Hui Zhang, Xiangrong Xu, Zuojun Zhu, Tianya You, Qiqi Li, Dan Li
{"title":"Surface Defect Detection for Die Castings Based on the Improved YOLOv5 Method","authors":"Hui Zhang, Xiangrong Xu, Zuojun Zhu, Tianya You, Qiqi Li, Dan Li","doi":"10.1109/ICARM58088.2023.10218864","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218864","url":null,"abstract":"This article proposes a novel method for surface defect recognition of die-casting parts based on deep learning YOLOv5 network model. Previous methods, such as based on machine learning and based on template matching, can only classify defect type, and the accuracy and generalization of them are limited. The novel surface defects recognition method based on YOLOv5 algorithm can classify surface defects of die castings and accurately locate their positions which is import in powder metallurgy. To train the casting surface defect detection method based on the YOLOv5 algorithm, the transfer learning is initialized and trained on the Microsoft COCO dataset, we expanded the dataset based on the cyclegan algorithm, and used the kmeans++ algorithm to initialize the anchor-box size. We set up many groups of experiments, and experimental results show that our proposed method performed better than the previous method in joint identification of surface defects, and it can achieve very high mean of average precision (mAP@.5 and mAP@.5:.95) with more than 95%.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123889476","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 Pumpless Layflat Tube-Based Pneumatic Bending Actuator for Soft Assistive Glove","authors":"Senyuan Lin, Hao Liu, Changchun Wu, Yonghua Chen","doi":"10.1109/ICARM58088.2023.10218810","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218810","url":null,"abstract":"Layflat tube (LFT) is a soft tube that is pressed flat for easy winding onto a spool and continuous use. When inflating an LFT, the width of the FLT will contract, and the flat side of the FLT will expand. Based on this feature, a layflat tube-based pneumatic bending actuator (LFTPBA) is proposed and used for finger actuation in soft robotic glove design. Five LFTPBAs are mounted on a fabric glove to assist finger flexion. To eliminate noise and vibration of a normal pump system, a bellow actuation method is proposed. The finger flexion angle and bending speed can be controlled by motors directly. A mathematical model is developed to investigate the relationship between the LFTPBA flexion angle and bellow compression displacement. Besides, a finite element analysis of the LFTPBA bending trajectory versus pressure increase is also conducted. Compared with a fabric-based pneumatic bending actuator, the proposed system can generate 57% more blocked tip force (from 9 N to 14.13 N). A prototype assistive glove has been developed to demonstrate various grasping operations via a hand model.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125193070","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":"Mechanism Design of a Multi-rod and Wireline-coring Drill Tool for Seafloor Sediment-sampling Robots","authors":"Jiabin Liu, Jiashu Feng, Jinchang Xu, Hongyu Wei, Haifei Zhu, Tao Zhang","doi":"10.1109/ICARM58088.2023.10218942","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218942","url":null,"abstract":"Seafloor sediments offer a wealth of knowledge on the historical evolution and minerals of the ocean. The exploration and exploitation of deep-sea resources are crucial for the sustainable development of human society. Sampling robots have taken the role of humans to sample seafloor sediment for scientific or engineering research in the deep sea. The drill tool is a core mechanism that affects the coring rate, coring time, and coring size of seafloor sediment-sampling robots for scientific or engineering investigation. The operational complexity of conventional coring and wireline coring is discussed in this paper. The considerations of the multi-rod and wireline-coring drill tool for deep seafloor sediment sampling are analyzed. A multi-rod and wireline-coring drill tool is proposed, including a core barrel assembly and an overshot assembly. The basic structure and working principle of the drill tool are introduced. The overall assembly and prototype of the proposed drill tool are described. This paper can provide some theoretical and technical references for the innovative design of drill tools for seafloor sediment sampling.