2022 International Conference on Service Robotics (ICoSR)最新文献

Non-cooperative Spacecraft Relative Navigation Based on Monocular Camera in Space On-orbit Servicing 空间在轨服务中基于单目相机的航天器非合作相对导航

2022 International Conference on Service Robotics (ICoSR) Pub Date : 2022-06-01 DOI: 10.1109/ICoSR57188.2022.00033

Aodi Wu, Shengyang Zhang, Leizheng Shu, Chaoming Si, Xue Wan

{"title":"Non-cooperative Spacecraft Relative Navigation Based on Monocular Camera in Space On-orbit Servicing","authors":"Aodi Wu, Shengyang Zhang, Leizheng Shu, Chaoming Si, Xue Wan","doi":"10.1109/ICoSR57188.2022.00033","DOIUrl":"https://doi.org/10.1109/ICoSR57188.2022.00033","url":null,"abstract":"With the development of space technology, there is an increasing demand for spacecraft on-orbit servicing, such as on-orbit assembly. Relative navigation of spacecraft is a key technology in on-orbit servicing because it ensures the safe and accurate approach of the two spacecraft. Non-cooperative spacecraft means that there is no communication with it and therefore cannot get precise relative position and attitude from differential GNSS. The ground guidance using ground-based orbit determination technology can guide the two spacecraft to be close as 200m. However, when the relative distance is less than 200m, higher-precision relative navigation is required. Binocular cameras can provide relative position and attitude within close range, however, as the focal length of binocular cameras is usually small, they are not suitable for medium range navigation. Thus, the relative navigation in medium range, such as 200m to 10m, becomes a challenge as the distance scale is uncertain using monocular camera. To solve this problem, this paper proposes a relative position visual navigation algorithm based on deep learning technology using monocular cameras. The navigation algorithm uses YOLOv5 target detection technology to obtain the position of the spacecraft in the image, and then calculates the real relative position in space based on the pinhole camera model. The speed of the proposed algorithm can reach 10 FPS on the NVIDIA TX2 computing device, and the average relative position error is 5.16% at 200m-10m. The proposed algorithm has been successfully applied to an on-orbit visual navigation task and achieve fast and robust navigation result.","PeriodicalId":234590,"journal":{"name":"2022 International Conference on Service Robotics (ICoSR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128769358","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}

引用次数: 0

Grasp Detection for Assembly Robots Using High-fidelity Synthetic Data 基于高保真合成数据的装配机器人抓取检测

2022 International Conference on Service Robotics (ICoSR) Pub Date : 2022-06-01 DOI: 10.1109/ICoSR57188.2022.00024

Yeheng Chen, Nan Li, Jian Zhang, Wenxuan Chen, Yuehua Li, Haifeng Li

{"title":"Grasp Detection for Assembly Robots Using High-fidelity Synthetic Data","authors":"Yeheng Chen, Nan Li, Jian Zhang, Wenxuan Chen, Yuehua Li, Haifeng Li","doi":"10.1109/ICoSR57188.2022.00024","DOIUrl":"https://doi.org/10.1109/ICoSR57188.2022.00024","url":null,"abstract":"Artificial intelligence-driven collaborative robots (cobots) have attracted significant interest. Object perception is one of the important capabilities for robotic grasping in complex environments. Vision-based methods in the main perception tasks of robotic systems mostly require large pre-labeled training datasets. Building large-scale datasets that satisfy the conditions has always been a challenge in this field. In this work, we propose a robot vision system for robotic grasping tasks. The proposed system's primary design goal is to minimize the cost of human annotation during system setup. Moreover, since it is difficult to collect sufficient labeled training data, the existing methods are typically trained on real data that are highly correlated with test data. The system we presented includes a one-shot deep neural network trained with high-fidelity synthetic data based entirely on domain randomization to avoid collecting large amounts of human-annotated data and inaccurate annotation data in real world. At last, we build the vision system in the real environment and simulation with the robot operating system (ROS).","PeriodicalId":234590,"journal":{"name":"2022 International Conference on Service Robotics (ICoSR)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130141255","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}

