Robotic Intelligence and Automation最新文献

{"title":"An efficient steel defect detection model based on multi-scale information extraction","authors":"Wenshen Xu, Yifan Zhang, Xinhang Jiang, Jun Lian, Ye Lin","doi":"10.1108/ria-03-2024-0065","DOIUrl":"https://doi.org/10.1108/ria-03-2024-0065","url":null,"abstract":"\u0000Purpose\u0000In the field of steel defect detection, the existing detection algorithms struggle to achieve a satisfactory balance between detection accuracy, computational cost and inference speed due to the interference from complex background information, the variety of defect types and significant variations in defect morphology. To solve this problem, this paper aims to propose an efficient detector based on multi-scale information extraction (MSI-YOLO), which uses YOLOv8s as the baseline model.\u0000\u0000\u0000Design/methodology/approach\u0000First, the authors introduce an efficient multi-scale convolution with different-sized convolution kernels, which enables the feature extraction network to accommodate significant variations in defect morphology. Furthermore, the authors introduce the channel prior convolutional attention mechanism, which allows the network to focus on defect areas and ignore complex background interference. Considering the lightweight design and accuracy improvement, the authors introduce a more lightweight feature fusion network (Slim-neck) to improve the fusion effect of feature maps.\u0000\u0000\u0000Findings\u0000MSI-YOLO achieves 79.9% mean average precision on the public data set Northeastern University (NEU)-DET, with a model size of only 19.0 MB and an frames per second of 62.5. Compared with other state-of-the-art detectors, MSI-YOLO greatly improves the recognition accuracy and has significant advantages in computational cost and inference speed. Additionally, the strong generalization ability of MSI-YOLO is verified on the collected industrial site steel data set.\u0000\u0000\u0000Originality/value\u0000This paper proposes an efficient steel defect detector with high accuracy, low computational cost, excellent detection speed and strong generalization ability, which is more valuable for practical applications in resource-limited industrial production.\u0000","PeriodicalId":379181,"journal":{"name":"Robotic Intelligence and Automation","volume":"53 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141919072","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}

{"title":"Recognition and pose estimation method for random bin picking considering incomplete point cloud scene","authors":"Yan Kan, Hao Li, Zhengtao Chen, Changjiang Sun, Hao Wang, Joachim Seidelmann","doi":"10.1108/ria-07-2023-0089","DOIUrl":"https://doi.org/10.1108/ria-07-2023-0089","url":null,"abstract":"\u0000Purpose\u0000This paper aims to propose a stable and precise recognition and pose estimation method to deal with the difficulties that industrial parts often present, such as incomplete point cloud data due to surface reflections, lack of color texture features and limited availability of effective three-dimensional geometric information. These challenges lead to less-than-ideal performance of existing object recognition and pose estimation methods based on two-dimensional images or three-dimensional point cloud features.\u0000\u0000\u0000Design/methodology/approach\u0000In this paper, an image-guided depth map completion method is proposed to improve the algorithm's adaptability to noise and incomplete point cloud scenes. Furthermore, this paper also proposes a pose estimation method based on contour feature matching.\u0000\u0000\u0000Findings\u0000Through experimental testing on real-world and virtual scene dataset, it has been verified that the image-guided depth map completion method exhibits higher accuracy in estimating depth values for depth map hole pixels. The pose estimation method proposed in this paper was applied to conduct pose estimation experiments on various parts. The average recognition accuracy in real-world scenes was 88.17%, whereas in virtual scenes, the average recognition accuracy reached 95%.\u0000\u0000\u0000Originality/value\u0000The proposed recognition and pose estimation method can stably and precisely deal with the difficulties that industrial parts present and improve the algorithm's adaptability to noise and incomplete point cloud scenes.\u0000","PeriodicalId":379181,"journal":{"name":"Robotic Intelligence and Automation","volume":"54 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141918974","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}

