Robotics and Computer-integrated Manufacturing最新文献

{"title":"Long short term robot safe control framework based on hidden action space heuristic soft actor–critic","authors":"Yixuan Liang,&nbsp;Ze Wang,&nbsp;Yunan Wang,&nbsp;Jichuan Yu,&nbsp;Jizhou Yan,&nbsp;Shize Lin,&nbsp;Zhao Jin,&nbsp;Jiuru Lu,&nbsp;Chuxiong Hu","doi":"10.1016/j.rcim.2025.103107","DOIUrl":"10.1016/j.rcim.2025.103107","url":null,"abstract":"<div><div>Real-time safety control for robots in dynamic environments is a critical and challenging problem in robotics. With the advent of intelligent manufacturing, the demand for advanced safety control technologies in robotics has steadily increased. Robot planning typically involves global and local approaches, but both face limitations in real-time safety control in dynamic environments with unknown obstacles. Recent hybrid frameworks have shown progress, but challenges persist, including limited perception capabilities and poor coordination between global and local components. To address these challenges, this work proposes a novel long short term safety control framework leveraging reinforcement learning for decision-making. Perception and planning are decoupled into long-term and short-term components, with long-term perception utilizing unsupervised clustering DBSCAN for structured environment information and short-term perception enhancing efficiency through prior knowledge. Long-term planning provides reference trajectories based on static environments, while short-term planning adjusts these trajectories in real time for local safety using control barrier functions. Based on hidden action heuristic soft actor–critic and curriculum learning, the decision-making mechanism ensures safety during obstacles or attacks and maximizes robot efficiency without compromising safety. Experiments are conducted with 10,000 randomized obstacle collision scenarios, and our framework is compared with four methods, including SAC and manually designed trajectory adjustment. The results demonstrate that our approach outperforms these methods in both safety performance and operational efficiency. Finally, the system is successfully implemented in a physical environment, showcasing its practical potential for real-world applications.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"98 ","pages":"Article 103107"},"PeriodicalIF":11.4,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145021002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Modeling flexible configuration of cell finishing for future battery production research","authors":"Sicong Deng ,&nbsp;Jonas Wieskamp ,&nbsp;Henrik Born ,&nbsp;Heiner Hans Heimes ,&nbsp;Achim Kampker","doi":"10.1016/j.rcim.2025.103119","DOIUrl":"10.1016/j.rcim.2025.103119","url":null,"abstract":"<div><div>Today, the increasing demand for battery cells requires efficient large-scale production. At the same time, cell design continues to improve regarding various performance metrics causing product feature changes, which in turn affect the process chain, equipment and process parameter design in production. In cell finishing – the final cell production section – both external cell features, related to the system components, and internal cell features, related to process protocol, are directly affected. However, the interrelations between the core domains – product, process, parameters and equipment – are hardly assessed in the current cell finishing planning and thus no systematic approach to configuration design has been established. This paper focuses on this research need and presents an approach through configuration modeling based on Modularization and Knowledge-Based Design and uses real data from factory planning. From the analyzed raw data, a structured database of product, process, parameters, equipment and their interrelations are derived. For this modeling approach, the paper first explains the conceptual framework. Then, it introduces domains and sub-domains of the database and their formalization for modeling. Subsequently, the architecture of a Two-Stage Configuration Model is explained for flexible configurations (first stage) and virtual modeling (second stage). Finally, the modeling approach is implemented for a real case of prismatic cell finishing. It demonstrates how various configurations can be systematically generated and visualized based on design requirements to advance design optimizations in cell finishing for research purposes and industrial application.