Pub Date : 2025-01-29DOI: 10.1016/j.rcim.2025.102973
Morteza Dianatfar , Eeva Järvenpää , Niko Siltala , Minna Lanz
The industry 4.0 vision has accelerated technology development, particularly in the use of augmented reality (AR) and virtual reality (VR) in industry, such as the metaverse. However, creating VR environments is known to be a laborious task, which means their full potential is not yet fully utilized. There is a need for a reusable VR model that enables faster generation and population of VR environments. This research aims to find solutions for quicker development and deployment of VR environments in an industrial context. Specifically, this paper proposes one solution for creating and modifying these environments more efficiently. The focus of the research, along with the associated industrial use cases, is to develop safety training for human–robot collaboration in final assembly scenarios using VR environments. The paper will introduce a template concept, which includes individual templates and the full architecture to deploy these templates, allowing for faster modification of VR environments to meet specific use case needs. This template concept is developed using two separate use cases from academia and industry.
{"title":"Template concept for VR environments: A case study in VR-based safety training for human–robot collaboration","authors":"Morteza Dianatfar , Eeva Järvenpää , Niko Siltala , Minna Lanz","doi":"10.1016/j.rcim.2025.102973","DOIUrl":"10.1016/j.rcim.2025.102973","url":null,"abstract":"<div><div>The industry 4.0 vision has accelerated technology development, particularly in the use of augmented reality (AR) and virtual reality (VR) in industry, such as the metaverse. However, creating VR environments is known to be a laborious task, which means their full potential is not yet fully utilized. There is a need for a reusable VR model that enables faster generation and population of VR environments. This research aims to find solutions for quicker development and deployment of VR environments in an industrial context. Specifically, this paper proposes one solution for creating and modifying these environments more efficiently. The focus of the research, along with the associated industrial use cases, is to develop safety training for human–robot collaboration in final assembly scenarios using VR environments. The paper will introduce a template concept, which includes individual templates and the full architecture to deploy these templates, allowing for faster modification of VR environments to meet specific use case needs. This template concept is developed using two separate use cases from academia and industry.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"94 ","pages":"Article 102973"},"PeriodicalIF":9.1,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143072414","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}
As manufacturing demands shift towards enhanced part geometries and materials, the need for flexibility in production has driven interest in robotic machining. This fast-growing technology offers advantages like cost-effectiveness, adaptability, and easy deployment, making it suitable for agile production lines. However, robotic machining encounters accuracy challenges due to inherent robot flexibility, causing deviations and vibrations.
The positioning error along a robotic machining trajectory is composed of two contributions: the steady-state error and the transient. This research addresses these challenges through compensation methods based on a robotic cell equipped with a Stäubli TX200 and its digital shadow. By proposing trajectory corrections based on the results from virtual machining simulator including the robot dynamical model, the study aims to compensate the static and dynamic deviations, responsible for steady-state and transient errors respectively. To achieve this, the trajectory is discretised in elementary sections, modelled with Hermite splines and connected by nodes that are iteratively repositioned in space based on the error estimated from the dynamics simulation and weighted along the tool path.
Simulations and experiments are carried out in Aluminium 6082 to demonstrate the gain of iterative compensation algorithm. The error reduction encountered in simulation is successfully confirmed in experimental cases, within the repeatability tolerance of the robot, decreasing the steady-state error by 90% and about 60% in transient phases.