引用次数: 0

Robot Path Planning based on Probabilistic Roadmaps and Velocity Potential Field in Complex Environment 复杂环境下基于概率路线图和速度势场的机器人路径规划

2022 International Conference on Service Robotics (ICoSR) Pub Date : 2022-06-01 DOI: 10.1109/ICoSR57188.2022.00027

Long Zhang

引用次数: 0

Modeling and Simulation Analysis of Energy Self-sustainment Behavior Decision in Robot Ecosphere 机器人生态圈能量自我维持行为决策建模与仿真分析

2022 International Conference on Service Robotics (ICoSR) Pub Date : 2022-06-01 DOI: 10.1109/ICoSR57188.2022.00012

Hu Nenghao, Li Taibo, Liu Hongwei, Xu Lei

引用次数: 0

Identification of Offshore Wind Farms Electrical Abnormal State Based on Multi-dimensional-matrix Profile 基于多维矩阵剖面的海上风电场电气异常状态识别

2022 International Conference on Service Robotics (ICoSR) Pub Date : 2022-06-01 DOI: 10.1109/ICoSR57188.2022.00013

Jie Song, Ke Peng, De-Bao Zhou, Qiushi Cui, Lixian Shi, Jian Fu, Wei Bao, Heng Guo

{"title":"Identification of Offshore Wind Farms Electrical Abnormal State Based on Multi-dimensional-matrix Profile","authors":"Jie Song, Ke Peng, De-Bao Zhou, Qiushi Cui, Lixian Shi, Jian Fu, Wei Bao, Heng Guo","doi":"10.1109/ICoSR57188.2022.00013","DOIUrl":"https://doi.org/10.1109/ICoSR57188.2022.00013","url":null,"abstract":"As the increasing installed scale of offshore wind farms, the harsh environment and the complexity of equipment lead to frequent occurrence of electric abnormal states in offshore wind farms. However, the lack of sufficient abnormal state samples in offshore wind farms makes it difficult for traditional identification methods to achieve accurate online identification of abnormal state. Therefore, this paper proposes a method for identifying the electric abnormal states of offshore wind farms based on multi-dimensional-matrix profile (MDMP) algorithm, which can realize remote monitoring and online diagnosis of the operating status of offshore wind farms. First, the ensemble empirical mode decomposition (EEMD) algorithm is used to effectively mine the fault and disturbance historical data of the offshore wind farms, and to extract the features to construct the feature sample library of abnormal states without training process. Then, real-time data of abnormal operation of offshore wind farms are obtained, and feature extraction is performed. Finally, the MDMP method is used to match the real-time abnormal sample features with the abnormal sample library to realize the abnormal state identification. In addition, considering the computational burden in reality, a heartbeat packet mechanism is introduced to detect electrical abnormal waveforms in offshore wind farms, which can effectively save computing resources. The effectiveness and scalability of the identification method are verified by Matlab/Simulink simulation and actual engineering data.","PeriodicalId":234590,"journal":{"name":"2022 International Conference on Service Robotics (ICoSR)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126593010","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}