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125108476","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 Adaptive Unscented Kalman Filter for Needle Steering with Missing Measurements","authors":"Dikai Lou, Lihong Liu, Sheng Fang, Jiabin Hu, Dan Zhang, Huageng Liang","doi":"10.1109/ICARM58088.2023.10218793","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218793","url":null,"abstract":"In the robot-assisted puncture surgery, the measurements from the ultrasound image may be lost due to the uneven distribution of image grayscale and blurred image which could affect the estimation accuracy of the filter. Furthermore, the probability of the missing measurement cannot be precisely known due to the heterogeneity of biological tissue and the complexity of the surgery environment. Aiming at these problems, an adaptive unscented Kalman filter algorithm based on virtual measurement noise is proposed to estimate the pose of the needle tip in this paper. The missing measurement is converted into a virtual measurement noise which has an indefinite variance. Then the variance of the virtual noise is estimated in real-time to suppress the influence of missing measurements during the puncture process. Furthermore, according to the strong tracking filtering algorithm, an adaptive fading factor is constructed to reduce the sensitivity of the filter to the statistical characteristics of the noise. Finally, the proposed filter is applied to estimate the pose of the puncture needle and the effectiveness of the proposed method is verified via simulation experiments.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125646101","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}
Le Chang, Rongjie Kang, Changchao Sun, Peikang Yuan, Tong Wang, Zhibin Song, J. Dai
{"title":"Visual-Servo Based End-Effector Control for Continuum Robots","authors":"Le Chang, Rongjie Kang, Changchao Sun, Peikang Yuan, Tong Wang, Zhibin Song, J. Dai","doi":"10.1109/ICARM58088.2023.10218886","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218886","url":null,"abstract":"Delicate manipulation for continuum robots remains challenging. The key is to establish a motion controller with real-time perception, fast response, and high precision. Integrating visual sensors into the system can enhance the precision of end position control while minimizing uncertainties in the robot model. In this paper, a depth camera is used to identify the Aruco code to provide pose information to the continuum robot. Then the end-effector is controlled to achieve horizontal linear displacement and plug into a socket based on the pose information. Based on experimental findings, it has been demonstrated that the control accuracy can achieve a level of precision in the centimeter range. The presented methods expand the potential scenarios of the continuum robot.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122858049","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}
Ye Wang, Junjie Fu, Meiqi Tang, Shuai Wang, G. Wen
{"title":"Collision Avoidance Visual Coverage Control of Multiple Second-Order Mobile Aerial Agents","authors":"Ye Wang, Junjie Fu, Meiqi Tang, Shuai Wang, G. Wen","doi":"10.1109/ICARM58088.2023.10218836","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218836","url":null,"abstract":"This work investigates the collision avoidance visual coverage control problem of multiple second-order Mobile Aerial Agents (MAAs). When performing coverage control tasks, MAAs need to consider both the sensing model and the sensing quality. An integrated coverage performance function is defined to evaluate the coverage effect. For the coverage control problem, a novel distributed control law is proposed to drive the second-order MAA system to converge to a locally optimal coverage configuration, and the stability of the corresponding coverage control system is proven by introducing a Lyapunov-like function. Moreover, a potential function term is employed to avoid collision between the MAAs and improve the safety performance of the system. Finally, numerical examples are given which demonstrate the effectiveness and practicality of the proposed control law.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"402 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131754457","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":"Intelligent Prediction Method of Hot Spot Temperature in Transformer by Using CNN-LSTM&GRU Network","authors":"Yuxi Dong, Zhenxin Zhong, Yun Zhang, Ruifeng Zhu, Huiling Wen, Rongzhen Han","doi":"10.1109/ICARM58088.2023.10218818","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218818","url":null,"abstract":"In this paper, an intelligent prediction method of hot spot temperature in transformer abnormal thermal diffusion by using CNN-LSTM&GRU network is proposed. With the continuous development of power grid, as an important equipment in transmission line, the stable operation of transformer is very important. However, the increase of power load demand leads to frequent transformer accidents in recent years, among which, hot spot temperature is the key factor causing transformer thermal aging and even fire. Due to the anisotropy of transformer materials, the thermal diffusion of transformer is an abnormal diffusion process, making the traditional method difficult to predict the hotspot temperature efficiently and accurately. Therefore, this paper studies a deep learning algorithm based on CNN-LSTM&GRU network to predict transformer hot spot temperature. We conduct experiments, and the final results indicated the performance of our model is better than that of the traditional approach in transformer hot spot temperature prediction tasks.