{"title":"Iterative offline trajectory correction based on dynamic model for compensating robot-dependent errors in robotic machining","authors":"Valentin Dambly , Bryan Olivier , Edouard Rivière-Lorphèvre , François Ducobu , Olivier Verlinden","doi":"10.1016/j.rcim.2025.102960","DOIUrl":"10.1016/j.rcim.2025.102960","url":null,"abstract":"<div><div>As manufacturing demands shift towards enhanced part geometries and materials, the need for flexibility in production has driven interest in robotic machining. This fast-growing technology offers advantages like cost-effectiveness, adaptability, and easy deployment, making it suitable for agile production lines. However, robotic machining encounters accuracy challenges due to inherent robot flexibility, causing deviations and vibrations.</div><div>The positioning error along a robotic machining trajectory is composed of two contributions: the steady-state error and the transient. This research addresses these challenges through compensation methods based on a robotic cell equipped with a Stäubli TX200 and its digital shadow. By proposing trajectory corrections based on the results from virtual machining simulator including the robot dynamical model, the study aims to compensate the static and dynamic deviations, responsible for steady-state and transient errors respectively. To achieve this, the trajectory is discretised in elementary sections, modelled with Hermite splines and connected by nodes that are iteratively repositioned in space based on the error estimated from the dynamics simulation and weighted along the tool path.</div><div>Simulations and experiments are carried out in Aluminium 6082 to demonstrate the gain of iterative compensation algorithm. The error reduction encountered in simulation is successfully confirmed in experimental cases, within the repeatability tolerance of the robot, decreasing the steady-state error by 90% and about 60% in transient phases.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"94 ","pages":"Article 102960"},"PeriodicalIF":9.1,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143072415","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}
Pub Date : 2025-01-28DOI: 10.1016/j.rcim.2025.102965
Zhongfei Zhang , Ting Qu , George Q. Huang , Yongheng Zhang , Kuo Zhao , Jun Zhang
With the growth of personalized demands, manufacturers need to dynamically collaborate with external resources, forming social production logistics systems (SPLS). The complexity and dynamic nature of these systems increase management difficulty, rendering traditional static decision-making methods unsuitable. This study proposes a reliable dynamic collaborative control method for SPLS in discrete manufacturing environments. It aims to provide a secure and controllable collaborative platform for multiple participants, enhancing the system's resilience to disturbances in dynamic environments. A blockchain and digital twin-based trusted synchronized decision-making framework is designed, enabling real-time and reliable acquisition of comprehensive information to support efficient decision-making. Simultaneously, a blockchain smart contract tree-based trusted synchronized decision-making mechanism is proposed to address dynamic disturbances. Utilizing a collaborative optimization algorithm, the "production-distribution-warehousing" collaborative decision model is optimally coordinated to achieve efficient resource allocation and process management. Using the home appliance manufacturing industry chain as a case study, results show that the proposed trusted synchronized control method outperforms the non-trusted synchronized control method, resulting in a 35.3 % reduction in total system costs and an enhancement in the collaborative operational efficiency of the production logistics system, and ensures reliable and efficient system operation in a dynamic demand environment. This research provides valuable references for the operational management of future production logistics systems.
{"title":"Towards a trusted synchronized decision-making method for social production logistics systems based on blockchain and digital twin","authors":"Zhongfei Zhang , Ting Qu , George Q. Huang , Yongheng Zhang , Kuo Zhao , Jun Zhang","doi":"10.1016/j.rcim.2025.102965","DOIUrl":"10.1016/j.rcim.2025.102965","url":null,"abstract":"<div><div>With the growth of personalized demands, manufacturers need to dynamically collaborate with external resources, forming social production logistics systems (SPLS). The complexity and dynamic nature of these systems increase management difficulty, rendering traditional static decision-making methods unsuitable. This study proposes a reliable dynamic collaborative control method for SPLS in discrete manufacturing environments. It aims to provide a secure and controllable collaborative platform for multiple participants, enhancing the system's resilience to disturbances in dynamic environments. A blockchain and digital twin-based trusted synchronized decision-making framework is designed, enabling real-time and reliable acquisition of comprehensive information to support efficient decision-making. Simultaneously, a blockchain smart contract tree-based trusted synchronized decision-making mechanism is proposed to address dynamic disturbances. Utilizing a collaborative optimization algorithm, the \"production-distribution-warehousing\" collaborative decision model is optimally coordinated to achieve efficient resource allocation and process management. Using the home appliance manufacturing industry chain as a case study, results show that the proposed trusted synchronized control method outperforms the non-trusted synchronized control method, resulting in a 35.3 % reduction in total system costs and an enhancement in the collaborative operational efficiency of the production logistics system, and ensures reliable and efficient system operation in a dynamic demand environment. This research provides valuable references for the operational management of future production logistics systems.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"94 ","pages":"Article 102965"},"PeriodicalIF":9.1,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143072447","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}
Pub Date : 2025-01-27DOI: 10.1016/j.rcim.2025.102970
Semin Ahn , Jae-Hoon Kim , Jun Heo , Sung-Hoon Ahn
Highly reliable sound-based interaction in noisy and dynamic environments is a known challenge with simultaneous Human-Robot Interaction (HRI) and Robot-Robot Interaction (RRI). Here, we introduce 3-dimensional acoustic ranging (3DAR) using the meta-structured single microphone rotation, a compact system with a three-dimensional meta-structure with a phase-cancellation mechanism for enhanced beamforming across audible and inaudible frequencies. Inspired by dolphin communication, the 3DAR employs frequency modulation and separation of sound channels for seamless HRI and RRI. The system achieved over 90 % accuracy in multiple source localization for HRI and 99 % for RRI, even in challenging noise conditions, along with 94 % accuracy in tracking multiple sound sources. Furthermore, real-world tests in a factory demonstrated 95.6 % accuracy in multi-HRI localization and up to 93.8 % accuracy when human speech direction originated from an angle of 120° relative to the system. Real-world application of a collaborative rescue robot confirmed effectiveness of the 3DAR in various applications, highlighting its potential for robust, sound-based collaboration among humans and robots.
