{"title":"Impedance-based Foot-end Torque Vibration Isolation Control of Parallel Structure Wheel-legged Robot","authors":"Junfeng Xue, Shou-kun Wang, Jiehao Li, Junzheng Wang, Jialong Zhang, Zhihua Chen","doi":"10.1109/WRCSARA57040.2022.9903930","DOIUrl":"https://doi.org/10.1109/WRCSARA57040.2022.9903930","url":null,"abstract":"Vibration isolation control is a major challenge for the wheeled motion of hexapod robot in unknown terrain, especially when the ground will produce disturbing torque on the foot-end. In this paper, a torque vibration isolation control method based on impedance is proposed to counteract the disturbance torque at the foot-end of the robot during wheel motion. Firstly, the kinematics model of the robot single leg Stewart platform is introduced, and the kinematics formula of the foot rotating around the X-axis of its tip center is derived. Secondly, a torque impedance algorithm with torque as input and foot attitude angle as output is established. Finally, the joint simulation based on Python and V-rep is carried out. The simulation results show that the disturbance torque at the foot-end can be largely offset by the torque impedance control method, which improves the stability of the fuselage attitude, and verifies the effectiveness of the algorithm.","PeriodicalId":106730,"journal":{"name":"2022 WRC Symposium on Advanced Robotics and Automation (WRC SARA)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127074933","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}
Xiaowen Zhang, S. Yuan, F. Luan, Jiaqi Lv, Guifu Liu
{"title":"Similarity Mask Mixed Attention for YOLOv5 Small Ship Detection of Optical Remote Sensing Images","authors":"Xiaowen Zhang, S. Yuan, F. Luan, Jiaqi Lv, Guifu Liu","doi":"10.1109/WRCSARA57040.2022.9903957","DOIUrl":"https://doi.org/10.1109/WRCSARA57040.2022.9903957","url":null,"abstract":"Ship detection has always been an important and challenging task. Small ship targets and complex backgrounds in optical remote sensing images can both lead to false alarms and missed alarms in detection. The YOLO series algorithms have been widely used in optical remote sensing ship target detection, which has the advantage of fast detection speed. However, the YOLO series algorithms have poor detection performance when facing small targets. Therefore, we propose a new algorithm, SMMA-YOLOv5, which can improve the model detection accuracy without significantly increasing the model size. We first introduce a self-attention mechanism to replace some of the convolutional layers to capture the global information of the feature map. Second, we integrate an efficient channel attention (ECA) model to the self-attention mechanism to enable information interaction between channels without adding additional computational overhead. Furthermore, we propose a new similarity mask structure to filter out the invalid regions in the feature map based on the elements’ similarity. The experiments on the public MASATI ship dataset indicate that SMMA-YOLOv5 improves Precision by 3.9%, Recall by 5.3%, and AP by 5.4%, and prove the effectiveness of the algorithm while maintaining real-time detection.","PeriodicalId":106730,"journal":{"name":"2022 WRC Symposium on Advanced Robotics and Automation (WRC SARA)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125974193","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 hybrid paradigm based on steady-state visual evoked potentials and motor imagery","authors":"Jiaxin Li, Jing Zhao, Ye Shi","doi":"10.1109/WRCSARA57040.2022.9903988","DOIUrl":"https://doi.org/10.1109/WRCSARA57040.2022.9903988","url":null,"abstract":"Hybrid brain-computer interfaces have the advantage of higher accuracy and more commands. This paper presents a hybrid brain-computer interface (BCI) paradigm based on steady-state visual evoked potentials (SSVEP) and motor imagery(MI).The subject started the first SSVEP task, and 2 seconds later the subject was asked to perform the second MI task and keep both tasks running simultaneously. The moment when the second task was joined was defined as the moment of switching. The performance of SSVEP was improved after the switch. Five healthy subjects participated in the experiment. The experimental results demonstrated the improvement of SSVEP classification accuracy, in addition to demonstrating that the performance of most of the subject MI was not affected in the paradigm.","PeriodicalId":106730,"journal":{"name":"2022 WRC Symposium on Advanced Robotics and Automation (WRC SARA)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129291274","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":"Design of Photovoltaic Glass Automatic Stacking and Paper Laying Robot","authors":"A. Pan, B. Q. Liu, C. Ye","doi":"10.1109/WRCSARA57040.2022.9903977","DOIUrl":"https://doi.org/10.1109/WRCSARA57040.2022.9903977","url":null,"abstract":"In the process of palletizing photovoltaic glass, due to the influence of temperature and humidity, the surface of the photovoltaic glass will become moldy or two pieces of the photovoltaic glass will be glued after a long time, which will affect their quality and use. In this paper, a kind of photovoltaic glass automatic stacking and paper laying robot is designed, the paper roll is placed on the rotating shaft, and the paper is put out with the rotation of the rotating shaft, Paper is placed between each layer of glass, driven back and forth by a car that moves above. The paper does not need to be cut in the process of paper laying, which has high efficiency, and the paper will not slide under the action of