{"title":"An efficient steel defect detection model based on multi-scale information extraction","authors":"Wenshen Xu, Yifan Zhang, Xinhang Jiang, Jun Lian, Ye Lin","doi":"10.1108/ria-03-2024-0065","DOIUrl":"https://doi.org/10.1108/ria-03-2024-0065","url":null,"abstract":"\u0000Purpose\u0000In the field of steel defect detection, the existing detection algorithms struggle to achieve a satisfactory balance between detection accuracy, computational cost and inference speed due to the interference from complex background information, the variety of defect types and significant variations in defect morphology. To solve this problem, this paper aims to propose an efficient detector based on multi-scale information extraction (MSI-YOLO), which uses YOLOv8s as the baseline model.\u0000\u0000\u0000Design/methodology/approach\u0000First, the authors introduce an efficient multi-scale convolution with different-sized convolution kernels, which enables the feature extraction network to accommodate significant variations in defect morphology. Furthermore, the authors introduce the channel prior convolutional attention mechanism, which allows the network to focus on defect areas and ignore complex background interference. Considering the lightweight design and accuracy improvement, the authors introduce a more lightweight feature fusion network (Slim-neck) to improve the fusion effect of feature maps.\u0000\u0000\u0000Findings\u0000MSI-YOLO achieves 79.9% mean average precision on the public data set Northeastern University (NEU)-DET, with a model size of only 19.0 MB and an frames per second of 62.5. Compared with other state-of-the-art detectors, MSI-YOLO greatly improves the recognition accuracy and has significant advantages in computational cost and inference speed. Additionally, the strong generalization ability of MSI-YOLO is verified on the collected industrial site steel data set.\u0000\u0000\u0000Originality/value\u0000This paper proposes an efficient steel defect detector with high accuracy, low computational cost, excellent detection speed and strong generalization ability, which is more valuable for practical applications in resource-limited industrial production.\u0000","PeriodicalId":379181,"journal":{"name":"Robotic Intelligence and Automation","volume":"1 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141919519","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}

{"title":"Recognition and pose estimation method for random bin picking considering incomplete point cloud scene","authors":"Yan Kan, Hao Li, Zhengtao Chen, Changjiang Sun, Hao Wang, Joachim Seidelmann","doi":"10.1108/ria-07-2023-0089","DOIUrl":"https://doi.org/10.1108/ria-07-2023-0089","url":null,"abstract":"\u0000Purpose\u0000This paper aims to propose a stable and precise recognition and pose estimation method to deal with the difficulties that industrial parts often present, such as incomplete point cloud data due to surface reflections, lack of color texture features and limited availability of effective three-dimensional geometric information. These challenges lead to less-than-ideal performance of existing object recognition and pose estimation methods based on two-dimensional images or three-dimensional point cloud features.\u0000\u0000\u0000Design/methodology/approach\u0000In this paper, an image-guided depth map completion method is proposed to improve the algorithm's adaptability to noise and incomplete point cloud scenes. Furthermore, this paper also proposes a pose estimation method based on contour feature matching.\u0000\u0000\u0000Findings\u0000Through experimental testing on real-world and virtual scene dataset, it has been verified that the image-guided depth map completion method exhibits higher accuracy in estimating depth values for depth map hole pixels. The pose estimation method proposed in this paper was applied to conduct pose estimation experiments on various parts. The average recognition accuracy in real-world scenes was 88.17%, whereas in virtual scenes, the average recognition accuracy reached 95%.\u0000\u0000\u0000Originality/value\u0000The proposed recognition and pose estimation method can stably and precisely deal with the difficulties that industrial parts present and improve the algorithm's adaptability to noise and incomplete point cloud scenes.\u0000","PeriodicalId":379181,"journal":{"name":"Robotic Intelligence and Automation","volume":"2 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141919488","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}

{"title":"Generalizable and precise control based on equilibrium-point hypothesis for musculoskeletal robotic system","authors":"Yaxiong Wu, Jiahao Chen, Hong Qiao","doi":"10.1108/ria-01-2024-0022","DOIUrl":"https://doi.org/10.1108/ria-01-2024-0022","url":null,"abstract":"Purpose\u0000The purpose of this study is realizing human-like motions and performance through musculoskeletal robots and brain-inspired controllers. Human-inspired robotic systems, owing to their potential advantages in terms of flexibility, robustness and generality, have been widely recognized as a promising direction of next-generation robots.\u0000\u0000Design/methodology/approach\u0000In this paper, a deep forward neural network (DFNN) controller was proposed inspired by the neural mechanisms of equilibrium-point hypothesis (EPH) and musculoskeletal dynamics.\u0000\u0000Findings\u0000First, the neural mechanism of EPH in human was analyzed, providing the basis for the control scheme of the proposed method. Second, the effectiveness of proposed method was verified by demonstrating that equilibrium states can be reached under the constant activation signals. Finally, the performance was quantified according to the experimental results.\u0000\u0000Originality/value\u0000Based on the neural mechanism of EPH, a DFNN was crafted to simulate the process of activation signal generation in human motion control. Subsequently, a bio-inspired musculoskeletal robotic system was designed, and the high-precision target-reaching tasks were realized in human manner. The proposed methods provide a direction to realize the human-like motion in musculoskeletal robots.\u0000","PeriodicalId":379181,"journal":{"name":"Robotic Intelligence and Automation","volume":"71 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141360339","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}