{"title":"Human-robot and robot-robot sound interaction using a 3-Dimensional Acoustic Ranging (3DAR) in audible and inaudible frequency","authors":"Semin Ahn , Jae-Hoon Kim , Jun Heo , Sung-Hoon Ahn","doi":"10.1016/j.rcim.2025.102970","DOIUrl":"10.1016/j.rcim.2025.102970","url":null,"abstract":"<div><div>Highly reliable sound-based interaction in noisy and dynamic environments is a known challenge with simultaneous Human-Robot Interaction (HRI) and Robot-Robot Interaction (RRI). Here, we introduce 3-dimensional acoustic ranging (3DAR) using the meta-structured single microphone rotation, a compact system with a three-dimensional meta-structure with a phase-cancellation mechanism for enhanced beamforming across audible and inaudible frequencies. Inspired by dolphin communication, the 3DAR employs frequency modulation and separation of sound channels for seamless HRI and RRI. The system achieved over 90 % accuracy in multiple source localization for HRI and 99 % for RRI, even in challenging noise conditions, along with 94 % accuracy in tracking multiple sound sources. Furthermore, real-world tests in a factory demonstrated 95.6 % accuracy in multi-HRI localization and up to 93.8 % accuracy when human speech direction originated from an angle of 120° relative to the system. Real-world application of a collaborative rescue robot confirmed effectiveness of the 3DAR in various applications, highlighting its potential for robust, sound-based collaboration among humans and robots.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"94 ","pages":"Article 102970"},"PeriodicalIF":9.1,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143072448","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}
Pub Date : 2025-01-25DOI: 10.1016/j.rcim.2025.102971
Zuoxue Wang , Xiaobin Li , Pei Jiang , Xi Vincent Wang , Haitao Yuan
Industrial robots are widely used in manufacturing industries due to their high efficiency, flexibility, and ability to respond to diverse needs. However, the large-scale deployment of industrial robots has resulted in a significant increase in energy consumption. Therefore, it is crucial to develop an accurate modeling method for predicting the energy consumption of robotic systems, in order to optimize energy usage and achieve green and sustainable development of the manufacturing industry. Based on the analysis of temporal causal relationships between motion variables and the power of industrial robots, as well as spatial dependence between trajectory points, this study proposes a spatial-based torque prediction network and a temporal–spatial-based energy consumption prediction network by combining layer normalization with bidirectional long short-term memory neural network. This model achieves high-precision predictions of robot motion under variable motion modes, time scaling functions, and load conditions. Experimental results with KUKA KR210 and KR60 robots demonstrate that the model achieves the prediction accuracy of 99.01% for joint torque, 96.61% for total power, and 98.72% for total energy consumption under varying conditions.
