Pub Date : 2024-07-18DOI: 10.1108/ria-06-2023-0081
Zhiyu Li, Hongguang Li, Yang Liu, Lingyun Jin, Congqing Wang
Purpose Autonomous flight of unmanned aerial vehicles (UAVs) in global position system (GPS)-denied environments has become an increasing research hotspot. This paper aims to realize the indoor fixed-point hovering control and autonomous flight for UAVs based on visual inertial simultaneous localization and mapping (SLAM) and sensor fusion algorithm based on extended Kalman filter. Design/methodology/approach The fundamental of the proposed method is using visual inertial SLAM to estimate the position information of the UAV and position-speed double-loop controller to control the UAV. The motion and observation models of the UAV and the fusion algorithm are given. Finally, experiments are performed to test the proposed algorithms. Findings A position-speed double-loop controller is proposed, by fusing the position information obtained by visual inertial SLAM with the data of airborne sensors. The experiment results of the indoor fixed-points hovering show that UAV flight control can be realized based on visual inertial SLAM in the absence of GPS. Originality/value A position-speed double-loop controller for UAV is designed and tested, which provides a more stable position estimation and enabled UAV to fly autonomously and hover in GPS-denied environment.
目的无人飞行器（UAV）在全球定位系统（GPS）覆盖环境下的自主飞行已成为一个日益突出的研究热点。本文旨在基于视觉惯性同步定位与映射（SLAM）和基于扩展卡尔曼滤波器的传感器融合算法，实现无人飞行器的室内定点悬停控制和自主飞行。给出了无人机的运动和观测模型以及融合算法。通过融合视觉惯性 SLAM 获得的位置信息和机载传感器的数据，提出了位置-速度双环控制器。室内定点悬停的实验结果表明，在没有 GPS 的情况下，基于视觉惯性 SLAM 可以实现无人机的飞行控制。
{"title":"Indoor fixed-point hovering control for UAVs based on visual inertial SLAM","authors":"Zhiyu Li, Hongguang Li, Yang Liu, Lingyun Jin, Congqing Wang","doi":"10.1108/ria-06-2023-0081","DOIUrl":"https://doi.org/10.1108/ria-06-2023-0081","url":null,"abstract":"Purpose\u0000Autonomous flight of unmanned aerial vehicles (UAVs) in global position system (GPS)-denied environments has become an increasing research hotspot. This paper aims to realize the indoor fixed-point hovering control and autonomous flight for UAVs based on visual inertial simultaneous localization and mapping (SLAM) and sensor fusion algorithm based on extended Kalman filter.\u0000\u0000Design/methodology/approach\u0000The fundamental of the proposed method is using visual inertial SLAM to estimate the position information of the UAV and position-speed double-loop controller to control the UAV. The motion and observation models of the UAV and the fusion algorithm are given. Finally, experiments are performed to test the proposed algorithms.\u0000\u0000Findings\u0000A position-speed double-loop controller is proposed, by fusing the position information obtained by visual inertial SLAM with the data of airborne sensors. The experiment results of the indoor fixed-points hovering show that UAV flight control can be realized based on visual inertial SLAM in the absence of GPS.\u0000\u0000Originality/value\u0000A position-speed double-loop controller for UAV is designed and tested, which provides a more stable position estimation and enabled UAV to fly autonomously and hover in GPS-denied environment.\u0000","PeriodicalId":501194,"journal":{"name":"Robotic Intelligence and Automation","volume":"41 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141639847","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-15DOI: 10.1108/ria-01-2024-0006
Min Zhao, Wei He, Xiuyu He, Liang Zhang, Hongxue Zhao
Purpose Bionic flapping-wing aerial vehicles (FWAVs) mimic natural flyers to generate the lift and thrust, such as birds, bats and insects. As an important component of the FWAVs, the flapping wings are crucial for the flight performance. The aim of this paper is to study the effects of different wings on aerodynamic performance. Design/methodology/approach Inspired by the wings structure of birds, the authors design four cambered wings to analyze the effect of airfoils on the FWAVs aerodynamic performance. The authors design the motor-driven mechanism of flapping wings, and realize the control of flapping frequency. Combined with the wind tunnel equipment, the authors build the FWAVs force test platform to test the static and dynamic aerodynamic performance of different flapping wings under the state variables of flapping frequency, wind speed and inclined angle. Findings The results show that the aerodynamic performance of flapping wing with a camber of 20 mm is the best. Compared with flat wing, the average lift can be improved by 59.5%. Originality/value Different from the traditional flat wing design of FWAVs, different cambered flapping wings are given in this paper. The influence of airfoils on aerodynamic performance of FWAVs is analyzed and the optimal flapping wing is obtained.