引用次数: 0

Robot Ecosphere for Lunar Exploration and Development 月球探测与开发机器人生态圈

2022 International Conference on Service Robotics (ICoSR) Pub Date : 2022-06-01 DOI: 10.1109/ICoSR57188.2022.00041

Xu Lei, Liu Hongwei, Zhang Xiang, Hu Nenghao

{"title":"Robot Ecosphere for Lunar Exploration and Development","authors":"Xu Lei, Liu Hongwei, Zhang Xiang, Hu Nenghao","doi":"10.1109/ICoSR57188.2022.00041","DOIUrl":"https://doi.org/10.1109/ICoSR57188.2022.00041","url":null,"abstract":"Expanding human living space and making use of moon resources have been the dream and goal of mankind since ancient times. However, the current level of human technology is not enough to support the large-scale lunar landing and realize the comprehensive development and utilization of the moon. With the development and progress in recent years, the robot cluster technology has achieved a high level of autonomy and intelligence. However, under the harsh lunar environment and the complete absence of human participation, it is still difficult to achieve the long-term survival and development of robots only relying on the current level of robot cluster technology. Based on the principles of bionics and the characteristics of natural biological individuals and communities, this paper proposes the concept of robot ecosphere for lunar exploration and development, which enables lunar robot clusters to emerge swarm intelligence behaviors of life systems through simple interaction, such as self-maintenance, self-replication, self-evolution characteristics and task execution functions. The lunar robot ecosphere is designed and divided into six kinds of robots to realize the closed-loop flow of energy and matter. According to the design results, in the future, robot clusters can be first launched to the moon to establish a lunar base, laying a material foundation for human landing on the moon and long-term working and living on the moon, making it possible for human to fully exploit and utilize the moon.","PeriodicalId":234590,"journal":{"name":"2022 International Conference on Service Robotics (ICoSR)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120946931","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}

引用次数: 0

Design and Experimental Investigation of DMD Lamp to Improve Driver's Visual Perception 提高驾驶员视觉感知的DMD灯设计与实验研究

2022 International Conference on Service Robotics (ICoSR) Pub Date : 2022-06-01 DOI: 10.1109/ICoSR57188.2022.00011

Shuo Zhang, Jianwei Huang, Ping Su, Jianshe Ma

{"title":"Design and Experimental Investigation of DMD Lamp to Improve Driver's Visual Perception","authors":"Shuo Zhang, Jianwei Huang, Ping Su, Jianshe Ma","doi":"10.1109/ICoSR57188.2022.00011","DOIUrl":"https://doi.org/10.1109/ICoSR57188.2022.00011","url":null,"abstract":"The core of driving is vision. Drivers need to obtain information based on vision perception to make decisions. Previous studies on smart headlamps mostly focused on several specific issues, such as the anti-glare function and the projection function. These functions indirectly have a certain effect on the driver's visual perception, but they do not fully consider the surrounding environment, which is easy to affect the driver's perception of other elements in the scene, resulting in potential safety hazards. Besides, most of the existing research focuses on the optical design, there is no design and test at the system level. This research creatively presents the concept of visual perception optimization for the whole scene ahead, uses an ordinary vehicle monocular camera to capture the scene ahead, and uses a YOLO deep learning algorithm to identify vehicles and obtain location information. Since eliminating glare interference, for other elements of the scene, we write an algorithm based on the minimum perceptual difference theory of human eyes to get the optimized light type to improve visual perception in real time. The pixel structure DMD (Digital Micromirror Device) is used for variable depth projection to realize the real-time perception optimization of the front scene. Experimental results show that the system can improve the image quality, natural degree and human eye acceptance of the captured scene, improve the visual perception of human eyes and ensure traffic safety.","PeriodicalId":234590,"journal":{"name":"2022 International Conference on Service Robotics (ICoSR)","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128023033","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}

引用次数: 0

A Modified Protocol to Evaluate Masseter Morphology Based on Automatic Segmentation and Registration 基于自动分割配准的咬咬器形态学评估改进方案