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"98 ","pages":"Article 103119"},"PeriodicalIF":11.4,"publicationDate":"2025-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145007612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Force-sensing-based compliant error compensation control for robotic milling of weak-stiffness thin-walled components","authors":"Qunfei Gu ,&nbsp;Shun Liu ,&nbsp;Sun Jin ,&nbsp;Dong Liu","doi":"10.1016/j.rcim.2025.103121","DOIUrl":"10.1016/j.rcim.2025.103121","url":null,"abstract":"<div><div>Industrial robots hold considerable potential in the field of milling operations. However, due to their structural characteristics, significant machining errors often occur during the milling process. For the robotic milling, existing research rarely provides direct control strategies for machining error compensation, which limits the further application of industrial robots in high-precision machining tasks. To enhance the robotic milling accuracy, this paper proposes an error compensation control method based on force sensing. First, to predict the relationship between cutting forces and machining parameters, an improved cutting force model is developed by introducing the material removal parameter S_l. Combining the cutting force signals with the robot's position data, the machining error can be predicted. Furthermore, by considering the stiffness characteristics of both the robot and the workpiece, an error compensation control method is proposed. The initial milling trajectory is generated using the robot’s spatial pose and the workpiece model. Based on force sensing and the desired machining accuracy, the cutting parameters are adaptively adjusted. A data-driven adaptive parameter adjustment strategy is further proposed by integrating robot motion data, machining data, and cutting force signals. By adjusting the feed rate in different out-of-tolerance regions, a new compensated milling trajectory is generated to correct machining errors. To validate the effectiveness of the proposed method, robotic milling experiments were conducted on thin-walled light alloy workpieces and feature components. The experimental results demonstrate that the proposed approach significantly reduces machining errors in robotic milling, thereby improving both machining quality and efficiency. These results indicate that the proposed method has strong potential for high-precision robotic milling of complex thin-walled structures.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"98 ","pages":"Article 103121"},"PeriodicalIF":11.4,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145005338","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Inverse calibration of kinematic error for parallel kinematic mechanism based on deviation of multi-DOF formed component","authors":"Bo Huang ,&nbsp;Xinghui Han ,&nbsp;Fangyan Zheng ,&nbsp;Lin Hua ,&nbsp;Wuhao Zhuang","doi":"10.1016/j.rcim.2025.103116","DOIUrl":"10.1016/j.rcim.2025.103116","url":null,"abstract":"<div><div>In the multi-DOF forming process, it is critical to calibrate kinematic error for forming machine with parallel kinematic mechanism (PKM). However, on one hand, the detection process of kinematic error is complex due to the limited workspace and highly dynamic forming process. On the other hand, the kinematic error sources of forming machine are diverse and thus the kinematic error modeling is complex. So, this paper proposes a novel inverse calibration method of kinematic error for PKM based on deviation of multi-DOF formed thin-wall and high-rib component (THC), which is convenient and efficient. Firstly, the minimal error model of PKM is established based on screw theory, in which the minimal 108 kinematic errors are used to represent multi-error sources and the mapping relationship between 108 kinematic errors and upper die motion error is established. Then, the deviation prediction model of multi-DOF formed THC is established by the upper die motion error. It is found that 108 kinematic errors have different sensitivities to the upper die motion error and the distribution of multi-DOF formed THC deviation. Based on the above mechanism, the optimal calibration points on multi-DOF formed THC are planned. The inverse mapping relationship between the deviation of calibration points on THC and the upper die motion error is established, and the inverse calibration of kinematic error for PKM is realized. Finally, multi-DOF forming experiments of THC are carried out, and the deviation of formed THC without inverse calibration is -90∼384 μm. After the inverse calibration, the deviation of formed THC with optimal calibration points is -17∼84 μm while the deviation of formed THC with random calibration points is -29∼131 μm. That is, the accuracy of formed THC with inverse calibration is improved by about 3∼4 times compared to that without inverse calibration. Further, the accuracy of formed THC with optimal calibration points is significantly improved by about 37% compared to that with random calibration points. This research demonstrates that the proposed convenient and efficient inverse calibration method of kinematic error for PKM based on deviation of multi-DOF formed THC is reasonable.