{"title":"Design and performance analysis of different cambered wings for flapping-wing aerial vehicles based on wind tunnel test","authors":"Min Zhao, Wei He, Xiuyu He, Liang Zhang, Hongxue Zhao","doi":"10.1108/ria-01-2024-0006","DOIUrl":"https://doi.org/10.1108/ria-01-2024-0006","url":null,"abstract":"\u0000Purpose\u0000Bionic flapping-wing aerial vehicles (FWAVs) mimic natural flyers to generate the lift and thrust, such as birds, bats and insects. As an important component of the FWAVs, the flapping wings are crucial for the flight performance. The aim of this paper is to study the effects of different wings on aerodynamic performance.\u0000\u0000\u0000Design/methodology/approach\u0000Inspired by the wings structure of birds, the authors design four cambered wings to analyze the effect of airfoils on the FWAVs aerodynamic performance. The authors design the motor-driven mechanism of flapping wings, and realize the control of flapping frequency. Combined with the wind tunnel equipment, the authors build the FWAVs force test platform to test the static and dynamic aerodynamic performance of different flapping wings under the state variables of flapping frequency, wind speed and inclined angle.\u0000\u0000\u0000Findings\u0000The results show that the aerodynamic performance of flapping wing with a camber of 20 mm is the best. Compared with flat wing, the average lift can be improved by 59.5%.\u0000\u0000\u0000Originality/value\u0000Different from the traditional flat wing design of FWAVs, different cambered flapping wings are given in this paper. The influence of airfoils on aerodynamic performance of FWAVs is analyzed and the optimal flapping wing is obtained.\u0000","PeriodicalId":501194,"journal":{"name":"Robotic Intelligence and Automation","volume":"48 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141644594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-12DOI: 10.1108/ria-01-2024-0019
Peng Guo, Weiyong Si, Chenguang Yang
Purpose The purpose of this paper is to enhance the performance of robots in peg-in-hole assembly tasks, enabling them to swiftly and robustly accomplish the task. It also focuses on the robot’s ability to generalize across assemblies with different hole sizes. Design/methodology/approach Human behavior in peg-in-hole assembly serves as inspiration, where individuals visually locate the hole firstly and then continuously adjust the peg pose based on force/torque feedback during the insertion process. This paper proposes a novel framework that integrate visual servo and adjustment based on force/torque feedback, the authors use deep neural network (DNN) and image processing techniques to determine the pose of hole, then an incremental learning approach based on a broad learning system (BLS) is used to simulate human learning ability, the number of adjustments required for insertion process is continuously reduced. Findings The author conducted experiments on visual servo, adjustment based on force/torque feedback, and the proposed framework. Visual servo inferred the pixel position and orientation of the target hole in only about 0.12 s, and the robot achieved peg insertion with 1–3 adjustments based on force/torque feedback. The success rate for peg-in-hole assembly using the proposed framework was 100%. These results proved the effectiveness of the proposed framework. Originality/value This paper proposes a framework for peg-in-hole assembly that combines visual servo and adjustment based on force/torque feedback. The assembly tasks are accomplished using DNN, image processing and BLS. To the best of the authors’ knowledge, no similar methods were found in other people’s work. Therefore, the authors believe that this work is original.