2022 International Conference on Service Robotics (ICoSR) Pub Date : 2022-06-01 DOI: 10.1109/ICoSR57188.2022.00025

Ling Wu, Jing Wang, Xiao-jing Liu

{"title":"A Modified Protocol to Evaluate Masseter Morphology Based on Automatic Segmentation and Registration","authors":"Ling Wu, Jing Wang, Xiao-jing Liu","doi":"10.1109/ICoSR57188.2022.00025","DOIUrl":"https://doi.org/10.1109/ICoSR57188.2022.00025","url":null,"abstract":"The purpose of the current study was to develop a modified protocol of evaluating the masseter morphology based on graph-cut automatic segmentation. The protocol was applied in the study on pre and postoperative masseter variation in patients receiving mandibular angle reduction. Computed tomography (CT) was used for the image data analysis. The masseter boundary was automatically segmentate on slices. The bony structure of mandible was segmented by the threshold restrain and three-dimensional (3D) reconstructed using the matching cubes algorithm. The pre- and postoperative images of the bony and masseter structures are overlapped in on coordinate system via the ICP registration. The masseter variation was reflected by the measures of the total volume and the 3D surface meshes through comparison of pre- vs. post-operative data. The average volume of the masseter was 32270.5±9354.1 mm3 prior to the surgery, and decreased to 26376.89±7571.4 mm3 and 26650.7±7179.3 mm3 at 6 and 24 months after surgery, respectively. The variation on the cross section at 6 months after the surgery was 6.4±1.5 mm on the angular plane, 2.2±0.9 mm on the occlusion plan and 0.1±0.1 mm on the zygomatic plane. At 24 months after the surgery, the variation was 6.0±1.1 mm on the angular plane, 0.9±0.5mm on the occlusion plane and 0 mm on the zygomatic plane. The 3D color map of the meshes showed that the variation occurred mainly at angular and lower ramous area. The modified protocol was feasible for the evaluation of the masseter morphological variation. 3D comparison between the masseter meshes with representative color map is a convenient and time-saving method to evaluate the morphological variation after mandibular angle reduction.","PeriodicalId":234590,"journal":{"name":"2022 International Conference on Service Robotics (ICoSR)","volume":"313 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115625715","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}

引用次数: 0

LNOA: A Real-time Obstacle Avoidance Motion Planning Method for Redundant Manipulator Based on Reinforcement Learning 基于强化学习的冗余机械臂实时避障运动规划方法

2022 International Conference on Service Robotics (ICoSR) Pub Date : 2022-06-01 DOI: 10.1109/ICoSR57188.2022.00019

Zeyuan Huang, Gang Chen, Yue Shen, Yu Liu, Hong You, Tong Li

引用次数: 0

Human motion intention recognition method based on gasbag human-machine interactive force detection and multi-source information fusion 基于气囊人机交互力检测和多源信息融合的人体运动意图识别方法

2022 International Conference on Service Robotics (ICoSR) Pub Date : 2022-06-01 DOI: 10.1109/ICoSR57188.2022.00044

Yong Zhang, Pingang Han, Hao Liu, Jiali Chen

{"title":"Human motion intention recognition method based on gasbag human-machine interactive force detection and multi-source information fusion","authors":"Yong Zhang, Pingang Han, Hao Liu, Jiali Chen","doi":"10.1109/ICoSR57188.2022.00044","DOIUrl":"https://doi.org/10.1109/ICoSR57188.2022.00044","url":null,"abstract":"A power-assisted exoskeleton robot can provide its operator a comfortable and natural motion assistance, which requires a perfect human-machine cooperative motion control algorithm according to the operator's intentions. As a bioelectrical signal, surface electromyography (sEMG) has the advantage of real-time for motion control, but its accuracy and reliability are still low due to strong ambiguity and coupling. So interactive force signal is still the most reliable and stable method as the control signal source for human motion intention detection. In this study, a gasbag-based human-machine interaction force signal detection method is proposed, which is combined with bioelectrical signals to identify human motion intentions and take full advantage of the two different control signal sources. A gasbag interactive force detection device is designed to monitor the internal pressure of the gasbag in real time with a pressure sensor, and the signal is converted to an interactive force by a pre-calibrated human- machine interaction force model. The interactive force is fused with the sEMG, the joint angular displacement, and the internal pressure of the pneumatic muscle, then the movement intention of the operator is obtained based on the logistic regression algorithm. Experimental results show that the method for human motion intention recognition has the characters of fast response, accurate recognition and stability.","PeriodicalId":234590,"journal":{"name":"2022 International Conference on Service Robotics (ICoSR)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127255980","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}

引用次数: 0