2018 WRC Symposium on Advanced Robotics and Automation (WRC SARA)最新文献

Pose Estimation of Flying Object Based on Monocular Camera and Feature Detection 基于单目相机和特征检测的飞行物姿态估计

2018 WRC Symposium on Advanced Robotics and Automation (WRC SARA) Pub Date : 2018-08-01 DOI: 10.1109/WRC-SARA.2018.8584207

N. Zheng, Yuekun Wang, Junjie Zhang

引用次数: 0

Object Detection for Soft Robotic Manipulation Based on RGB-D Sensors 基于RGB-D传感器的软机器人操作目标检测

2018 WRC Symposium on Advanced Robotics and Automation (WRC SARA) Pub Date : 2018-08-01 DOI: 10.1109/WRC-SARA.2018.8584237

Wu Dongyu, Hu Fuwen, T. Mikołajczyk, He Yunhua

{"title":"Object Detection for Soft Robotic Manipulation Based on RGB-D Sensors","authors":"Wu Dongyu, Hu Fuwen, T. Mikołajczyk, He Yunhua","doi":"10.1109/WRC-SARA.2018.8584237","DOIUrl":"https://doi.org/10.1109/WRC-SARA.2018.8584237","url":null,"abstract":"In this paper, a visual recognition and location method using RGB-D information fusion is proposed for object detection, which is convenient for soft robotic manipulation to grasp objects. First, the environment is scanned and reconstructed by ORB-SLAM2, and the acquired color image and point cloud data are further processed, and the object feature database, which includes color and depth information, is constructed. Secondly, the point cloud in the point cloud library and the matching point cloud are put into the same coordinate system, and the ICP algorithm is used to match the point cloud to the point cloud in the point cloud library as much as possible, and the matching error is obtained, and the region of interest is obtained according to the size of the matching error. Then, if the region of interest is not uniquely determined, the object recognition is further realized by using the inception-v3 model and the transfer learning to identify the region of interest. After obtaining the only definite region, the position of the object relative to the camera is obtained through the correspondence between the color information and the point cloud data, and the object location is achieved. In order to verify the rationality of the method, a matching validation experiment was designed and a database containing multiple objects was established. In the experimental stage, the point cloud information and color information of the object are collected again from another angle, and they are matched with the point cloud in the point cloud library to get the results and analyze them. The results show that the error of the point cloud that belongs to the same object is much less than that of the point cloud that does not belong to the same object. Then the object can be identified and the location of the object can be identified successfully by color recognition.","PeriodicalId":185881,"journal":{"name":"2018 WRC Symposium on Advanced Robotics and Automation (WRC SARA)","volume":"312 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116624272","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: 2

Design of inspection system for railway engine room based on visual detection 基于视觉检测的铁路机房检测系统设计

2018 WRC Symposium on Advanced Robotics and Automation (WRC SARA) Pub Date : 2018-08-01 DOI: 10.1109/WRC-SARA.2018.8584155

Junzheng Hao, Meng Dai, Xiaopeng Zong

引用次数: 0

Gliding Pitch Control Model of Bionic Flying Squirrel Robot 仿生鼯鼠机器人滑翔俯仰控制模型

2018 WRC Symposium on Advanced Robotics and Automation (WRC SARA) Pub Date : 2018-08-01 DOI: 10.1109/WRC-SARA.2018.8584201

W. Lingqing, Wang Wei, Li Xuepeng, Zhao Fei, Quan Hualin

引用次数: 0

Global Localization Using Object Detection in Indoor Environment Based on Semantic Map 基于语义地图的室内目标检测全局定位

2018 WRC Symposium on Advanced Robotics and Automation (WRC SARA) Pub Date : 2018-08-01 DOI: 10.1109/WRC-SARA.2018.8584204