gravity. A good practical effect has been achieved in glass production, and the production efficiency and storage quality have been significantly improved.","PeriodicalId":106730,"journal":{"name":"2022 WRC Symposium on Advanced Robotics and Automation (WRC SARA)","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126710075","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":"Image Based River Navigation System of Catamaran USV with Image Semantic Segmentation","authors":"Ping Yang, Ch. H. Song, L. Chen, Weicheng Cui","doi":"10.1109/WRCSARA57040.2022.9903932","DOIUrl":"https://doi.org/10.1109/WRCSARA57040.2022.9903932","url":null,"abstract":"USV’s river navigation system is very complex, including USV’s environmental perception, USV’s positioning, obstacle avoidance, and path planning. Different sensors are required in various applications, such as lidar or cameras in environmental perception, GPS or IMU in positioning, and ultrasonic sensors or cameras in obstacle avoidance. As an intuitive and affordable sensor, the cameras can be used for environment perception, obstacle recognition, and distance estimation for component stereo vision systems over a catamaran USV. This paper proposes an image based USV river navigation system. The main functions include riverbank line recognition and distance estimation. Aiming at the inaccurate of traditional riverbank line detection, we design a line segment detection algorithm for riverbank based on image semantic segmentation, which can effectively reduce the interference of the object’s texture on edge recognition while ensuring the object edge recognition. Subsequently, according to the built stereo vision system, the distance of the detected riverbank line is estimated for following navigation, obstacle avoidance, or other operations. We further demonstrate the designed catamaran USV and its stereo vision system. Compared with the traditional unsupervised straight line detection algorithm, its riverbank line detection function has been significantly improved, and its real-time ranging process is also more intuitive.","PeriodicalId":106730,"journal":{"name":"2022 WRC Symposium on Advanced Robotics and Automation (WRC SARA)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123381565","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":"State estimation of QAUV Based on dynamic model","authors":"Daxiong Ji, Rui Wang, Zhi Wang, Qinyuan Ren","doi":"10.1109/WRCSARA57040.2022.9903961","DOIUrl":"https://doi.org/10.1109/WRCSARA57040.2022.9903961","url":null,"abstract":"Quadrotor Autonomous Underwater Vehicle (QAUV) is a new type of intelligent robot with simple structure and high motion efficiency. Like other underwater robots, its state acquisition has always been a thorny problem. In order to realize low-cost control of QAUV, a state estimation method based on 6 Degrees-Of-Freedom (DOF) dynamic model is proposed in this paper. By analyzing the unique coupling motion characteristics of the QAIJV, the dynamic model is simplified, and the relationship between inclination and velocity is obtained when moving at a uniform speed. According to the simulation and theoretical derivation, the estimation method is extended from uniform motion to generalized forward and translational motion. The simulation results show that the state values obtained by this method have high accuracy, low cost and convenient use.","PeriodicalId":106730,"journal":{"name":"2022 WRC Symposium on Advanced Robotics and Automation (WRC SARA)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125685549","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}
Yi Lv, Yu Ning, Yu Shen, Junchen Wang, Mingbo Zhang
{"title":"A Real-time Interactive 3D Ultrasound Imaging System","authors":"Yi Lv, Yu Ning, Yu Shen, Junchen Wang, Mingbo Zhang","doi":"10.1109/WRCSARA57040.2022.9903990","DOIUrl":"https://doi.org/10.1109/WRCSARA57040.2022.9903990","url":null,"abstract":"Real-time 3D ultrasound (US) imaging has attracted more attention since it can display spatial 3D images of tissues and organs in real time to provide important information for diagnosis and intervention. In this study, Bezier interpolation and PNN reconstruction algorithms are combined to achieve real-time repeatable 3D reconstruction. A real-time interactive 3D US imaging system with a 2DB-mode probe is developed. The system employs an optical measuring equipment to collect six degrees of freedom (6-DoF) poses of the US probe. 2D US image acquisition using a calibrated probe with the pose information is performed to reconstruct a 3D volume. A multi-thread scheme is proposed to achieve real-time data acquisition, overlapped 3D reconstruction and volume visualization. Interactive functions and image segmentation enable users to freely select regions of interest (ROI) and adjust image color and opacity. The system was evaluated on a 3D printing femur model, a neck phantom and human carotid arteries. The surface point clouds segmented from the reconstructed 3D volumes were rigidly registered with the models whose CT scans were available. The surface matching error was used as the reconstruction error. The 3D volumes were reconstructed with different voxel sizes of (0.5 mm, 1.0 mm, 1.5 mm). The reconstruction errors of the femur and trachea model were (0.85 mm, 0.99 mm, 1.43 mm) and (0.96 mm, 1.17 mm, 1.37 mm), respectively. The 3D reconstruction on real human carotid arteries has confirmed the clinical feasibility.","PeriodicalId":106730,"journal":{"name":"2022 WRC Symposium on Advanced Robotics and Automation (WRC