Robotics and Computer-integrated Manufacturing最新文献

{"title":"Non-prehensile tool-object manipulation by integrating LLM-based planning and manoeuvrability-driven controls","authors":"Hoi-Yin Lee ,&nbsp;Peng Zhou ,&nbsp;Anqing Duan ,&nbsp;Wanyu Ma ,&nbsp;Chenguang Yang ,&nbsp;David Navarro-Alarcon","doi":"10.1016/j.rcim.2026.103231","DOIUrl":"10.1016/j.rcim.2026.103231","url":null,"abstract":"<div><div>The ability to wield tools was once considered exclusive to human intelligence, but it is now known that many other animals, like crows, possess this capability. Yet, robotic systems still fall short of matching biological dexterity. In this paper, we investigate the use of Large Language Models (LLMs), tool affordances, and object manoeuvrability for non-prehensile tool-based manipulation tasks. Our novel method leverages LLMs based on scene information and natural language instructions to enable symbolic task planning for tool-object manipulation. This approach allows the system to convert a human language sentence into a sequence of feasible motion functions. We have developed a novel manoeuvrability-driven controller using a new tool affordance model derived from visual feedback. This controller helps guide the robot’s tool utilization and manipulation actions, even within confined areas, using a stepping incremental approach. The proposed methodology is evaluated with experiments to prove its effectiveness under various manipulation scenarios.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"100 ","pages":"Article 103231"},"PeriodicalIF":11.4,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145940156","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 cutting chatter detection and suppression in robotic milling","authors":"Ning Li,&nbsp;Jiaqi Zhao,&nbsp;Ruiduan Sun,&nbsp;Li Cui,&nbsp;Xin Wang","doi":"10.1016/j.rcim.2025.103219","DOIUrl":"10.1016/j.rcim.2025.103219","url":null,"abstract":"<div><div>Robotic milling offers high manufacturing flexibility and reduced tooling costs for machining large, complex workpieces, but its inherently low structural stiffness makes it highly prone to cutting chatter. Chatter deteriorates surface quality and dimensional accuracy, accelerates tool wear, and may compromise robotic system safety. This review comprehensively examines cutting chatter in robotic milling, focusing on mechanisms, monitoring, and suppression strategies. First, it analyses robot-specific chatter mechanisms, including regenerative and modal coupling effects, posture-dependent compliant multi-body dynamics, and nonlinear chatter phenomena within unified rigid–flexible and multi-body dynamic frameworks. Second, chatter monitoring and diagnosis methods are summarised, spanning classical time–frequency and cyclostationary analysis to advanced data-driven and deep learning techniques, with emphasis on multi-sensor fusion and real-time edge deployment in robotic settings. Third, chatter suppression and control strategies are reviewed, covering machining parameter and robot pose optimisation, passive and active damping (e.g., tuned mass dampers, smart materials), and emerging reinforcement learning techniques and digital twin-based approaches. Unlike prior surveys focusing on conventional CNC machines or treating dynamics, detection, and control in isolation, this review uniquely addresses the interplay of posture-dependent robot dynamics with chatter across all stages. By highlighting distinctive challenges such as nonlinear chatter in compliant robotic systems and discussing state-of-the-art solutions, it clarifies research gaps and provides guidance for achieving stable, high-precision robotic milling.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"100 ","pages":"Article 103219"},"PeriodicalIF":11.4,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145902455","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":"Large language models for high-level computer-aided process planning in a distributed manufacturing paradigm","authors":"Emmanuel Stathatos ,&nbsp;Panorios Benardos ,&nbsp;George-Christopher Vosniakos ,&nbsp;Dennis Gross ,&nbsp;Helge Spieker ,&nbsp;Arnaud Gotlieb","doi":"10.1016/j.rcim.2026.103233","DOIUrl":"10.1016/j.rcim.2026.103233","url":null,"abstract":"<div><div>This study applies Large Language Models (LLMs) to high-level Computer-Aided Process Planning (CAPP) in a distributed manufacturing context. It aims to generate alternative, feasible process chains for production of a wide range of parts. Parts are encoded in a custom encoding scheme supporting diverse part overall shapes, geometrical features within them, and corresponding manufacturing processes. The CAPP problem is formulated as a sequence prediction task, where a GPT-2-based LLM generates process chains autoregressively. To train and test the LLM a synthetic dataset of 7,840 unique parts and their alternative process chains was generated using expert-driven rule-based logic. The LLM is trained from scratch using a tokenization scheme treating part features and processes uniformly as discrete tokens, special tokens being employed to control sequence flow. Performance evaluation was performed for systematically reducing the size of the dataset. Finally, even with as little as 5% of the training data, the LLM achieves over 99% accuracy at the process chain-level. The extremely few spotted errors mainly involve minor secondary process mispredictions without critical failures. For comparison, a Recurrent Neural Network (RNN) was also trained with the same dataset. Since manufacturing data stemming from experts and not from sensors is notoriously difficult to collect, training a machine learning model with a dataset that is as small as possible is of utmost importance. In this light, the LLM proved superior to RNN, in fact emphatically so, the more the training dataset was limited.