{"title":"A goal-conditioned policy search method with multi-timescale value function tuning","authors":"Zhihong Jiang, Jiachen Hu, Yan Zhao, Xiao Huang, Hui Li","doi":"10.1108/ria-11-2023-0167","DOIUrl":"https://doi.org/10.1108/ria-11-2023-0167","url":null,"abstract":"\u0000Purpose\u0000Current reinforcement learning (RL) algorithms are facing issues such as low learning efficiency and poor generalization performance, which significantly limit their practical application in real robots. This paper aims to adopt a hybrid model-based and model-free policy search method with multi-timescale value function tuning, aiming to allow robots to learn complex motion planning skills in multi-goal and multi-constraint environments with a few interactions.\u0000\u0000\u0000Design/methodology/approach\u0000A goal-conditioned model-based and model-free search method with multi-timescale value function tuning is proposed in this paper. First, the authors construct a multi-goal, multi-constrained policy optimization approach that fuses model-based policy optimization with goal-conditioned, model-free learning. Soft constraints on states and controls are applied to ensure fast and stable policy iteration. Second, an uncertainty-aware multi-timescale value function learning method is proposed, which constructs a multi-timescale value function network and adaptively chooses the value function planning timescales according to the value prediction uncertainty. It implicitly reduces the value representation complexity and improves the generalization performance of the policy.\u0000\u0000\u0000Findings\u0000The algorithm enables physical robots to learn generalized skills in real-world environments through a handful of trials. The simulation and experimental results show that the algorithm outperforms other relevant model-based and model-free RL algorithms.\u0000\u0000\u0000Originality/value\u0000This paper combines goal-conditioned RL and the model predictive path integral method into a unified model-based policy search framework, which improves the learning efficiency and policy optimality of motor skill learning in multi-goal and multi-constrained environments. An uncertainty-aware multi-timescale value function learning and selection method is proposed to overcome long horizon problems, improve optimal policy resolution and therefore enhance the generalization ability of goal-conditioned RL.\u0000","PeriodicalId":379181,"journal":{"name":"Robotic Intelligence and Automation","volume":"74 24","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141358008","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}

{"title":"Motion optimization based on hierarchical iterative parameter learning for complicated trajectory","authors":"Yi Guo, Tianyi Huang, Haohui Huang, Huangting Zhao, Weitao Liu","doi":"10.1108/ria-11-2023-0168","DOIUrl":"https://doi.org/10.1108/ria-11-2023-0168","url":null,"abstract":"\u0000Purpose\u0000The purpose of this paper is to propose an accurate and practical imitation learning for robotics. The modified dynamic movement primitives (DMPs), global fitting DMPs (GLDMPs), is presented. Framework design, theoretical derivation and stability proof of GLDMPs are discussed in the paper.\u0000\u0000\u0000Design/methodology/approach\u0000Based on the DMPs, the hierarchical iterative parameter adaptive framework is developed as the hierarchical iteration stage of the GLDMPs to tune the designed parameters adaptively to extract richer features. Inspired by spatial transformations, the coupling analytical module which can be regarded as a reversible transformation is proposed to analyze the high-dimensional coupling information and transfer it to trajectory.\u0000\u0000\u0000Findings\u0000With the proposed framework and module, DMPs derive majority features of the demonstration and cope with three-dimensional rotations. Moreover, GLDMPs achieve favorable performance without specialized knowledge. The modified method has been demonstrated to be stable and convergent through inference.\u0000\u0000\u0000Originality/value\u0000GLDMPs have an advantage in accuracy, adaptability and practicality for it is capable of adaptively computing parameters to extract richer features and handling variations in coupling information. With demonstration and simple parameter settings, GLDMPs can exhibit excellent and stable performance, accomplish learning and generalize in other regions. The proposed framework and module in the paper are useful for imitation learning in robotics and could be intuitive for similar imitation learning methods.\u0000","PeriodicalId":379181,"journal":{"name":"Robotic Intelligence and Automation","volume":" 14","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141374046","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}