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116522225","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":"FaRo-PPF: Fast and Robust Point Pair Feature for 6D Pose Estimation in Industrial Stamping","authors":"Cheng He, Xuebo Zhang, Zhenjie Zhao","doi":"10.1109/ICARM58088.2023.10218804","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218804","url":null,"abstract":"Estimating 6D poses of targets efficiently is critical for industrial stamping tasks, in which the Point Pair Feature (PPF) method has been widely used. Based on PPF, this paper proposes Fast and Robust PPF, i.e. FaRo-PPF, which improves PPF in the following three key aspects: adaptive down-sampling based on surface features, point pair matching based on voting ball, and normal-based pose verification. The three designs alleviate existing problems of the local matching stage in PPF, and make FaRo-PPF a stronger method of 6D pose estimation in industrial stamping. To demonstrate the effectiveness of FaRo-PPF, we compare it with PPF on five publically available datasets. Experiment results showed that FaRo-PPF is able to significantly improve accuracy by about 15% and reduce the execution time by about 40% across all test data. We further conduct a grasping and assembly experiment on a physical robot arm, and similar improvement can be observed. FaRo-PPF achieves a higher success rate of assembly and reduces the execution time by about 50%.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127831038","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":"Energy-aware Coverage Path Planning of Multi-UAV Based on Relative Distance Scaling Cluster Method","authors":"Shen Liu, Xiuxian Li, Min Meng, Xin Gong","doi":"10.1109/ICARM58088.2023.10218969","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218969","url":null,"abstract":"In recent years, unmanned aerial vehicle (UAV) aerial photography becomes a new method of disaster area exploration. UAVs have been widely used in the fields for aerial photography, monitoring, transportation, communication and so on. They can expand the dimension and scale of search and rescue (SAR) work, reduce the cost of human and material resources, and improve the efficiency of SAR work. Considering the limited of a single UAV, multi-UAV and energy-aware path planning algorithms are proposed here for SAR missions, which improve the cluster algorithm. In the algorithm design, we take the energy consumption of each UAV as an important factor for optimizing the division of search area, and propose the spiral search path generation algorithm. And numerical examples corroborate the effectiveness of the theoretical results.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133211181","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":"Point Cloud Segmentation of Breast Ultrasound Regions to be Scanned by Fusing 2D Image Instance Segmentation and Keypoint Detection","authors":"Jiyong Tan, Hui Qin, Xinxing Chen, Jiawang Li, Yuan-Fang Li, Bing Li, Yuquan Leng, Chenglong Fu","doi":"10.1109/ICARM58088.2023.10218846","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218846","url":null,"abstract":"Automatic segmentation of the region of interest to be scanned (ROIS) is one of the key tasks to achieve autonomous scanning of ultrasound robots. By analyzing breast ROIS in an unstructured environment, a point cloud segmentation framework for the breast ultrasound ROIS that incorporates 2D image instance segmentation and keypoint detection is proposed. Firstly, 2D image instance segmentation based on the improved SOLOv2 is performed to extract the human torso point cloud in the unstructured environment. Then, based on YOLO-Pose, the keypoints of human body are automatically detected, and the upper and lower lines of breast ROIS are obtained according to the constraint matching relationship between breast ROIS and keypoints, and finally the point cloud of breast ROIS is obtained effectively and accurately. Experiments show that the proposed framework can achieve automatic segmentation of breast ROIS within 2 s.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"358 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133287712","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}