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"100 ","pages":"Article 103233"},"PeriodicalIF":11.4,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145956532","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 novel robotic welding trajectory planning system for steel structure workpieces based on vision-guided virtual assembly","authors":"Jiaqi Sun ,&nbsp;Ze’an Liu ,&nbsp;Yanfang Feng ,&nbsp;Feng Pan ,&nbsp;Ke Xiang ,&nbsp;Xuanyin Wang","doi":"10.1016/j.rcim.2026.103243","DOIUrl":"10.1016/j.rcim.2026.103243","url":null,"abstract":"<div><div>The welding robot system plays a crucial role in welding production in the construction industry. However, existing welding trajectory planning methods face challenges in achieving both accuracy and efficiency when dealing with large-scale steel structure workpieces that feature numerous weld seams with complex spatial distributions. Inspired by human welders, who rely on visual perception to assemble components and determine welding trajectories based on feature edges and relative component placement, a novel and flexible welding trajectory planning system based on vision-guided virtual assembly is proposed. The proposed system consists of three core tasks. Firstly, a process for extracting candidate weld seams from CAD mesh models is proposed to delineate potential welding areas for each component. Secondly, a point cloud registration process with multi-scale feature focusing is proposed to achieve accurate vision-guided virtual assembly of the workpiece. Finally, based on the virtual assembly result, a novel process for robotic welding trajectory planning based on the joint analysis of geometric feature edge clusters and spatial mesh distribution is proposed to generate safe and effective robot programs. According to an extensive series of experiments, the proposed robotic welding trajectory planning system effectively overcomes the limitations of existing methods, and achieves accurate and efficient welding of steel structure workpieces in the construction industry.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"100 ","pages":"Article 103243"},"PeriodicalIF":11.4,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146033278","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":"Improve geometric accuracy in robotic forming","authors":"Yanrong Zhang ,&nbsp;Zeran Hou ,&nbsp;Fan Yang ,&nbsp;Bernd Kuhlenkötter ,&nbsp;Antonio Sánchez Egea ,&nbsp;Junying Min","doi":"10.1016/j.rcim.2026.103236","DOIUrl":"10.1016/j.rcim.2026.103236","url":null,"abstract":"<div><div>Robotic forming is a die-less manufacturing process that utilizes single or multiple industrial robots to incrementally deform metal sheets into complex, customized parts. Owing to its high flexibility, it has become an important research direction in the field of intelligent manufacturing due to its high flexibility. However, issues such as complex local deformation mechanisms and insufficient support during robotic forming often lead to low geometric accuracy in fabricated parts, which is one of the most critical factors hindering the broader application of robotic forming in high-precision manufacturing. In this context, this paper presents a comprehensive review of the methods for improving geometric accuracy in robotic forming. Firstly, to address the core issue of geometric accuracy, the categories and origins of geometric errors in robotic forming are systematically examined. Subsequently, typical precision control strategies and related research are categorized into three aspects: process innovation, optimization of process parameters, and tool path planning and compensation. Current challenges associated with each strategy are also summarized. Finally, potential future research directions are discussed, incorporating advanced technologies such as multi-robot forming, artificial intelligence, multi-source data fusion, and digital twins.