{"title":"Energy consumption modeling based on operation mechanisms of industrial robots","authors":"Zuoxue Wang , Xiaobin Li , Pei Jiang , Xi Vincent Wang , Haitao Yuan","doi":"10.1016/j.rcim.2025.102971","DOIUrl":"10.1016/j.rcim.2025.102971","url":null,"abstract":"<div><div>Industrial robots are widely used in manufacturing industries due to their high efficiency, flexibility, and ability to respond to diverse needs. However, the large-scale deployment of industrial robots has resulted in a significant increase in energy consumption. Therefore, it is crucial to develop an accurate modeling method for predicting the energy consumption of robotic systems, in order to optimize energy usage and achieve green and sustainable development of the manufacturing industry. Based on the analysis of temporal causal relationships between motion variables and the power of industrial robots, as well as spatial dependence between trajectory points, this study proposes a spatial-based torque prediction network and a temporal–spatial-based energy consumption prediction network by combining layer normalization with bidirectional long short-term memory neural network. This model achieves high-precision predictions of robot motion under variable motion modes, time scaling functions, and load conditions. Experimental results with KUKA KR210 and KR60 robots demonstrate that the model achieves the prediction accuracy of 99.01% for joint torque, 96.61% for total power, and 98.72% for total energy consumption under varying conditions.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"94 ","pages":"Article 102971"},"PeriodicalIF":9.1,"publicationDate":"2025-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143031438","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}
Pub Date : 2025-01-25DOI: 10.1016/j.rcim.2025.102967
Ruipeng Pan , Zesheng Wang , Hui Wang , Dongbo Wu
The uncertainty of the blade's position and attitude in robotic flexible polishing leads to poor accuracy and stability of force-position coupling, resulting in potential issues like over-polishing or under-polishing, significantly impacting the consistency of final polishing quality. The study proposes an online positioning method of thin-walled blade with small curvature for robotic flexible polishing. The novelty of proposed method lies in that it is based on optimal local geometric feature matching between the actual workpiece and CAD model to obtain the actual position and attitude of thin-walled blade with small curvature and limited measurement area, with a positioning accuracy of 0.3164 mm, thus achieving the adaptive optimization of robotic movement trajectory. Firstly, a mathematical model for the adaptive optimization of robotic movement trajectory based on the actual posture of workpiece is established. The theoretical principles of spatial point cloud mapping based on the forward kinematics model of serial-robot, spatial point cloud registration based on dense and sparse point clouds, workpiece posture analysis based on reverse derivation of point cloud transformation are secondly studied to achieve an accurate positioning of workpiece in the robotic workspace. The error sources of proposed positioning method are analyzed and a quantitative mathematical model is established to characterize the positioning accuracy of workpiece. The feasibility and reliability of proposed positioning method are finally validated through a typical experiment. The results demonstrate that the proposed method can achieve an accurate positioning of thin-walled blade with small curvature and limited measurement area and thereby ensuring the consistency of final polishing quality.
{"title":"Online positioning of thin-walled blade with small curvature for robotic flexible polishing based on optimal local feature matching","authors":"Ruipeng Pan , Zesheng Wang , Hui Wang , Dongbo Wu","doi":"10.1016/j.rcim.2025.102967","DOIUrl":"10.1016/j.rcim.2025.102967","url":null,"abstract":"<div><div>The uncertainty of the blade's position and attitude in robotic flexible polishing leads to poor accuracy and stability of force-position coupling, resulting in potential issues like over-polishing or under-polishing, significantly impacting the consistency of final polishing quality. The study proposes an online positioning method of thin-walled blade with small curvature for robotic flexible polishing. The novelty of proposed method lies in that it is based on optimal local geometric feature matching between the actual workpiece and CAD model to obtain the actual position and attitude of thin-walled blade with small curvature and limited measurement area, with a positioning accuracy of 0.3164 mm, thus achieving the adaptive optimization of robotic movement trajectory. Firstly, a mathematical model for the adaptive optimization of robotic movement trajectory based on the actual posture of workpiece is established. The theoretical principles of spatial point cloud mapping based on the forward kinematics model of serial-robot, spatial point cloud registration based on dense and sparse point clouds, workpiece posture analysis based on reverse derivation of point cloud transformation are secondly studied to achieve an accurate positioning of workpiece in the robotic workspace. The error sources of proposed positioning method are analyzed and a quantitative mathematical model is established to characterize the positioning accuracy of workpiece. The feasibility and reliability of proposed positioning method are finally validated through a typical experiment. The results demonstrate that the proposed method can achieve an accurate positioning of thin-walled blade with small curvature and limited measurement area and thereby ensuring the consistency of final polishing quality.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"94 ","pages":"Article 102967"},"PeriodicalIF":9.1,"publicationDate":"2025-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143031439","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}
