and robotics to revolutionize manufacturing with a focus on sustainability and human well-being, Digital Twins (DT) have become essential to real-time optimization. However, the complexity of managing DT for large-scale systems poses challenges in terms of data transmission, analytics, and advanced applications, which can be potentially addressed by Large Language Model (LLM). This research firstly performs a literature review to study the roles and functions of LLM in DT in the context of Industry 5.0. Subsequently, we propose a framework named Interactive-DT for LLM-DT integration that reveals the technical pathway for how LLM can be effectively integrated and function within DT environments. Within this framework, the roles and functionalities of LLM at the edge layer, DT layer, and service layer are elaborated upon. Finally, the identified research gaps and prospects for the integration of LLM and DT are outlined and discussed. The research outcomes of this paper highlight the potential of LLM to augment DT capabilities through improved construction and operation, enhanced cloud-edge collaboration, and sophisticated data analytics, ultimately promoting industrial practices that are both efficient and aligned with human-centric and sustainability principles in Industry 5.0.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"94 ","pages":"Article 102982"},"PeriodicalIF":9.1,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376499","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