{"title":"A novel framework inspired by human behavior for peg-in-hole assembly","authors":"Peng Guo, Weiyong Si, Chenguang Yang","doi":"10.1108/ria-01-2024-0019","DOIUrl":"https://doi.org/10.1108/ria-01-2024-0019","url":null,"abstract":"\u0000Purpose\u0000The purpose of this paper is to enhance the performance of robots in peg-in-hole assembly tasks, enabling them to swiftly and robustly accomplish the task. It also focuses on the robot’s ability to generalize across assemblies with different hole sizes.\u0000\u0000\u0000Design/methodology/approach\u0000Human behavior in peg-in-hole assembly serves as inspiration, where individuals visually locate the hole firstly and then continuously adjust the peg pose based on force/torque feedback during the insertion process. This paper proposes a novel framework that integrate visual servo and adjustment based on force/torque feedback, the authors use deep neural network (DNN) and image processing techniques to determine the pose of hole, then an incremental learning approach based on a broad learning system (BLS) is used to simulate human learning ability, the number of adjustments required for insertion process is continuously reduced.\u0000\u0000\u0000Findings\u0000The author conducted experiments on visual servo, adjustment based on force/torque feedback, and the proposed framework. Visual servo inferred the pixel position and orientation of the target hole in only about 0.12 s, and the robot achieved peg insertion with 1–3 adjustments based on force/torque feedback. The success rate for peg-in-hole assembly using the proposed framework was 100%. These results proved the effectiveness of the proposed framework.\u0000\u0000\u0000Originality/value\u0000This paper proposes a framework for peg-in-hole assembly that combines visual servo and adjustment based on force/torque feedback. The assembly tasks are accomplished using DNN, image processing and BLS. To the best of the authors’ knowledge, no similar methods were found in other people’s work. Therefore, the authors believe that this work is original.\u0000","PeriodicalId":501194,"journal":{"name":"Robotic Intelligence and Automation","volume":"45 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141652892","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Purpose Current flexible printed circuit (FPC) assembly relies heavily on manual labor, limiting capacity and increasing costs. Small FPC size makes automation challenging as terminals can be visually occluded. The purpose of this study is to use 3D tactile sensing to mimic human manual mating skills for enabling sensing offset between FPC terminals (FPC-t) and FPC mating slots (FPC-s) under visual occlusion. Design/methodology/approach The proposed model has three stages: spatial encoding, offset estimation and action strategy. The spatial encoder maps sparse 3D tactile data into a compact 1D feature capturing valid spatial assembly information to enable temporal processing. To compensate for low sensor resolution, consecutive spatial features are input to a multistage temporal convolutional network which estimates alignment offsets. The robot then performs alignment or mating actions based on the estimated offsets. Findings Experiments are conducted on a Redmi Note 4 smartphone assembly platform. Compared to other models, the proposed approach achieves superior offset estimation. Within limited trials, it successfully assembles FPCs under visual occlusion using three-axis tactile sensing. Originality/value A spatial encoder is designed to encode three-axis tactile data into feature maps, overcoming multistage temporal convolution network’s (MS-TCN) inability to directly process such input. Modifying the output to estimate assembly offsets with related motion semantics overcame MS-TCN’s segmentation points output, unable to meet assembly monitoring needs. Training and testing the improved MS-TCN on an FPC data set demonstrated accurate monitoring of the full process. An assembly platform verified performance on automated FPC assembly.
{"title":"An MS-TCN based spatiotemporal model with three-axis tactile for enhancing flexible printed circuit assembly","authors":"Zengxin Kang, Jing Cui, Yijie Wang, Zhikai Hu, Zhongyi Chu","doi":"10.1108/ria-10-2023-0136","DOIUrl":"https://doi.org/10.1108/ria-10-2023-0136","url":null,"abstract":"Purpose\u0000Current flexible printed circuit (FPC) assembly relies heavily on manual labor, limiting capacity and increasing costs. Small FPC size makes automation challenging as terminals can be visually occluded. The purpose of this study is to use 3D tactile sensing to mimic human manual mating skills for enabling sensing offset between FPC terminals (FPC-t) and FPC mating slots (FPC-s) under visual occlusion.\u0000\u0000Design/methodology/approach\u0000The proposed model has three stages: spatial encoding, offset estimation and action strategy. The spatial encoder maps sparse 3D tactile data into a compact 1D feature capturing valid spatial assembly information to enable temporal processing. To compensate for low sensor resolution, consecutive spatial features are input to a multistage temporal convolutional network which estimates alignment offsets. The robot then performs alignment or mating actions based on the estimated offsets.\u0000\u0000Findings\u0000Experiments are conducted on a Redmi Note 4 smartphone assembly platform. Compared to other models, the proposed approach achieves superior offset estimation. Within limited trials, it successfully assembles FPCs under visual occlusion using three-axis tactile sensing.\u0000\u0000Originality/value\u0000A spatial encoder is designed to encode three-axis tactile data into feature maps, overcoming multistage temporal convolution network’s (MS-TCN) inability to directly process such input. Modifying the output to estimate assembly offsets with related motion semantics overcame MS-TCN’s segmentation points output, unable to meet assembly monitoring needs. Training and testing the improved MS-TCN on an FPC data set demonstrated accurate monitoring of the full process. An assembly platform verified performance on automated FPC assembly.\u0000","PeriodicalId":501194,"journal":{"name":"Robotic Intelligence and Automation","volume":"124 37","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141666314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-09DOI: 10.1108/ria-10-2023-0142
Zengrui Zheng, Kainan Su, Shifeng Lin, Zhiquan Fu, Chenguang Yang
Purpose Visual simultaneous localization and mapping (SLAM) has limitations such as sensitivity to lighting changes and lower measurement accuracy. The effective fusion of information from multiple modalities to address these limitations has emerged as a key research focus. This study aims to provide a comprehensive review of the development of vision-based SLAM (including visual SLAM) for navigation and pose estimation, with a specific focus on techniques for integrating multiple modalities. Design/methodology/approach This paper initially introduces the mathematical models and framework development of visual SLAM. Subsequently, this paper presents various methods for improving accuracy in visual SLAM by fusing different spatial and semantic features. This paper also examines the research advancements in vision-based SLAM with respect to multi-sensor fusion in both loosely coupled and tightly coupled approaches. Finally, this paper analyzes the limitations of current vision-based SLAM and provides predictions for future advancements. Findings The combination of vision-based SLAM and deep learning has significant potential for development. There are advantages and disadvantages to both loosely coupled and tightly coupled approaches in multi-sensor fusion, and the most suitable algorithm should be chosen based on the specific application scenario. In the future, vision-based SLAM is evolving toward better addressing challenges such as resource-limited platforms and long-term mapping. Originality/value This review introduces the development of vision-based SLAM and focuses on the advancements in multimodal fusion. It allows readers to quickly understand the progress and current status of research in this field.