Pub Date : 2025-01-23DOI: 10.1016/j.rcim.2025.102963
Dan Li , Tianliang Hu , Lili Dong , Songhua Ma
The machining process knowledge base is a crucial tool in the decision-making process for cutting process parameters, as the diversity and accuracy of its stored process knowledge directly affect the decision effectiveness. To address the complex demands in actual production, it is necessary to adopt effective expansion methods to enrich the process knowledge base content and improve its generalizability. However, current expansion methods face limitations such as insufficient process knowledge coverage and the lack of an effective evaluation mechanism. In response to these issues, this paper proposes a generalized generation and evaluation method for cutting process parameter knowledge based on CTGAN. Firstly, a cutting process data acquisition platform is developed to serve as the basic data source. Then, Conditional Tabular Generative Adversarial Network (CTGAN) is used to construct a generalized generation model to learn the joint distribution law of real process parameter data and enable the intelligent generation of cutting process parameter cases. Finally, the accuracy and applicability of the generated cutting process parameter cases are evaluated through statistical indicator analysis and machine learning performance analysis. The proposed framework is validated using the external cylindrical turning process of a sleeve part as a test case. Results indicate that the generated process parameter data samples not only cover a broader range of machining scenarios but also maintain high quality, which can effectively support the autonomous expansion of machining process knowledge base, and enhance its generalization capability.
{"title":"A generalized generation and evaluation method for cutting process parameter knowledge based on CTGAN","authors":"Dan Li , Tianliang Hu , Lili Dong , Songhua Ma","doi":"10.1016/j.rcim.2025.102963","DOIUrl":"10.1016/j.rcim.2025.102963","url":null,"abstract":"<div><div>The machining process knowledge base is a crucial tool in the decision-making process for cutting process parameters, as the diversity and accuracy of its stored process knowledge directly affect the decision effectiveness. To address the complex demands in actual production, it is necessary to adopt effective expansion methods to enrich the process knowledge base content and improve its generalizability. However, current expansion methods face limitations such as insufficient process knowledge coverage and the lack of an effective evaluation mechanism. In response to these issues, this paper proposes a generalized generation and evaluation method for cutting process parameter knowledge based on CTGAN. Firstly, a cutting process data acquisition platform is developed to serve as the basic data source. Then, Conditional Tabular Generative Adversarial Network (CTGAN) is used to construct a generalized generation model to learn the joint distribution law of real process parameter data and enable the intelligent generation of cutting process parameter cases. Finally, the accuracy and applicability of the generated cutting process parameter cases are evaluated through statistical indicator analysis and machine learning performance analysis. The proposed framework is validated using the external cylindrical turning process of a sleeve part as a test case. Results indicate that the generated process parameter data samples not only cover a broader range of machining scenarios but also maintain high quality, which can effectively support the autonomous expansion of machining process knowledge base, and enhance its generalization capability.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"94 ","pages":"Article 102963"},"PeriodicalIF":9.1,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143027342","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}
Pub Date : 2025-01-23DOI: 10.1016/j.rcim.2025.102969
Wanyong Wang, Haohan Sun, Cong Chen, Ke Zhang
For composite plates side-sealing, traditional teaching-playback method is low-quality and inefficient, and cannot adapt to the rapid development of intelligent manufacturing. Aiming at this problem, an autonomous localization and welding path generation method based on binocular vision and lightweight deep learning network is proposed. Firstly, a lightweight background removal model based on VGG16-UNet (Visual Geometry Group Network-16 U-shaped Network) was proposed to eliminate different interference of illumination and redundant information. Secondly, Hough transform with RANSAC (Random Sample Consensus) correction was employed for accurate line extraction from unsharp workpiece edges. Then, an error compensation strategy was presented. Finally, a positioning accuracy of 0.47 mm was achieved, meeting the requirements for side-sealing. Autonomous localization and welding base path generation for composite plate billets with 20 mm depth grooves at a 3000 mm viewing distance were successfully realized. Welding results demonstrate that the proposed method is accurate and reliable, laying a solid foundation for further autonomous pass planning and adaptive controlling.