{"title":"Research on the trajectory planning and global optimization strategy of cold spraying technique for complex products coating preparation","authors":"Xu Yang, Xin Yue, Zhenhua Cai, Shengshi Zhong","doi":"10.1108/ria-08-2023-0108","DOIUrl":"https://doi.org/10.1108/ria-08-2023-0108","url":null,"abstract":"Purpose\u0000This paper aims to present a set of processes for obtaining the global spraying trajectory of a cold spraying robot on a complex surface.\u0000\u0000Design/methodology/approach\u0000The complex workpiece surfaces in the project are first divided by triangular meshing. Then, the geodesic curve method is applied for local path planning. Finally, the subsurface trajectory combination optimization problem is modeled as a GTSP problem and solved by the ant colony algorithm, where the evaluation scores and the uniform design method are used to determine the optimal parameter combination of the algorithm. A global optimized spraying trajectory is thus obtained.\u0000\u0000Findings\u0000The simulation results show that the proposed processes can achieve the shortest global spraying trajectory. Moreover, the cold spraying experiment on the IRB4600 six-joint robot verifies that the spraying trajectory obtained by the processes can ensure a uniform coating thickness.\u0000\u0000Originality/value\u0000The proposed processes address the issue of different parameter combinations, leading to different results when using the ant colony algorithm. The two methods for obtaining the optimal parameter combinations can solve this problem quickly and effectively, and guarantee that the processes obtain the optimal global spraying trajectory.\u0000","PeriodicalId":379181,"journal":{"name":"Robotic Intelligence and Automation","volume":"58 17","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140656390","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}

{"title":"Path planning for robot search task using belief criteria decision-making","authors":"Long Zhao, Xiaoye Liu, Linxiang Li, Run Guo, Yang Chen","doi":"10.1108/ria-11-2023-0173","DOIUrl":"https://doi.org/10.1108/ria-11-2023-0173","url":null,"abstract":"Purpose\u0000This study aims to realize efficient, fast and safe robot search task, the belief criteria decision-making approach is proposed to solve the object search task with an uncertain location.\u0000\u0000Design/methodology/approach\u0000The study formulates the robot search task as a partially observable Markov decision process, uses the semantic information to evaluate the belief state and designs the belief criteria decision-making approach. A cost function considering a trade-off among belief state, path length and movement effort is modelled to select the next best location in path planning.\u0000\u0000Findings\u0000The semantic information is successfully modelled and propagated, which can represent the belief of finding object. The belief criteria decision-making (BCDM) approach is evaluated in both Gazebo simulation platform and physical experiments. Compared to greedy, uniform and random methods, the performance index of path length and execution time is superior by BCDM approach.\u0000\u0000Originality/value\u0000The prior knowledge of robot working environment, especially semantic information, can be used for path planning to achieve efficient task execution in path length and execution time. The modelling and updating of environment information can lead a promising research topic to realize a more intelligent decision-making method for object search task.\u0000","PeriodicalId":379181,"journal":{"name":"Robotic Intelligence and Automation","volume":"58 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140656399","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}

{"title":"Research on decoupling control of single leg joints of hydraulic quadruped robot","authors":"Bing-Tuan Gao, Hongjian Zhao, Wenlong Han, Shilong Xue","doi":"10.1108/ria-06-2023-0080","DOIUrl":"https://doi.org/10.1108/ria-06-2023-0080","url":null,"abstract":"\u0000Purpose\u0000This study proposes a predictive neural network model reference decoupling control method for the coupling problem between the leg joints of hydraulic quadruped robots, and verifies its decoupling effect..\u0000\u0000\u0000Design/methodology/approach\u0000The machine–hydraulic cross-linking coupling is studied as the coupling behavior of the hydraulically driven quadruped robot, and the mechanical dynamics coupling force of the robot system is controlled as the disturbance force of the hydraulic system through the Jacobian matrix transformation. According to the principle of multivariable decoupling, a prediction-based neural network model reference decoupling control method is proposed; each module of the control algorithm is designed one by one, and the stability of the system is analyzed by the Lyapunov stability theorem.\u0000\u0000\u0000Findings\u0000The simulation and experimental research on the robot joint decoupling control method is carried out, and the prediction-based neural network model reference decoupling control method is compared with the decoupling control method without any decoupling control method. The results show that taking the coupling effect experiment between the hip joint and knee joint as an example, after using the predictive neural network model reference decoupling control method, the phase lag of the hip joint response line was reduced from 20.3° to 14.8°, the amplitude attenuation was reduced from 1.82% to 0.21%, the maximum error of the knee joint coupling line was reduced from 0.67 mm to 0.16 mm and the coupling effect between the hip joint and knee joint was reduced from 1.9% to 0.48%, achieving good decoupling.\u0000\u0000\u0000Originality/value\u0000The prediction-based neural network model reference decoupling control method proposed in this paper can use the neural network model to predict the next output of the system according to the input and output. Finally, the weights of the neural network are corrected online according to the predicted output and the given reference output, so that the optimization index of the neural network decoupling controller is extremely small, and the purpose of decoupling control is achieved.\u0000","PeriodicalId":379181,"journal":{"name":"Robotic Intelligence and Automation","volume":"70 s288","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140694040","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}