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"98 ","pages":"Article 103116"},"PeriodicalIF":11.4,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144997770","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Smooth, rigid, and dexterous robotic machining path planning based on on-site scanned point clouds","authors":"Gang Wang ,&nbsp;Xijing Cui ,&nbsp;Huayan Pu ,&nbsp;Qingyu Peng ,&nbsp;Zhoulong Li ,&nbsp;Xuyang Zheng ,&nbsp;Wenlong Li ,&nbsp;Jun Luo","doi":"10.1016/j.rcim.2025.103114","DOIUrl":"10.1016/j.rcim.2025.103114","url":null,"abstract":"<div><div>Industrial robots with integrated sensing units possess the advantages of parallelism, dexterity, and intelligent operation, making them a cost-effective alternative to large and expensive machine tools for processing large and complex parts such as aircraft skins, ship hulls, and wind turbine blades. These complex parts are susceptible to deformation during transportation, clamping, and assembly. Therefore, employing robots to perform on-site scanning of clamped parts to acquire point clouds and subsequently conducting adaptive machining path planning based on these point clouds is a viable approach. In this paper, a novel method for planning a smooth, rigid, and dexterous robotic machining path based on on-site scanned point clouds is presented, which is suitable for the semi-finishing or finishing stages. First, a dual quaternion non-uniform rational B-spline (NURBS) curve fitting method is proposed to generate a smooth tool path from the point clouds. Then, to address the functional redundancy of the robot, a method is proposed to select the postures of all machining path points, optimizing the smoothness of the robot's joint space trajectory, rigidity, and dexterity under the constraints of joint limitations and avoiding collisions. A directed graph with robot configurations as its nodes is constructed, and an improved A* algorithm is proposed to find the shortest path in the directed graph. We conducted simulations and actual robotic cutting experiments, which demonstrated that executable robotic machining paths can be obtained, achieving a superior balance of joint space trajectory smoothness, rigidity, and dexterity.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"98 ","pages":"Article 103114"},"PeriodicalIF":11.4,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144997771","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DSF-Net: Dual-Space frequency dynamic network for spacecraft thermal control coating defect detection","authors":"Kailin Hou ,&nbsp;Rongyi Li ,&nbsp;Xianli Liu ,&nbsp;Xiaohua Liu ,&nbsp;Ying Wang ,&nbsp;Caixu Yue ,&nbsp;Haining Gao","doi":"10.1016/j.rcim.2025.103117","DOIUrl":"10.1016/j.rcim.2025.103117","url":null,"abstract":"<div><div>Thermal control coatings are critical functional materials for high-end equipment such as spacecraft, directly affecting their operational stability and service life. During manufacturing, process parameter fluctuations and material contamination can easily cause various defects including crystal points, blemishes, and wrinkles. Traditional detection methods struggle to meet industrial real-time and high-precision requirements. Existing deep learning algorithms for spacecraft thermal control coating detection face three major challenges: lack of standardized industrial datasets, complex industrial lighting conditions interfering with feature extraction, and decreased recognition accuracy when multiple defects coexist. To address these issues, this paper first establishes an industrial-grade thermal control coating defect dataset (ITCCD), covering six typical defect types including crystal points and blemishes. Through frequency domain analysis, this paper reveals the spectral feature distribution patterns of different defect types and establishes the relationship between defect characteristics and frequency domain representation. Based on these findings, this paper designs a Dual-Space Frequency Dynamic Network (DSF-Net) with two key technical innovations: (1) a Dynamic Inception Mixer backbone network using cascaded dual-stage architecture with adaptive weight allocation mechanism; (2) a frequency-aware feature fusion module that implements frequency domain mapping and decoupling through learnable frequency response functions. Experimental results on the ITCCD dataset show that DSF-Net achieves 83.0 % on the mAP50, outperforming the best comparison model by 7.4 %, while reducing parameters by 23.9 %. Notably, detection accuracy for challenging defect types such as crystal points and blemishes improved by 22.7 % and 13.3 % respectively. This research constructs a standardized dataset and improves defect detection accuracy under complex lighting conditions through a frequency domain analysis framework. The proposed frequency domain feature decoupling method provides a new approach for material surface defect detection. DSF-Net achieves end-to-end detection while maintaining high accuracy, providing an effective technical solution for online quality control of thermal control coatings.