{"title":"Autonomous path generation for side-seal welding of composite plate billets based on binocular vision and lightweight network VGG16-UNet","authors":"Wanyong Wang, Haohan Sun, Cong Chen, Ke Zhang","doi":"10.1016/j.rcim.2025.102969","DOIUrl":"10.1016/j.rcim.2025.102969","url":null,"abstract":"<div><div>For composite plates side-sealing, traditional teaching-playback method is low-quality and inefficient, and cannot adapt to the rapid development of intelligent manufacturing. Aiming at this problem, an autonomous localization and welding path generation method based on binocular vision and lightweight deep learning network is proposed. Firstly, a lightweight background removal model based on VGG16-UNet (Visual Geometry Group Network-16 U-shaped Network) was proposed to eliminate different interference of illumination and redundant information. Secondly, Hough transform with RANSAC (Random Sample Consensus) correction was employed for accurate line extraction from unsharp workpiece edges. Then, an error compensation strategy was presented. Finally, a positioning accuracy of 0.47 mm was achieved, meeting the requirements for side-sealing. Autonomous localization and welding base path generation for composite plate billets with 20 mm depth grooves at a 3000 mm viewing distance were successfully realized. Welding results demonstrate that the proposed method is accurate and reliable, laying a solid foundation for further autonomous pass planning and adaptive controlling.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"94 ","pages":"Article 102969"},"PeriodicalIF":9.1,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143027367","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}
Pub Date : 2025-01-23DOI: 10.1016/j.rcim.2025.102972
Teng Zhang , Fangyu Peng , Jianzhuang Wang , Zhao Yang , Xiaowei Tang , Rong Yan , Shengqiang Zhao , Runpeng Deng
In recent years, robotic machining has been widely noticed, especially in the manufacturing of large and complex parts, where large workspaces and flexible movements give it an even greater advantage. However, significant intrinsic errors, compliance errors due to weak stiffness of the joints, and spatially dependent nonlinear properties lead to significant challenges in high-precision machining. In this case, the dynamically changing contact area during the material removal process triggers a time-varying cutting force, which in combination with the characteristics of the robot body leads to a typical spatial–temporal coupling process that maps the error onto the workpiece. To address this process, an intelligent foreknowledge method for robot machining error with spatial–temporal feature coupling is proposed by considering the robot ontology error and the machining process. The proposed method carries out joint extraction of robot-related structured features and time-related serialized features and feature-level fusion mapping, respectively, and thus achieves accurate prediction of part machining errors. The proposed method is experimentally validated on eight inner wall workpieces of a cabin segment. Overall, the model achieved an optimal 0.026 mm RMSE on three test sub-workpieces. The ability of the proposed method to accurately extract spatial–temporal features and accurately predict machining errors is also verified through ablation experiments, parameter influence analysis experiments, and intermediate feature analysis. The proposed method takes data-driven as the core idea and spatial–temporal feature extraction as the dual perspective to achieve accurate prediction of robot machining error. It is of great significance for prediction-based accuracy compensation.