目的 视觉同步定位和绘图（SLAM）存在一些局限性，如对光照变化的敏感性和较低的测量精度。如何有效融合多种模式的信息以解决这些局限性已成为研究的重点。本研究旨在全面回顾基于视觉的 SLAM（包括视觉 SLAM）在导航和姿态估计方面的发展情况，并特别关注整合多种模式的技术。随后，本文介绍了通过融合不同的空间和语义特征来提高视觉 SLAM 精确度的各种方法。本文还探讨了松耦合和紧耦合方法中基于视觉的多传感器融合 SLAM 的研究进展。最后，本文分析了当前基于视觉的 SLAM 的局限性，并对未来的发展进行了预测。 研究结果基于视觉的 SLAM 与深度学习的结合具有巨大的发展潜力。多传感器融合中的松耦合和紧耦合方法各有利弊，应根据具体应用场景选择最合适的算法。未来，基于视觉的 SLAM 将朝着更好地应对资源有限的平台和长期制图等挑战的方向发展。 原创性/价值 本综述介绍了基于视觉的 SLAM 的发展，并重点介绍了多模态融合的进展。它使读者能够快速了解该领域的研究进展和现状。
{"title":"Development of vision–based SLAM: from traditional methods to multimodal fusion","authors":"Zengrui Zheng, Kainan Su, Shifeng Lin, Zhiquan Fu, Chenguang Yang","doi":"10.1108/ria-10-2023-0142","DOIUrl":"https://doi.org/10.1108/ria-10-2023-0142","url":null,"abstract":"Purpose\u0000Visual simultaneous localization and mapping (SLAM) has limitations such as sensitivity to lighting changes and lower measurement accuracy. The effective fusion of information from multiple modalities to address these limitations has emerged as a key research focus. This study aims to provide a comprehensive review of the development of vision-based SLAM (including visual SLAM) for navigation and pose estimation, with a specific focus on techniques for integrating multiple modalities.\u0000\u0000Design/methodology/approach\u0000This paper initially introduces the mathematical models and framework development of visual SLAM. Subsequently, this paper presents various methods for improving accuracy in visual SLAM by fusing different spatial and semantic features. This paper also examines the research advancements in vision-based SLAM with respect to multi-sensor fusion in both loosely coupled and tightly coupled approaches. Finally, this paper analyzes the limitations of current vision-based SLAM and provides predictions for future advancements.\u0000\u0000Findings\u0000The combination of vision-based SLAM and deep learning has significant potential for development. There are advantages and disadvantages to both loosely coupled and tightly coupled approaches in multi-sensor fusion, and the most suitable algorithm should be chosen based on the specific application scenario. In the future, vision-based SLAM is evolving toward better addressing challenges such as resource-limited platforms and long-term mapping.\u0000\u0000Originality/value\u0000This review introduces the development of vision-based SLAM and focuses on the advancements in multimodal fusion. It allows readers to quickly understand the progress and current status of research in this field.\u0000","PeriodicalId":501194,"journal":{"name":"Robotic Intelligence and Automation","volume":"107 17","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141665899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-08DOI: 10.1108/ria-08-2023-0099
S. Lupuleac, Tatiana Pogarskaia
Purpose The purpose of the current study is development of effective and fast algorithm for optimization the arrangement of temporary fasteners during aircraft assembly. Design/methodology/approach Combinatorial nature, uncertain input data, sensitivity to mechanical properties and geometric tolerances are the specific features of the fastening optimization problem. These characteristics make the problem-solving by standard methods very resource-intensive because the calculation of the objective function requires multiple solution of contact problems. The work provides an extended description of the geodesic algorithm (GA) which is a novel non-iterative optimization approach avoiding multiple objective function calculations. Findings The GA makes it possible to optimize the arrangement of temporary fasteners during the different stages of the assembly process. The objective functions for the optimization are number of installed fasteners and quality of contact between joined parts. The mentioned properties of the GA also make it possible to introduce an automatic procedure for optimizing fastener arrangement into everyday practice of aircraft manufacturing. Practical implications The algorithm has been applied to optimization of the assembly process in Airbus company. Originality/value Performance of the GA is orders of magnitude greater than standard optimization algorithms while maintaining the quality of results. The use of the assembly process specifics is the main limitation of the GA, because it cannot be automatically applied to optimization problems in other areas. High speed of work and quality of the results make it possible to use it for real optimization problems on assembly line in the production of commercial airliners.