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"98 ","pages":"Article 103117"},"PeriodicalIF":11.4,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144997769","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"LLM based autonomous agent of human-robot collaboration for aerospace wire harnessing assembly","authors":"Yiwei Wang ,&nbsp;Qi Guo ,&nbsp;Lianyu Zheng ,&nbsp;Binbin Wang ,&nbsp;Pai Zheng ,&nbsp;Zhonghua Qi","doi":"10.1016/j.rcim.2025.103120","DOIUrl":"10.1016/j.rcim.2025.103120","url":null,"abstract":"<div><div>The fusion of large language models (LLMs) and robotic system bring transformative potential to human-robot collaboration (HRC). Existing LLMs-based HRC methods mainly realize on fine-tune techniques, which has the shortcomings such as damage of the inherent ability of original LLMs, difficulty performing complex continuous task, less flexibility, fixed response strategy and computationally expensive. Alternatively, the development paradigm of LLM applications is transiting towards the autonomous agent mode. This paper proposed an interesting LLM agent based HRC framework (or HRC agent), which empowers the robot with human’s think mode and execution ability of sensing, interaction, self-reasoning, task planning and task execution. The chain-of-thought technique that generates a series of intermediate reasoning steps is adopted to improve the ability of LLMs to execute complex reasoning and task. Few-shot learning is used such that HRC agent can quickly learns new specific industry tasks by being provided a few examples. The reflection-based contextual memory mechanism enables HRC agent to have long term memory and continuous instruction understanding ability. A series of tools are developed and integrated into HRC agent, by which the capabilities of HRC agent can be easily expanded without much changing of the code framework. The functionality and effectiveness of HRC agent is validated in the aerospace wire harnessing assembly task, whose products has the characteristics of small diameter wires, complicated wire text, dense and tiny assembly holes, varying product batch size and customized production, and thus has high requirements for flexibility. The results show that the HRC agent is able to well understand the natural language instructions and give correct and effective response by chain-of-though, and subsequently, drive the robot to execute tasks correctly by calling tools.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"97 ","pages":"Article 103120"},"PeriodicalIF":11.4,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144932216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Transformation of industrial robotics with natural language models: Recent progress and future prospects","authors":"Zhao Yu,&nbsp;Peize Zhang,&nbsp;Jing Shi","doi":"10.1016/j.rcim.2025.103113","DOIUrl":"10.1016/j.rcim.2025.103113","url":null,"abstract":"<div><div>Integration of Natural Language Models (NLMs) into industrial robots enhances operational efficiency and intuitive human-robot interactions, and thus it represents a significant opportunity in the pursuit of Industry 4.0/5.0. This paper provides a comprehensive survey on the technological advancements and applications in this area, by emphasizing their role in improving task execution, cognitive capabilities, and communication in the industrial environments. Meanwhile, related challenges are analyzed and discussed. In particular, NLMs inherently struggle with contextual understanding, which can lead to inappropriate or impractical outputs in complex industrial environments. Also, the external noise and the need for real-time responsiveness present further complications to the effectiveness of NLMs. Concerns regarding safety, transparency, privacy, and ethical usage amplify the need for regulatory considerations. In addition, standardized approaches to interpreting vague human instructions are called for to improve the interaction between humans and robots. It is pointed out that the broader impacts of NLMs can extend beyond industrial environments into commercial and social settings, thereby enhancing service quality and customer interactions. As a result, the review is expected to provide insights on how to effectively integrate NLMs with robotic systems, stimulate research to address the remaining challenges, and enhance transparency to improve social acceptability.