{"title":"Spatial–temporal feature fusion for intelligent foreknowledge of robotic machining errors","authors":"Teng Zhang , Fangyu Peng , Jianzhuang Wang , Zhao Yang , Xiaowei Tang , Rong Yan , Shengqiang Zhao , Runpeng Deng","doi":"10.1016/j.rcim.2025.102972","DOIUrl":"10.1016/j.rcim.2025.102972","url":null,"abstract":"<div><div>In recent years, robotic machining has been widely noticed, especially in the manufacturing of large and complex parts, where large workspaces and flexible movements give it an even greater advantage. However, significant intrinsic errors, compliance errors due to weak stiffness of the joints, and spatially dependent nonlinear properties lead to significant challenges in high-precision machining. In this case, the dynamically changing contact area during the material removal process triggers a time-varying cutting force, which in combination with the characteristics of the robot body leads to a typical spatial–temporal coupling process that maps the error onto the workpiece. To address this process, an intelligent foreknowledge method for robot machining error with spatial–temporal feature coupling is proposed by considering the robot ontology error and the machining process. The proposed method carries out joint extraction of robot-related structured features and time-related serialized features and feature-level fusion mapping, respectively, and thus achieves accurate prediction of part machining errors. The proposed method is experimentally validated on eight inner wall workpieces of a cabin segment. Overall, the model achieved an optimal 0.026 mm RMSE on three test sub-workpieces. The ability of the proposed method to accurately extract spatial–temporal features and accurately predict machining errors is also verified through ablation experiments, parameter influence analysis experiments, and intermediate feature analysis. The proposed method takes data-driven as the core idea and spatial–temporal feature extraction as the dual perspective to achieve accurate prediction of robot machining error. It is of great significance for prediction-based accuracy compensation.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"94 ","pages":"Article 102972"},"PeriodicalIF":9.1,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143027363","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}
Pub Date : 2025-01-22DOI: 10.1016/j.rcim.2025.102957
Corentin Hubert , Nathan Odic , Marie Noel , Sidney Gharib , Seyedhossein H.H. Zargarbashi , Lama Séoud
The proliferation of tedious and repetitive tasks on production lines has accelerated the deployment of automated robots. This has also led to a demand for more flexible robots, known as cobots, that can work in collaboration with operators to perform a variety of tasks in different contexts. This paper explores the potential of computer vision-based hand gesture recognition as a means of human–robot interaction within cobotic platforms. Our research focuses on the challenges of gesture recognition in the face of visual occlusions and different camera viewpoints, typical of part finishing tasks in a real-world industrial setting. We introduce a new dataset, MuViH (Multi-View Hand gesture), which features a high variability in camera viewpoints, human operator characteristics, and occlusions, and is fully annotated for hand detection and gesture recognition. We then present a comprehensive hand gesture recognition pipeline that leverages this dataset. Our pipeline incorporates a multi-view aggregation step that significantly enhances gesture recognition accuracy, particularly in the case of visual occlusions. Thanks to extensive experiments and cross-validation on the MuViH dataset and another public dataset, HANDS, our approach demonstrates state-of-the-art performance in gesture recognition. This breakthrough underlines the potential of integrating robust vision-based interaction techniques into cobotic systems, improving flexibility and speed on the production line.
{"title":"MuViH: Multi-View Hand gesture dataset and recognition pipeline for human–robot interaction in a collaborative robotic finishing platform","authors":"Corentin Hubert , Nathan Odic , Marie Noel , Sidney Gharib , Seyedhossein H.H. Zargarbashi , Lama Séoud","doi":"10.1016/j.rcim.2025.102957","DOIUrl":"10.1016/j.rcim.2025.102957","url":null,"abstract":"<div><div>The proliferation of tedious and repetitive tasks on production lines has accelerated the deployment of automated robots. This has also led to a demand for more flexible robots, known as cobots, that can work in collaboration with operators to perform a variety of tasks in different contexts. This paper explores the potential of computer vision-based hand gesture recognition as a means of human–robot interaction within cobotic platforms. Our research focuses on the challenges of gesture recognition in the face of visual occlusions and different camera viewpoints, typical of part finishing tasks in a real-world industrial setting. We introduce a new dataset, MuViH (Multi-View Hand gesture), which features a high variability in camera viewpoints, human operator characteristics, and occlusions, and is fully annotated for hand detection and gesture recognition. We then present a comprehensive hand gesture recognition pipeline that leverages this dataset. Our pipeline incorporates a multi-view aggregation step that significantly enhances gesture recognition accuracy, particularly in the case of visual occlusions. Thanks to extensive experiments and cross-validation on the MuViH dataset and another public dataset, HANDS, our approach demonstrates state-of-the-art performance in gesture recognition. This breakthrough underlines the potential of integrating robust vision-based interaction techniques into cobotic systems, improving flexibility and speed on the production line.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"94 ","pages":"Article 102957"},"PeriodicalIF":9.1,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143027345","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号