Proceedings of the 6th International Conference on Robotics and Artificial Intelligence最新文献_第2页

Analysis of Duplicate Packing in FruitChain 水果链中重复包装的分析

Proceedings of the 6th International Conference on Robotics and Artificial Intelligence Pub Date : 2020-11-20 DOI: 10.1145/3449301.3449335

Guangcheng Li, Xuanhui Chen, Qinglin Zhao, Daidong Du, Hong Liang

引用次数: 2

Autonomous Decision-Making of Path Re-planning for UGV UGV路径重规划的自主决策

Proceedings of the 6th International Conference on Robotics and Artificial Intelligence Pub Date : 2020-11-20 DOI: 10.1145/3449301.3449345

Ning Li, Huachao Yu, Liang Zhou, W. Cheng, Xijun Zhao, Bo Su

引用次数: 0

Fatigue Life Estimation of 2(3HUS+S) Parallel Manipulator for Simulation of Hip Joint Motion 2(3HUS+S)并联机器人髋关节运动仿真疲劳寿命估算

Proceedings of the 6th International Conference on Robotics and Artificial Intelligence Pub Date : 2020-11-20 DOI: 10.1145/3449301.3449347

Feng Guo, G. Cheng, Zhi Qiao, Zujin Jin, Yong Li

引用次数: 0

Analysis of Different Encoder-decoder-based Approaches for Biomedical Imaging Segmentation 基于编码器-解码器的生物医学图像分割方法分析

Proceedings of the 6th International Conference on Robotics and Artificial Intelligence Pub Date : 2020-11-20 DOI: 10.1145/3449301.3449320

Rongsheng Zhang, Rongguo Zhang, Jiechao Ma, Huiling Zhang

{"title":"Analysis of Different Encoder-decoder-based Approaches for Biomedical Imaging Segmentation","authors":"Rongsheng Zhang, Rongguo Zhang, Jiechao Ma, Huiling Zhang","doi":"10.1145/3449301.3449320","DOIUrl":"https://doi.org/10.1145/3449301.3449320","url":null,"abstract":"Recently, CNNs (convolutional neural networks) have been widely used in the field of medical image segmentation. In particular, the encoder-decoder architectures represented by U-Net have achieved state-of-art segmentation effects and inspired many more elaborated networks, which adopt newer and more advanced network designs. To our knowledge, the comprehensive and detailed comparison among these improved versions from a multiplicity of points of view has not been conducted up to now. With U-Net as the baseline, we select the other four typical improvements for U-Net. For higher reliability, we finish the task of segmentation on four datasets and more experiments are performed to test the performance in various conditions. Finally, we evaluate their performance using multiple evaluation metrics. We find that attention U-Net achieves the best segmentation results in terms of F1-score but also owns the most trainable parameters and is most time-consuming. As training images decrease, the original U-Net is most robust even only less than 5 training samples are available. Besides, for any networks, adding auxiliary loss function with small weighting such as 0.01 or 0.01 whatever the cross-entropy loss and the dice-coefficient loss for the other one is beneficial as well.","PeriodicalId":429684,"journal":{"name":"Proceedings of the 6th International Conference on Robotics and Artificial Intelligence","volume":"353 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113985540","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

Link Perspective Based Network Embedding for Link Prediction 基于链路透视的链路预测网络嵌入

Proceedings of the 6th International Conference on Robotics and Artificial Intelligence Pub Date : 2020-11-20 DOI: 10.1145/3449301.3449781

Qixuan Ni, Lina Ma, Yaling Ye, Yuyao Wang, Zhan Bu

{"title":"Link Perspective Based Network Embedding for Link Prediction","authors":"Qixuan Ni, Lina Ma, Yaling Ye, Yuyao Wang, Zhan Bu","doi":"10.1145/3449301.3449781","DOIUrl":"https://doi.org/10.1145/3449301.3449781","url":null,"abstract":"Link prediction is an important task attractingmuch attention in the field of complex network, and it can be applied to many real-world scenarios such as recommendation engines, protein-protein interactions prediction, and stock index prediction. Recently, network embedding, which learns low-dimension latent representations of vertexes, has attracted considerable research efforts. It provides a new feasible solution to boost the accuracy of link prediction by preserving the rich structure information of the network. Most existing methods for network embedding depend exclusively on the perspective of nodes, but seldom focus on the perspective of links. In practice, different perspectives of network can bring us different information. As our empirical analysis shows, random walking from node perspective and link perspective of network could bring us different node sampling results, which may mean different partitions of communities. Thus, we designed a new network embedding approach for link prediction which incorporates the perspectives of both nodes and links. The aim of our method is to supplement the structure information from the perspective of links by using line graph, which improve the validity of nodes representations for link prediction. We compare our method with other popular approaches on four real-world networks and the experiment results demonstrate that our method improves performance in three link tasks.","PeriodicalId":429684,"journal":{"name":"Proceedings of the 6th International Conference on Robotics and Artificial Intelligence","volume":"23 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113957176","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