设计/方法/途径组合性质、不确定的输入数据、对机械性能和几何公差的敏感性是紧固件优化问题的具体特征。由于目标函数的计算需要多次解决接触问题，这些特点使得用标准方法解决问题非常耗费资源。该研究对大地算法（GA）进行了扩展描述，这是一种避免多重目标函数计算的新型非迭代优化方法。优化的目标函数是已安装紧固件的数量和连接部件之间的接触质量。该算法已应用于空中客车公司装配过程的优化。原创性/价值在保持结果质量的前提下，GA 的性能比标准优化算法高出几个数量级。由于无法自动应用于其他领域的优化问题，因此装配过程的特殊性是 GA 的主要局限性。由于工作速度快、结果质量高，因此可以将其用于解决商用客机生产装配线上的实际优化问题。
{"title":"Geodesic algorithm: new approach to optimization of temporary fastener arrangement in airframe assembly process","authors":"S. Lupuleac, Tatiana Pogarskaia","doi":"10.1108/ria-08-2023-0099","DOIUrl":"https://doi.org/10.1108/ria-08-2023-0099","url":null,"abstract":"\u0000Purpose\u0000The purpose of the current study is development of effective and fast algorithm for optimization the arrangement of temporary fasteners during aircraft assembly.\u0000\u0000\u0000Design/methodology/approach\u0000Combinatorial nature, uncertain input data, sensitivity to mechanical properties and geometric tolerances are the specific features of the fastening optimization problem. These characteristics make the problem-solving by standard methods very resource-intensive because the calculation of the objective function requires multiple solution of contact problems. The work provides an extended description of the geodesic algorithm (GA) which is a novel non-iterative optimization approach avoiding multiple objective function calculations.\u0000\u0000\u0000Findings\u0000The GA makes it possible to optimize the arrangement of temporary fasteners during the different stages of the assembly process. The objective functions for the optimization are number of installed fasteners and quality of contact between joined parts. The mentioned properties of the GA also make it possible to introduce an automatic procedure for optimizing fastener arrangement into everyday practice of aircraft manufacturing.\u0000\u0000\u0000Practical implications\u0000The algorithm has been applied to optimization of the assembly process in Airbus company.\u0000\u0000\u0000Originality/value\u0000Performance of the GA is orders of magnitude greater than standard optimization algorithms while maintaining the quality of results. The use of the assembly process specifics is the main limitation of the GA, because it cannot be automatically applied to optimization problems in other areas. High speed of work and quality of the results make it possible to use it for real optimization problems on assembly line in the production of commercial airliners.\u0000","PeriodicalId":501194,"journal":{"name":"Robotic Intelligence and Automation","volume":"112 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141666910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-06DOI: 10.1108/ria-08-2023-0109
Zhiwei Zhang, Saasha Nair, Zhe Liu, Yanzi Miao, Xiaoping Ma
Purpose This paper aims to facilitate the research and development of resilient navigation approaches, explore the robustness of adversarial training to different interferences and promote their practical applications in real complex environments. Design/methodology/approach In this paper, the authors first summarize the real accidents of self-driving cars and develop a set of methods to simulate challenging scenarios by introducing simulated disturbances and attacks into the input sensor data. Then a robust and transferable adversarial training approach is proposed to improve the performance and resilience of current navigation models, followed by a multi-modality fusion-based end-to-end navigation network to demonstrate real-world performance of the methods. In addition, an augmented self-driving simulator with designed evaluation metrics is built to evaluate navigation models. Findings Synthetical experiments in simulator demonstrate the robustness and transferability of the proposed adversarial training strategy. The simulation function flow can also be used for promoting any robust perception or navigation researches. Then a multi-modality fusion-based navigation framework is proposed as a light-weight model to evaluate the adversarial training method in real-world. Originality/value The adversarial training approach provides a transferable and robust enhancement for navigation models both in simulation and real-world.
