2021 7th International Conference on Automation, Robotics and Applications (ICARA)最新文献_第2页

Low Cost Point to Point Navigation System 低成本点对点导航系统

2021 7th International Conference on Automation, Robotics and Applications (ICARA) Pub Date : 2021-02-04 DOI: 10.1109/ICARA51699.2021.9376545

G. Spampinato, A. Bruna, Davide Giacalone, G. Messina

引用次数: 0

YOLOv3-Based Human Activity Recognition as Viewed from a Moving High-Altitude Aerial Camera 基于yolov3的移动高空航拍人眼活动识别

2021 7th International Conference on Automation, Robotics and Applications (ICARA) Pub Date : 2021-02-04 DOI: 10.1109/ICARA51699.2021.9376435

Wazha Mmereki, R. Jamisola, Dimane Mpoeleng, Tinao Petso

{"title":"YOLOv3-Based Human Activity Recognition as Viewed from a Moving High-Altitude Aerial Camera","authors":"Wazha Mmereki, R. Jamisola, Dimane Mpoeleng, Tinao Petso","doi":"10.1109/ICARA51699.2021.9376435","DOIUrl":"https://doi.org/10.1109/ICARA51699.2021.9376435","url":null,"abstract":"This paper presents a method to classify human activities as normal or suspicious using YOLOv3 to automatically process video footages taken from a high altitude moving aerial camera, such as the one attached to a drone. We consider four human activities namely, jogging, walking, fighting, and chasing. Objects generally appear much smaller, with less visible features, when viewed from high altitudes. The reduced visible features make automatic human activity detection from ground surveillance cameras not applicable to the high altitude case. Through transfer learning, we modified existing pre-trained YOLOv3 convolutional neural networks (CNN‘s) and retrained with our own high aerial human action dataset. By so doing, we were able to customize YOLOv3 to detect, localize, and recognize aerial human activities in real-time as normal or suspicious. The proposed approach achieves a promising average precision accuracy of 82.30%, and average F1 score of 88.10% on classifying high aerial human activities. We demonstrated that YOLOv3 is a powerful approach and relatively fast for the recognition and localization of human subjects as seen from above.","PeriodicalId":183788,"journal":{"name":"2021 7th International Conference on Automation, Robotics and Applications (ICARA)","volume":"191 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122163599","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

A Novel Haptic Based Guidance Scheme for Swarm of Magnetic Nanoparticles Steering 一种基于触觉的磁性纳米粒子群转向制导方法

2021 7th International Conference on Automation, Robotics and Applications (ICARA) Pub Date : 2021-02-04 DOI: 10.1109/ICARA51699.2021.9376563

Chayabhan Limpabandhu, A. K. Hoshiar

{"title":"A Novel Haptic Based Guidance Scheme for Swarm of Magnetic Nanoparticles Steering","authors":"Chayabhan Limpabandhu, A. K. Hoshiar","doi":"10.1109/ICARA51699.2021.9376563","DOIUrl":"https://doi.org/10.1109/ICARA51699.2021.9376563","url":null,"abstract":"A wide variety of haptic based teleoperation systems has been introduced for medical applications. Using force feedback in a haptic device is quite helpful for small and delicate medical interventions. This paper presents a haptic based virtual reality environment developed to steer magnetic nanoparticles (MNPs) with a guidance strategy for moving the MNPs to the desired outlet. As a proof of concept, a low-cost 3D printed open-source haptic device is used. The experiments show that the haptic can efficiently steer MNPs in different velocities by magnetic forces. We have studied process (magnetic field) and environmental (fluid velocity, number of particles) parameters with the VR-based haptic system to determine the most influential parameters. The fluid velocity showed to have the highest effect on steering performance. It has been shown that in the high fluid (10 mm/s velocities), only 50% of the particles are steered. We have developed a guidance scheme based on variable forbidden and safe zones to elevate the steering performance. By using the proposed guidance scheme, a 17.5% improvement in the performance has been observed. The promising results showed the potential of this approach in MNP based delivery.","PeriodicalId":183788,"journal":{"name":"2021 7th International Conference on Automation, Robotics and Applications (ICARA)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129610935","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

Who Controls Your Robot? An Evaluation of ROS Security Mechanisms 谁控制你的机器人?活性氧安全机制的评价

2021 7th International Conference on Automation, Robotics and Applications (ICARA) Pub Date : 2021-02-04 DOI: 10.1109/ICARA51699.2021.9376468

Niklas Goerke, David Timmermann, I. Baumgart

{"title":"Who Controls Your Robot? An Evaluation of ROS Security Mechanisms","authors":"Niklas Goerke, David Timmermann, I. Baumgart","doi":"10.1109/ICARA51699.2021.9376468","DOIUrl":"https://doi.org/10.1109/ICARA51699.2021.9376468","url":null,"abstract":"The Robot Operation System (ROS) is widely used in academia as well as the industry to build custom robot applications. Successful cyberattacks on robots can result in a loss of control for the legitimate operator and thus have a severe impact on safety if the robot is moving uncontrollably. A high level of security thus needs to be mandatory. Neither ROS 1 nor 2 in their default configuration provide protection against network based attackers. Multiple protection mechanisms have been proposed that can be used to overcome this. Unfortunately, it is unclear how effective and usable each of them are. We provide a structured analysis of the requirements these protection mechanisms need to fulfill by identifying realistic, network based attacker models and using those to derive relevant security requirements and other evaluation criteria. Based on these criteria, we analyze the protection mechanisms available and compare them to each other. We find that none of the existing protection mechanisms fulfill all of the security requirements. For both ROS 1 and 2, we discuss which protection mechanism are most relevant and give hints on how to decide on one. We hope that the requirements we identify simplify the development or enhancement of protection mechanisms that cover all aspects of ROS and that our comparison helps robot operators to choose an adequate protection mechanism for their use case.","PeriodicalId":183788,"journal":{"name":"2021 7th International Conference on Automation, Robotics and Applications (ICARA)","volume":"1894 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130045906","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: 9