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"97 ","pages":"Article 103113"},"PeriodicalIF":11.4,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144924723","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A review on deep learning for vision-based hand detection, hand segmentation and hand gesture recognition in human–robot interaction","authors":"Reza Jalayer ,&nbsp;Masoud Jalayer ,&nbsp;Carlotta Orsenigo ,&nbsp;Masayoshi Tomizuka","doi":"10.1016/j.rcim.2025.103110","DOIUrl":"10.1016/j.rcim.2025.103110","url":null,"abstract":"<div><div>Hand-based analysis, including hand detection, segmentation, and gesture recognition, plays a pivotal role in enabling natural and intuitive human–robot interaction (HRI). Recent advances in vision-based deep learning (DL) have significantly improved robots’ ability to interpret hand cues across diverse settings. However, previous reviews have not addressed all three tasks collectively or focused on recent DL architectures. Filling this gap, we review recent studies at the intersection of DL and hand-based interaction in HRI. We structure the literature around three core tasks, i.e. hand detection, segmentation, and gesture recognition, highlighting DL models, dataset characteristics, evaluation metrics, and key challenges for each. We further examine the application of these models across industrial, assistive, social, aerial, and space robotics domains. We identify the dominant role of Convolutional and Recurrent Neural Networks (CNNs and RNNs), as well as emerging approaches such as attention-based models (Transformers), uncertainty-aware models, Graph Neural Networks (GNNs), and foundation models, i.e. Vision-Language Models (VLMs) and Large Language Models (LLMs). Our analysis reveals gaps, including the scarcity of HRI-specific datasets, underrepresentation of multi-hand and multi-user scenarios, limited use of RGBD and multi-modal inputs, weak cross-dataset generalization, and inconsistent real-time benchmarking. Dynamic and long-range gestures, multi-view setups, and context-aware understanding also remain relatively underexplored. Despite these limitations, promising directions have emerged, such as multi-modal fusion, use of foundation models for intent reasoning, and the development of lightweight architectures for deployment. This review offers a consolidated foundation to support future research on robust and context-aware DL systems for hand-centric HRI.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"97 ","pages":"Article 103110"},"PeriodicalIF":11.4,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144932265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Geometrical quality prediction of machining process by Exechon X-mini PKM through deformation modelling and error compensation","authors":"Shakya Bandara ,&nbsp;Yan Jin ,&nbsp;Mien Van ,&nbsp;Dan Sun ,&nbsp;Rao Fu ,&nbsp;Patrick Curley ,&nbsp;Glenn Rutherford ,&nbsp;Colm Higgins","doi":"10.1016/j.rcim.2025.103115","DOIUrl":"10.1016/j.rcim.2025.103115","url":null,"abstract":"<div><div>Parallel Kinematic Machines (PKMs) offer enhanced motion dynamics and flexibility, bridging the gap between conventional CNC machines and industrial robots. Stiffness, a key determinant of machining accuracy, is often modelled with limited consideration of gravitational effects, leading to reduced predictive accuracy. This paper introduces a novel stiffness modelling approach that integrates a theoretical model without gravity and gravity-based parameter optimisation through experimental analysis. Comprehensive stiffness measurements were conducted to isolate gravitational effects on the machine structure, enabling precise calibration of the theoretical model for accurate stiffness prediction. A six-dimensional stiffness analysis of the X-Mini machine tool using the optimised model demonstrated improved prediction accuracy, reducing errors by 14 %, 21 %, and 8 % in the X, Y and Z directions, respectively. Predicted stiffness and estimated cutting forces were used to compute workspace deformations, which were then compensated by modifying the depth of cut in slot milling. Experimental validation demonstrated the method’s effectiveness, achieving a machined shape error prediction accuracy of 6–9 µm. This approach can be well applied to shape quality prediction of machined parts by robots and machine tools.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"97 ","pages":"Article 103115"},"PeriodicalIF":11.4,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144921297","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}