{"title":"Robust and transferable end-to-end navigation against disturbances and external attacks: an adversarial training approach","authors":"Zhiwei Zhang, Saasha Nair, Zhe Liu, Yanzi Miao, Xiaoping Ma","doi":"10.1108/ria-08-2023-0109","DOIUrl":"https://doi.org/10.1108/ria-08-2023-0109","url":null,"abstract":"Purpose\u0000This paper aims to facilitate the research and development of resilient navigation approaches, explore the robustness of adversarial training to different interferences and promote their practical applications in real complex environments.\u0000\u0000Design/methodology/approach\u0000In this paper, the authors first summarize the real accidents of self-driving cars and develop a set of methods to simulate challenging scenarios by introducing simulated disturbances and attacks into the input sensor data. Then a robust and transferable adversarial training approach is proposed to improve the performance and resilience of current navigation models, followed by a multi-modality fusion-based end-to-end navigation network to demonstrate real-world performance of the methods. In addition, an augmented self-driving simulator with designed evaluation metrics is built to evaluate navigation models.\u0000\u0000Findings\u0000Synthetical experiments in simulator demonstrate the robustness and transferability of the proposed adversarial training strategy. The simulation function flow can also be used for promoting any robust perception or navigation researches. Then a multi-modality fusion-based navigation framework is proposed as a light-weight model to evaluate the adversarial training method in real-world.\u0000\u0000Originality/value\u0000The adversarial training approach provides a transferable and robust enhancement for navigation models both in simulation and real-world.\u0000","PeriodicalId":501194,"journal":{"name":"Robotic Intelligence and Automation","volume":"47 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141265192","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-06DOI: 10.1108/ria-01-2024-0008
Meiling Sun, Changlei Cui
Purpose This paper aims to critically evaluate the role of advanced artificial intelligence (AI)-enhanced image fusion techniques in lung cancer diagnostics within the context of AI-driven precision medicine. Design/methodology/approach We conducted a systematic review of various studies to assess the impact of AI-based methodologies on the accuracy and efficiency of lung cancer diagnosis. The focus was on the integration of AI in image fusion techniques and their application in personalized treatment strategies. Findings The review reveals significant improvements in diagnostic precision, a crucial aspect of the evolution of AI in healthcare. These AI-driven techniques substantially enhance the accuracy of lung cancer diagnosis, thereby influencing personalized treatment approaches. The study also explores the broader implications of these methodologies on healthcare resource allocation, policy formation, and epidemiological trends. Originality/value This study is notable for both emphasizing the clinical importance of AI-integrated image fusion in lung cancer treatment and illuminating the profound influence these technologies have in the future AI-driven healthcare systems.
{"title":"Advanced AI-driven image fusion techniques in lung cancer diagnostics: systematic review and meta-analysis for precisionmedicine","authors":"Meiling Sun, Changlei Cui","doi":"10.1108/ria-01-2024-0008","DOIUrl":"https://doi.org/10.1108/ria-01-2024-0008","url":null,"abstract":"\u0000Purpose\u0000This paper aims to critically evaluate the role of advanced artificial intelligence (AI)-enhanced image fusion techniques in lung cancer diagnostics within the context of AI-driven precision medicine.\u0000\u0000\u0000Design/methodology/approach\u0000We conducted a systematic review of various studies to assess the impact of AI-based methodologies on the accuracy and efficiency of lung cancer diagnosis. The focus was on the integration of AI in image fusion techniques and their application in personalized treatment strategies.\u0000\u0000\u0000Findings\u0000The review reveals significant improvements in diagnostic precision, a crucial aspect of the evolution of AI in healthcare. These AI-driven techniques substantially enhance the accuracy of lung cancer diagnosis, thereby influencing personalized treatment approaches. The study also explores the broader implications of these methodologies on healthcare resource allocation, policy formation, and epidemiological trends.\u0000\u0000\u0000Originality/value\u0000This study is notable for both emphasizing the clinical importance of AI-integrated image fusion in lung cancer treatment and illuminating the profound influence these technologies have in the future AI-driven healthcare systems.\u0000","PeriodicalId":501194,"journal":{"name":"Robotic Intelligence and Automation","volume":"42 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141265208","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-05DOI: 10.1108/ria-06-2022-0157
Maroua Ghali, N. Aifaoui