Stability Analysis for T-S Fuzzy Semi-Markovian Switching CVNs with Mixed Delays and General Uncertain Transition Rates 具有混合延迟和一般不确定转移率的T-S模糊半马尔可夫切换CVNs的稳定性分析

2021 7th International Conference on Automation, Robotics and Applications (ICARA) Pub Date : 2021-02-04 DOI: 10.1109/ICARA51699.2021.9376561

Qiang Li, Jinling Liang

引用次数: 0

Towards Next Best View Planning for Time-Variant Scenes 面向时变场景的下一个最佳视图规划

2021 7th International Conference on Automation, Robotics and Applications (ICARA) Pub Date : 2021-02-04 DOI: 10.1109/ICARA51699.2021.9376559

Embla Morast, P. Jensfelt

引用次数: 0

Image-Based Visual Servoing of Rotationally Invariant Objects Using a U-Net Prediction 基于U-Net预测的旋转不变目标图像视觉伺服

2021 7th International Conference on Automation, Robotics and Applications (ICARA) Pub Date : 2021-02-04 DOI: 10.1109/ICARA51699.2021.9376577

Norbert Mitschke, M. Heizmann

引用次数: 0

Deep Learning Localization with 2D Range Scanner 2D距离扫描仪的深度学习定位

2021 7th International Conference on Automation, Robotics and Applications (ICARA) Pub Date : 2021-02-04 DOI: 10.1109/ICARA51699.2021.9376424

G. Spampinato, A. Bruna, I. Guarneri, Davide Giacalone

引用次数: 6

Improving Deep Multi-modal 3D Object Detection for Autonomous Driving 面向自动驾驶的深度多模态三维目标检测改进

2021 7th International Conference on Automation, Robotics and Applications (ICARA) Pub Date : 2021-02-04 DOI: 10.1109/ICARA51699.2021.9376453

Razieh Khamsehashari, K. Schill

{"title":"Improving Deep Multi-modal 3D Object Detection for Autonomous Driving","authors":"Razieh Khamsehashari, K. Schill","doi":"10.1109/ICARA51699.2021.9376453","DOIUrl":"https://doi.org/10.1109/ICARA51699.2021.9376453","url":null,"abstract":"Object detection in real-world applications such as autonomous driving scenarios is a challenging issue since objects often occlude each other. 3D object detection has achieved high accuracy and efficiency, but detecting small object instances and occluded objects are the most challenging issues to deploy detectors in crowded scenes. Our main focus in this paper is deep multi-modal based object detector in an automated driving system with early fusion on 3D object detection utilizing both Light Detection and Ranging (LiDAR) and image data. We aim at obtaining highly accurate 3D localization and recognition of objects in the road scene and try to improve the performance. In this regard, our basic architecture follows an established two-stage architecture, Aggregate View Object Detection-Feature Pyramid Network (AVOD-FPN), one of the best among sensor fusion-based methods. AVOD-FPN has yielded promising results especially for detecting small instances. Moreover, another main challenging issue in autonomous driving is detecting the occluded objects. So we try to address this difficulty by integrating attention network into the multi-modal 3D object detector. Experiments are shown to produce state-of-the-art results on the KITTI 3D sensor fusion-based object detection benchmark.","PeriodicalId":183788,"journal":{"name":"2021 7th International Conference on Automation, Robotics and Applications (ICARA)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131839161","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

Towards Pick and Place Multi Robot Coordination Using Multi-agent Deep Reinforcement Learning 基于多智能体深度强化学习的多机器人拾放协调研究

2021 7th International Conference on Automation, Robotics and Applications (ICARA) Pub Date : 2021-02-04 DOI: 10.1109/ICARA51699.2021.9376433

Xi Lan, Yuansong Qiao, Brian Lee

{"title":"Towards Pick and Place Multi Robot Coordination Using Multi-agent Deep Reinforcement Learning","authors":"Xi Lan, Yuansong Qiao, Brian Lee","doi":"10.1109/ICARA51699.2021.9376433","DOIUrl":"https://doi.org/10.1109/ICARA51699.2021.9376433","url":null,"abstract":"Recent advances in deep reinforcement learning are enabling the creation and use of powerful multi-agent systems in complex areas such as multi-robot coordination. These show great promise to help solve many of the difficult challenges of rapidly growing domains such as smart manufacturing. In this position paper we describe our early-stage work on the use of multi-agent deep reinforcement learning to optimise coordination in a multi-robot pick and place system. Our goal is to evaluate the feasibility of this new approach in a manufacturing environment. We propose to adopt a decentralised partially observable Markov Decision Process approach and to extend an existing cooperative game work to suitably formulate the problem as a multiagent system. We describe the centralised training/decentralised execution multi-agent learning approach which allows a group of agents to be trained simultaneously but to exercise decentralised control based on their local observations. We identify potential learning algorithms and architectures that we will investigate as a base for our implementation and we outline our open research questions. Finally we identify next steps in our research program.","PeriodicalId":183788,"journal":{"name":"2021 7th International Conference on Automation, Robotics and Applications (ICARA)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132235996","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: 6