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"100 ","pages":"Article 103236"},"PeriodicalIF":11.4,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145956531","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":"Towards efficient robotic milling: A novel time-varying feed rate control framework via system analysis and model parameters identification","authors":"Qingyu Peng ,&nbsp;Wenlong Li ,&nbsp;Hanyu Zhang ,&nbsp;Wei Xu ,&nbsp;Gang Wang ,&nbsp;Han Ding","doi":"10.1016/j.rcim.2026.103229","DOIUrl":"10.1016/j.rcim.2026.103229","url":null,"abstract":"<div><div>In robotic milling, feed rate is a pivotal factor in machining efficiency and quality. A common strategy is to maintain a lower feed rate to ensure system stability. However, this method lacks specific analysis of the robotic milling system, and the feed rate is typically set conservatively based on empirical experience. To address this limitation and achieve both high efficiency and machining quality, a novel time-varying feed rate control framework is proposed. The framework first schedules a time-varying feed rate through a system analysis of robotic milling, which accounts for the robot’s kinematic performance and the maximum vibration amplitude of thin-walled parts. It then introduces a parameter identification module that estimates the dynamic feed rate model parameters, thereby enhancing the designed controller and ensuring that the actual feed rate closely tracks the scheduled feed rate. Furthermore, an active controller with an event-triggered mechanism is proposed to update the identified parameters in real time, ensuring improved control accuracy. Experimental results validate the effectiveness of the proposed method, demonstrating that the machining efficiencies of two different skin parts with varying dimensions are improved by 29.3% and 41.5%, respectively, while maintaining machining quality. In addition, application verification experiment on a real horizontal tail skin part further confirms the practical potential of the proposed method.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"100 ","pages":"Article 103229"},"PeriodicalIF":11.4,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145979601","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 negative-pressure-based surface-compliant constant-force grinding end-effector for climbing machining robots","authors":"Zeyu Gong ,&nbsp;Junhui Huang ,&nbsp;Ying Shi ,&nbsp;Yaonan Wang ,&nbsp;Bo Tao","doi":"10.1016/j.rcim.2026.103241","DOIUrl":"10.1016/j.rcim.2026.103241","url":null,"abstract":"<div><div>Climbing robots, with their unique adsorption and locomotion mechanisms, overcome the accessibility limitations of traditional robots, offering innovative solutions for manufacturing large and complex components such as aircraft skins and wind turbine blades. This paper proposes a specialized grinding end-effector with surface-conforming and force control capabilities for climbing robots, targeting surface finishing tasks. A surface-adaptive module driven by vacuum suction force is introduced, enabling both 3-degree-of-freedom posture self-adjustment and dust collection for the end-effector using only a single centrifugal fan. Building upon this, a force control module decoupled from posture adaptation is designed. Utilizing voice coil motor (VCM) actuation, it integrates parallel force transmission and feedback mechanisms among the VCM, grinding head, and force sensor, combined with PID force control algorithms, to achieve high-precision grinding force regulation. Experiments conducted on both curved aluminum alloy skins and real aircraft skin workpiece demonstrate that the proposed end-effector achieves high-accuracy adaptive normal-direction tracking and constant grinding force control, with posture errors as low as 1.59° and average force errors of 0.18 N. The grinding process effectively activates workpiece surfaces and significantly improves surface roughness uniformity, proving that the proposed end-effector empowers climbing robots to perform high-quality surface finishing operations on curved structures.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"100 ","pages":"Article 103241"},"PeriodicalIF":11.4,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145979602","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":"An enhanced sample generation method for improving flexibility in human-robot cooperative disassembly of end-of-life products","authors":"Yicong Gao ,&nbsp;Chen Xu ,&nbsp;Shanhe Lou ,&nbsp;Jianrong Tan","doi":"10.1016/j.rcim.2025.103218","DOIUrl":"10.1016/j.rcim.2025.103218","url":null,"abstract":"<div><div>Industrial manufacturing is evolving towards adaptable and intelligent frameworks. Remanufacturing plays a critical role in promoting resource efficiency and resilience, particularly within the paradigm of Industry 5.0. As a foundational step in remanufacturing, disassembly benefits significantly from human-robot cooperative disassembly (HRCD), which synergistically integrates manual dexterity with robotic repeatability. However, uncertainties such as rusty screws might disable the pre-defined disassembly schedules. Computer vision systems (CVS) are integrated into HRCD to assess rusty screws and assist task allocation. Due to the combinatorial complexity of defects, the efficacy of CVS is constrained by the lack of varied defect datasets. This paper proposes the Physics-Constrained Defect Style Transfer Network (PhysDef-STN) to generate samples of screws with diverse types and severities of rusty screws. Realistic scenarios of screw rust were investigated and modeled for deriving related formulas under physicochemical limitations, which was employed as the unique physics-inspired loss function and incorporated into PhysDef-STN to generate high-quality and diversified images of rusty screws. These generated samples resolve the critical challenge of insufficient defect datasets and enable robust and precise detection of varied uncertain screw conditions that hindered adaptive task allocation. Experimental validation confirms that the dataset generated by PhysDef-STN substantially increases the diversity of rusted screws and significantly improves the efficacy of a vision model for rust detection and classification, which achieves up to 95% identification accuracy and 88% classification accuracy. An illustrative case study demonstrates the proposed method's feasibility and practical efficacy, which involves the human-robot cooperative disassembly of a control box. The results reveal that specific uncertainties such as various types and severities of rusty screws are precisely identified and used in task assignments between human operators and robots. It significantly improves the robustness and efficiency of the disassembly process by preventing potential failures.