Purpose This study aims to develop an optimal tolerance allocation strategy involves integrating the unique transfer (UT) approach and the difficulty coefficient evaluation (DCE) routine in an interactive hybrid method. This method combines the strengths of both UT and DCE, ensuring simultaneous utilization for enhanced performance. The proposed tolerancing model manifests an integrated computer-aided design (CAD) tool. Design/methodology/approach By combining UT and DCE based on failure mode, effects and criticality analysis (FMECA) tool and the Ishikawa diagram, the proposed collaborative hybrid tool ensures an efficient and optimal tolerance allocation approach. The integration of these methodologies not only addresses specific transfer challenges through UT but also conducts a thorough evaluation of difficulty coefficients via DCE routine using reliability analysis tools as FMECA tool and the Ishikawa diagram. This comprehensive framework contributes to a robust and informed decision-making process in tolerance allocation, ultimately optimizing the design and manufacturing processes. Findings The presented methodology is implemented with the aim of generating allocated tolerances that align with specific difficulty requirements, facilitating the creation of a mechanical assembly characterized by high quality and low cost. To substantiate and validate the conceptual framework and methods, an integrated tool has been developed, featuring a graphical user interface (GUI) designed in MATLAB. This interface serves as a platform to showcase various interactive and integrated tolerance allocation approaches that adhere to both functional and manufacturing prerequisites. The proposed integrated tool, designed with a GUI in MATLAB, offers the capability to execute various examples that effectively demonstrate the benefits of the developed tolerance transfer and allocation methodology. Originality/value The originality of the proposed approach is the twining between the UT and DCE simultaneous in an integrated and concurrent tolerance transfer and allocation model. Therefore, the proposed approach is named an integrated CAD/tolerance model based on the manufacturing difficulty tool. The obtained results underscore the tangible advantages stemming from the integration of this innovative tolerance transfer and allocation approach. These benefits include a notable reduction in total cost and a concurrent enhancement in product quality.
目的 本研究旨在开发一种最佳容差分配策略，将唯一性转移（UT）方法和难度系数评估（DCE）例程整合到一种交互式混合方法中。该方法结合了 UT 和 DCE 的优点，确保同时使用以提高性能。设计/方法/途径通过将基于失效模式、效应和临界分析（FMECA）工具和石川图的UT 和 DCE 相结合，所提出的协作式混合工具确保了高效和优化的公差分配方法。这些方法的整合不仅能通过 UT 解决特定的转移难题，还能利用 FMECA 工具和石川图等可靠性分析工具，通过 DCE 常规对难度系数进行全面评估。该综合框架有助于在公差分配过程中做出稳健、明智的决策，最终优化设计和制造流程。研究结果该方法的实施旨在生成符合特定难度要求的分配公差，从而促进高质量、低成本机械装配的创建。为了证实和验证概念框架和方法，我们开发了一个集成工具，该工具采用 MATLAB 设计的图形用户界面 (GUI)。该界面可作为一个平台，展示符合功能和制造前提条件的各种交互式综合公差分配方法。所提议的集成工具采用 MATLAB 图形用户界面设计，能够执行各种示例，有效展示所开发的公差转移和分配方法的优势。原创性/价值所提议方法的原创性在于在集成并发公差转移和分配模型中将 UT 和 DCE 同时结合在一起。因此，建议的方法被命名为基于制造困难工具的集成 CAD/公差模型。所获得的结果强调了这一创新公差转移和分配集成方法的实际优势。这些优势包括显著降低总成本，同时提高产品质量。
{"title":"An integrated hybrid approach for assembly tolerance transfer and allocation","authors":"Maroua Ghali, N. Aifaoui","doi":"10.1108/ria-06-2022-0157","DOIUrl":"https://doi.org/10.1108/ria-06-2022-0157","url":null,"abstract":"\u0000Purpose\u0000This study aims to develop an optimal tolerance allocation strategy involves integrating the unique transfer (UT) approach and the difficulty coefficient evaluation (DCE) routine in an interactive hybrid method. This method combines the strengths of both UT and DCE, ensuring simultaneous utilization for enhanced performance. The proposed tolerancing model manifests an integrated computer-aided design (CAD) tool.\u0000\u0000\u0000Design/methodology/approach\u0000By combining UT and DCE based on failure mode, effects and criticality analysis (FMECA) tool and the Ishikawa diagram, the proposed collaborative hybrid tool ensures an efficient and optimal tolerance allocation approach. The integration of these methodologies not only addresses specific transfer challenges through UT but also conducts a thorough evaluation of difficulty coefficients via DCE routine using reliability analysis tools as FMECA tool and the Ishikawa diagram. This comprehensive framework contributes to a robust and informed decision-making process in tolerance allocation, ultimately optimizing the design and manufacturing processes.\u0000\u0000\u0000Findings\u0000The presented methodology is implemented with the aim of generating allocated tolerances that align with specific difficulty requirements, facilitating the creation of a mechanical assembly characterized by high quality and low cost. To substantiate and validate the conceptual framework and methods, an integrated tool has been developed, featuring a graphical user interface (GUI) designed in MATLAB. This interface serves as a platform to showcase various interactive and integrated tolerance allocation approaches that adhere to both functional and manufacturing prerequisites. The proposed integrated tool, designed with a GUI in MATLAB, offers the capability to execute various examples that effectively demonstrate the benefits of the developed tolerance transfer and allocation methodology.\u0000\u0000\u0000Originality/value\u0000The originality of the proposed approach is the twining between the UT and DCE simultaneous in an integrated and concurrent tolerance transfer and allocation model. Therefore, the proposed approach is named an integrated CAD/tolerance model based on the manufacturing difficulty tool. The obtained results underscore the tangible advantages stemming from the integration of this innovative tolerance transfer and allocation approach. These benefits include a notable reduction in total cost and a concurrent enhancement in product quality.\u0000","PeriodicalId":501194,"journal":{"name":"Robotic Intelligence and Automation","volume":"2 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141265704","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-04DOI: 10.1108/ria-01-2024-0013