Hongyi Dong, S. Xu, Wusheng Chou, Ran Jiao, Hao Yu

{"title":"Global Localization Using Object Detection in Indoor Environment Based on Semantic Map","authors":"Hongyi Dong, S. Xu, Wusheng Chou, Ran Jiao, Hao Yu","doi":"10.1109/WRC-SARA.2018.8584204","DOIUrl":"https://doi.org/10.1109/WRC-SARA.2018.8584204","url":null,"abstract":"Global Localization in indoor environment remains a challenging problem since the indoor environment is always sparse and similar. At the startup stage of the robot, the particle filter algorithm, a widely used localization method, may converge particles to several different positions because of the similar structures in indoor environment, resulting in localization failures. In this paper, a global localization method combining maximum likelihood estimation (MLE) and single shot detector (SSD) detection network is proposed. Firstly, we build an indoor dataset consisting of 10 classes of objects and train a SSD network, which has the best tradeoff between speed and accuracy in object detection field. Based on the well trained model, a semantic map combining 2D grid map generated by Gmapping (a variant of the SLAM algorithm) and object position calculated by SSD network is built. Finally, under the consideration of computation, MLE algorithm and space pyramid method are applied to the process of global localization with object detection. The proposed method is verified with robustness in the experiments and could be easily applied in other localization systems.","PeriodicalId":185881,"journal":{"name":"2018 WRC Symposium on Advanced Robotics and Automation (WRC SARA)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129841072","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: 1

Automatic Grasp Planning Using Depth Image for Robotic Manipulator 基于深度图像的机械臂自动抓取规划

2018 WRC Symposium on Advanced Robotics and Automation (WRC SARA) Pub Date : 2018-08-01 DOI: 10.1109/WRC-SARA.2018.8584218

Bo Zhang, G. Du, Ping Zhang, Fang Li, Xinye Chen

引用次数: 0

Cooperative Control of Robotic Swarm Based on Self-organized Method and Human Swarm Interaction* 基于自组织方法和人群交互的机器人群协同控制*

2018 WRC Symposium on Advanced Robotics and Automation (WRC SARA) Pub Date : 2018-08-01 DOI: 10.1109/WRC-SARA.2018.8584234

Linna Wang, Jing Dai, Qifeng Cheng, Qixue Guan

引用次数: 1

Semi-parametric Decentralised Adaptive Control of Discrete-time Nonlinear Multi-agent Systems* 离散时间非线性多智能体系统的半参数分散自适应控制

2018 WRC Symposium on Advanced Robotics and Automation (WRC SARA) Pub Date : 2018-08-01 DOI: 10.1109/WRC-SARA.2018.8584209

Shan Li, Hongbin Ma, Xin Wang, Zhuang Li

引用次数: 1

Human Posture Recognition Using Skeleton and Depth Information 基于骨骼和深度信息的人体姿态识别

2018 WRC Symposium on Advanced Robotics and Automation (WRC SARA) Pub Date : 2018-08-01 DOI: 10.1109/WRC-SARA.2018.8584233

Bo Cao, S. Bi, Jingxiang Zheng, Dongsheng Yang

引用次数: 6

Development of a Terrain Adaptive Tracked Vehicle and Its Derivative-Dual Mode Vehicle* 地形自适应履带车辆及其衍生双模式车辆的研制*

2018 WRC Symposium on Advanced Robotics and Automation (WRC SARA) Pub Date : 2018-08-01 DOI: 10.1109/WRC-SARA.2018.8584249

Jun Lin, A. Goldenberg

{"title":"Development of a Terrain Adaptive Tracked Vehicle and Its Derivative-Dual Mode Vehicle*","authors":"Jun Lin, A. Goldenberg","doi":"10.1109/WRC-SARA.2018.8584249","DOIUrl":"https://doi.org/10.1109/WRC-SARA.2018.8584249","url":null,"abstract":"A terrain adaptive tracked vehicle (or mobile robot) with variable configurations was developed with an enhanced maneuverability to travel over a variety of rough and unpredictable surfaces. The active terrain adaptability of the vehicle is achieved through a pair of flippers, i.e. track configuration-controlling mechanisms. The mechanism can change and control track’s configurations to adapt all terrains, provide the tracks with a continuously invariable spring force to tension tracks, and adjust the center of gravity of the vehicle to prevent it turning over from slopes or obstacles. This technology has been used in the development of an innovative Micro-rover for the space exploration and a series of EOD mobile robots. On the other hand, its derivative, the Dual Mode Vehicle (DMV) was invented and might be beneficial to switch intermittently between wheels and tracks without manual conversion. If the terrain is unknown or unstructured, or a security mission in an urban setting that involves flat terrain (street) and stairs, a wheeled vehicle may be unsuitable for some of tasks and a tracked vehicle may be too slow for most of tasks.","PeriodicalId":185881,"journal":{"name":"2018 WRC Symposium on Advanced Robotics and Automation (WRC SARA)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129410535","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: 3