SARA)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132113336","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":"Deep Learning Assisted Automated Separation Platform of Single Cells and Microparticles Using Optoelectronic Tweezers","authors":"Jiawei Zhao, Chunyuan Gan, Jiaying Zhang, Shuzhang Liang, Jiapeng Yang, Lin Feng","doi":"10.1109/WRCSARA57040.2022.9903963","DOIUrl":"https://doi.org/10.1109/WRCSARA57040.2022.9903963","url":null,"abstract":"A deep learning-assisted automated separation platform of single cells and microparticles using optoelectronic tweezers was proposed in this paper, which allows accurate manipulation and long-term dynamic observation of single cells without complex microfluidic structures. A single-cell detector based on YOLOv5 was developed to realize single-cell automation and high throughput recognition in optoelectronic tweezers chips. Then these recognized cells or particles were captured and operated by the light patterns generated by the optoelectronic tweezers system. We built a single-cell separation platform and realized the automatic queuing of disordered microspheres or assigning them to each nearest microchannel in a short time. This work can potentially facilitate the study of cell heterogeneity and biologics drug discovery.","PeriodicalId":106730,"journal":{"name":"2022 WRC Symposium on Advanced Robotics and Automation (WRC SARA)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130450231","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}
Feng Zheng, Yu Tian, Weicong Zhan, Jiancheng Yu, Kaizhou Liu
{"title":"An IMM-BP based Algorithm for Tracking Maneuvering Underwater Targets by Multistatic Marine Robot Networks","authors":"Feng Zheng, Yu Tian, Weicong Zhan, Jiancheng Yu, Kaizhou Liu","doi":"10.1109/WRCSARA57040.2022.9903972","DOIUrl":"https://doi.org/10.1109/WRCSARA57040.2022.9903972","url":null,"abstract":"A mobile and distributed multistatic active sonar network formed by a collection of autonomous marine robots is a significant type of tool for underwater surveillance applications such as antisubmarine warfare. Developing a tracker that fuses the sonar data collected by the robots to accurately estimate the locations and velocities of many underwater maneuvering targets is a crucial issue for realizing such a robotic surveillance network. This paper investigates this issue and an IMM-BP tracking strategy. The strategy adopts the interacting multiple model (IMM) method to cope with the problem of accurate tracking of highly maneuvering targets and employs a belief propagation (BP)-based tracking method to implement the Bayesian multisensor-multitarget tracking. And a new algorithm implementing the integration of the IMM method with the BP-based tracker is developed and presented in this paper. The main features of the algorithm include the extraction of measurement-target association information and its utilization in the model probability update step, and using a track score-based strategy and predicted measurements in the track management step to improve the performance of track confirmation and maintenance. The performance of the developed algorithm is validated with numerical simulations. The results show that the developed algorithm could accurately estimate the number and states of multiple maneuvering targets in environments with clutter and conditions of missed measurements.","PeriodicalId":106730,"journal":{"name":"2022 WRC Symposium on Advanced Robotics and Automation (WRC SARA)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131050675","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}
Songbo Deng, Jiaqi Duan, Zelin Yang, Jiankang Zhi, H. Cai, Tao Yang, Yanbo Wang
{"title":"Design and Analysis of End-Effector for Multi-Target Spatial Operation","authors":"Songbo Deng, Jiaqi Duan, Zelin Yang, Jiankang Zhi, H. Cai, Tao Yang, Yanbo Wang","doi":"10.1109/WRCSARA57040.2022.9903986","DOIUrl":"https://doi.org/10.1109/WRCSARA57040.2022.9903986","url":null,"abstract":"With the development of space robot technology, it has become the main technical means to complete space payload replacement and operation with space manipulator. The end-effector is transferred to the desired position and attitude by space manipulator firstly, then end-effector conducts the final positioning and locking of the operating target. As the main part of space payload operations, the end effector requires large capture domain, high capture accuracy and high locking stiffness, which needs further research. A set of progressive closing capturing and positioning end-effector with synchronous action is designed in this paper according to the operation requirements of large range maneuvering with replaceable payload and high precision capturing and positioning. It has the characteristics of large position difference, small volume quality and universal capture interface. The transmission mechanism and capture finger configuration of end-effector are designed. A compliant control space manipulator with an end-effector is used to carry out replaceable payload capture test. The capture locking accuracy is measured in the air-bearing micro gravity environment. Based on the precision calibration results, the single-double finger configuration is optimized. Finally, the effectiveness of the design and control method of the end-effector are verified on ground test.","PeriodicalId":106730,"journal":{"name":"2022 WRC Symposium on Advanced Robotics and Automation (WRC SARA)","volume":"62 21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132775610","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}