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"100 ","pages":"Article 103218"},"PeriodicalIF":11.4,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145894581","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":"VL-GRiP3: A hierarchical pipeline leveraging vision-language models for autonomous robotic 3D grasping","authors":"Mirco Polonara ,&nbsp;Xingyu Yang ,&nbsp;Luca Carbonari ,&nbsp;Xuping Zhang","doi":"10.1016/j.rcim.2026.103244","DOIUrl":"10.1016/j.rcim.2026.103244","url":null,"abstract":"<div><div>Autonomous grasping has long been a central topic in robotics, yet deployment in small and medium-sized enterprises (SMEs) is still hindered by low-level robot programming and the lack of natural language interaction. Recent Vision-Language-Action models (VLAs) allow robots to interpret natural language commands for intuitive interaction and control, but they still exhibit output uncertainty and are not yet well suited to directly generating reliable, precise actions in safety-critical industrial contexts. To address this gap, we present VL-GRiP3, a hierarchical Vision-Language model (VLM)-enabled pipeline for autonomous 3D robotic grasping that bridges natural language interaction and accurate, reliable manipulation in SME settings. The framework decomposes language understanding, perception, and action planning in a transparent modular architecture, improving flexibility and interpretability. Within this architecture, a single VLM backbone handles natural language interpretation, target perception, and high-level action planning. CAD-augmented point cloud registration then mitigates occlusions in single RGB-D views while keeping hardware cost low, and an M2T2-based grasp planner predicts accurate 3D grasp poses that explicitly account for complex object geometry from the augmented point cloud, enabling reliable manipulation of irregular industrial parts. Experiments show that our fine-tuned VLM modules achieve segmentation performance comparable to YOLOv8n, and VL-GRiP3 attains a 94.67% success rate over 150 randomized grasping trials. A comparative evaluation against state-of-the-art end-to-end VLAs further indicates that our modular, CAD-augmented design with explicit 3D grasp pose prediction yields more reliable and controllable behavior for SME manufacturing applications.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"100 ","pages":"Article 103244"},"PeriodicalIF":11.4,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146048118","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":"Physics-informed prediction of modal parameters and stability analysis for robotic mirror milling","authors":"Kun Chen ,&nbsp;Haonan Ma ,&nbsp;Chenghao Huang ,&nbsp;Sheng Xu ,&nbsp;Peng Xu ,&nbsp;Bing Li","doi":"10.1016/j.rcim.2026.103237","DOIUrl":"10.1016/j.rcim.2026.103237","url":null,"abstract":"<div><div>Mirror milling technology is widely used in the aerospace industry for manufacturing thin-walled parts, yet existing machine tool-based mirror milling systems are costly and inflexible. Robotic mirror milling system is a cost-effective and flexible alternative to machine tools. However, the modal parameters of the mirror-arranged robots vary with their postures, and the robots’ low stiffness, coupled with the flexibility of thin-walled parts, leads to unstable milling processes. To address these challenges, a physics-informed framework is proposed for modal parameters measurement, prediction, and optimization, thereby analyzing the robotic mirror milling stability. First, the robot’s vibration characteristics are examined through transfer matrices of dynamic models, while the robot’s modal parameters are collected at uniform configurations in joint space. Using these characteristics and measurements as physical constraints and training sets, a modified multi-task Gaussian process regression is developed to predict the modal parameters, with the results further optimized through the Bayesian derivation. This two-step process forms the physics-informed modal parameters prediction method. Then, the obtained modal parameters are utilized to construct the robotic mirror milling system’s dynamic model, which can analyze its milling stability. Simulations and experiments are conducted to confirm these theories and algorithms.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"100 ","pages":"Article 103237"},"PeriodicalIF":11.4,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146014514","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}