Low Illumination Image Enhancement Based on Image Fusion 基于图像融合的低照度图像增强

Proceedings of the 6th International Conference on Robotics and Artificial Intelligence Pub Date : 2020-11-20 DOI: 10.1145/3449301.3449315

Shiqiang Tang, Changli Li

引用次数: 3

Research on Real-Time Semantic SLAM Based on Object Detection Network 基于目标检测网络的实时语义SLAM研究

Proceedings of the 6th International Conference on Robotics and Artificial Intelligence Pub Date : 2020-11-20 DOI: 10.1145/3449301.3449306

Juan Fang, Zhenhu Fang

{"title":"Research on Real-Time Semantic SLAM Based on Object Detection Network","authors":"Juan Fang, Zhenhu Fang","doi":"10.1145/3449301.3449306","DOIUrl":"https://doi.org/10.1145/3449301.3449306","url":null,"abstract":"Simultaneous localization and mapping (SLAM) is an important technology in the field of robotics. Semantic SLAM can provide a more accurate localization and satisfy the needs of complex applications, which has become a research hot spot. In this paper, we propose a real-time semantic SLAM system that uses semantic information in loop closure detection and mapping. In the system, we use object detection network to get semantic information including bounding box and category. In loop closure detection, we only use semantic information to construct feature structure, and implement feature comparison. Compared with the Bag of Visual Words (BoVW), the proposed approach does not need to generate vocabulary, holds very less amount of memory. Besides, we propose a fast semantic segmentation method combining bounding box and RGB-D image to create semantic OctoMap. Finally, we evaluate our semantic SLAM. Experimental results show that compared with BoVW, the proposed loop closure detection algorithm is about 20% higher in accuracy under the same recall rate. The semantic segmentation results reveal that the mean pixel accuracy of our method on NYUv2 dataset is 0.67.And our system takes 150ms to infer an image with the size of 640480 on MX150 GPU,i7-8550U CPU, which can be used in real-time visual SLAM.","PeriodicalId":429684,"journal":{"name":"Proceedings of the 6th International Conference on Robotics and Artificial Intelligence","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133385191","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

Entropy Targets for Adaptive Distillation 自适应蒸馏的熵目标

Proceedings of the 6th International Conference on Robotics and Artificial Intelligence Pub Date : 2020-11-20 DOI: 10.1145/3449301.3449332

Hao Liu, Haowen Yan, Jinxiang Xia, Ying Ai

引用次数: 1

Study Case: Data Acquisition System to Evaluate the Water Generation of an Evaporator 研究案例:评估蒸发器产水量的数据采集系统

Proceedings of the 6th International Conference on Robotics and Artificial Intelligence Pub Date : 2020-11-20 DOI: 10.1145/3449301.3449328

Jose Luis Ordoñez Avila, Lorvis Lisandro Trejo Guerrero, Nelson Alberto Lizardo Zelaya, Eli Samael Sanchez, Darwin Valentin Luque

引用次数: 2

Low-cost Robot Assistance Design for Health Area to Help Prevent COVID-19 in Honduras 洪都拉斯卫生领域低成本机器人辅助设计，帮助预防COVID-19

Proceedings of the 6th International Conference on Robotics and Artificial Intelligence Pub Date : 2020-11-20 DOI: 10.1145/3449301.3449349

Tagrid Gabrie, A. Carrasco, Jose Luis Ordoñez Avila

{"title":"Low-cost Robot Assistance Design for Health Area to Help Prevent COVID-19 in Honduras","authors":"Tagrid Gabrie, A. Carrasco, Jose Luis Ordoñez Avila","doi":"10.1145/3449301.3449349","DOIUrl":"https://doi.org/10.1145/3449301.3449349","url":null,"abstract":"The healthcare personnel stands out for their responsibility towards the care of people who suffer illnesses or accidents. Thanks to the doctors and nurses who ensure any emergency patients receive the proper attention and healthcare critical to their well-being. Currently, there is a pandemic, COVID-19, which is a virus that quickly spreads through contact with surfaces, directly or indirectly, from a person who carries the virus. Healthcare personnel is at risk of exposure to the virus every day by serving patients when carrying out tests and monitoring them. Despite the use of personal protective equipment, healthcare personnel is at risk of acquiring the virus. There have been doctors who have been exposed to the virus, became ill, and, in some cases, lost their lives. The goal of developing an electronic system is to assist healthcare workers by using a robot that will complete basic tasks such as taking patient's temperatures. For the design of the robot, a quantitative approach, experimental design, and a \"V\" methodology were used. As a main result, the approximate robot cost is $728. It was concluded that the project is functional and effective in implementing the robot design to assist healthcare personnel and reducing the risk of exposure.","PeriodicalId":429684,"journal":{"name":"Proceedings of the 6th International Conference on Robotics and Artificial Intelligence","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124121595","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: 5