Subhi Jleilaty, A. Ammounah, G. Abdulmalek, L. Nouvelière, Hang Su, S. Alfayad
Purpose This paper aims to develop an adaptable control architecture for electrohydraulic humanoid robots (HYDROïD) that emulate the functionality of the human nervous system. The developed control architecture overcomes the limitations of classical centralized and decentralized systems by distributing intelligence across controllers. Design/methodology/approach The proposed solution is a distributed real-time control architecture with robot operating system (ROS). The joint controllers have the intelligence to make decisions, dominate their actuators and publish their state. The real-time capabilities are ensured in the master controller by using a Preempt-RT kernel beside open robot control software middleware to operate the real-time tasks and in the customized joint controllers by free real-time operating systems firmware. Systems can be either centralized, where all components are connected to a central unit or decentralized, where distributed units act as interfaces between the I/Os and the master controller when the master controller is without the ability to make decisions. Findings The proposed architecture establishes a versatile and adaptive control framework. It features a centralized hardware topology with a master PC and distributed joint controllers, while the software architecture adapts based on the task. It operates in a distributed manner for precise, force-independent motions and in a decentralized manner for tasks requiring compliance and force control. This design enables the examination of the sensorimotor loop at both low-level joint controllers and the high-level master controller. Originality/value It developed a control architecture emulating the functionality of the human nervous system. The experimental validations were performed on the HYDROïD. The results demonstrated 50% advancements in the update rate compared to other humanoids and 30% in the latency of the master processor and the control tasks.
{"title":"Distributed real-time control architecture for electrohydraulic humanoid robots","authors":"Subhi Jleilaty, A. Ammounah, G. Abdulmalek, L. Nouvelière, Hang Su, S. Alfayad","doi":"10.1108/ria-01-2024-0013","DOIUrl":"https://doi.org/10.1108/ria-01-2024-0013","url":null,"abstract":"\u0000Purpose\u0000This paper aims to develop an adaptable control architecture for electrohydraulic humanoid robots (HYDROïD) that emulate the functionality of the human nervous system. The developed control architecture overcomes the limitations of classical centralized and decentralized systems by distributing intelligence across controllers.\u0000\u0000\u0000Design/methodology/approach\u0000The proposed solution is a distributed real-time control architecture with robot operating system (ROS). The joint controllers have the intelligence to make decisions, dominate their actuators and publish their state. The real-time capabilities are ensured in the master controller by using a Preempt-RT kernel beside open robot control software middleware to operate the real-time tasks and in the customized joint controllers by free real-time operating systems firmware. Systems can be either centralized, where all components are connected to a central unit or decentralized, where distributed units act as interfaces between the I/Os and the master controller when the master controller is without the ability to make decisions.\u0000\u0000\u0000Findings\u0000The proposed architecture establishes a versatile and adaptive control framework. It features a centralized hardware topology with a master PC and distributed joint controllers, while the software architecture adapts based on the task. It operates in a distributed manner for precise, force-independent motions and in a decentralized manner for tasks requiring compliance and force control. This design enables the examination of the sensorimotor loop at both low-level joint controllers and the high-level master controller.\u0000\u0000\u0000Originality/value\u0000It developed a control architecture emulating the functionality of the human nervous system. The experimental validations were performed on the HYDROïD. The results demonstrated 50% advancements in the update rate compared to other humanoids and 30% in the latency of the master processor and the control tasks.\u0000","PeriodicalId":501194,"journal":{"name":"Robotic Intelligence and Automation","volume":"5 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141267532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：