2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS)最新文献

An Agile Low-cost Testbed for Multi-Drone Target Tracking 多无人机目标跟踪的敏捷低成本试验台

2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS) Pub Date : 2019-11-01 DOI: 10.1109/REDUAS47371.2019.8999718

J. Amador, J.R. Martínez de Dios, J. Paneque, A. Ollero

引用次数: 1

Development of a Novel Water Landing UAV with Deflatable Floater 一种新型可充气浮筒水上降落无人机的研制

2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS) Pub Date : 2019-11-01 DOI: 10.1109/REDUAS47371.2019.8999694

Yiyun Bai, Ju-Hyeon Hong, A. Zolotas

引用次数: 2

A Mission Planning and Task Allocation Framework For Multi-UAV Swarm Coordination 多无人机群协调任务规划与任务分配框架

2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS) Pub Date : 2019-11-01 DOI: 10.1109/REDUAS47371.2019.8999708

Johannes Autenrieb, Natalia Strawa, Hyo-Sang Shin, Ju-Hyeon Hong

{"title":"A Mission Planning and Task Allocation Framework For Multi-UAV Swarm Coordination","authors":"Johannes Autenrieb, Natalia Strawa, Hyo-Sang Shin, Ju-Hyeon Hong","doi":"10.1109/REDUAS47371.2019.8999708","DOIUrl":"https://doi.org/10.1109/REDUAS47371.2019.8999708","url":null,"abstract":"This paper presents a multi-agent mission planning and task allocation framework designed to coordinate autonomous aerial vehicles engaged in a competition scenario. The development was a part of an inter-university UAV Swarm competition that was supported by BAE Systems. The proposed centralised system was developed with the main objectives of robustness and scalability. The system consists of a general mission planning module which decomposes the overall mission into identified sub-stages to achieve the overall mission goal. In order to enable autonomous defence actions a dynamic task allocation approach is proposed. The dynamic task allocation is using received information of detected enemies and utilises the information for a further combinatorial optimisation problem. In this work, we discuss the structure of the framework and present results obtained in a high-fidelity simulation environment. Moreover, a comparative study of the performance of three different optimization algorithms for the given combinatorial problem, namely Kuhn-Munkres, Jonker-Volgenant and Gale-Shapley, implemented in the system is included. The results demonstrate that the best allocation result performances, in terms of minimal costs, are obtained with utilising, both Kuhn-Munkres or Jonker-Volgenant methods, while the Gale-Shapley algorithms have benefits in terms of time efficiency for cases in which minimal costs are not the highest priority.","PeriodicalId":351115,"journal":{"name":"2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132783642","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: 4

Formal Assurances for Autonomous Systems Without Verifying Application Software 无需验证应用软件的自治系统的正式保证

2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS) Pub Date : 2019-11-01 DOI: 10.1109/REDUAS47371.2019.8999690

J. Stamenkovich, Lakshman Maalolan, C. Patterson

{"title":"Formal Assurances for Autonomous Systems Without Verifying Application Software","authors":"J. Stamenkovich, Lakshman Maalolan, C. Patterson","doi":"10.1109/REDUAS47371.2019.8999690","DOIUrl":"https://doi.org/10.1109/REDUAS47371.2019.8999690","url":null,"abstract":"Our ability to ensure software correctness is especially challenged by autonomous systems. In particular, the use of artificial intelligence can cause unpredictable behavior when encountering situations that were not included in the training data. We describe an alternative to static analysis and conventional testing that monitors and enforces formally specified properties describing a system’s physical state. All external inputs and outputs are monitored by multiple parallel automata synthesized from guards specified as linear temporal logic (LTL) formulas capturing application-specific correctness, safety, and liveness properties. Unlike conventional runtime verification, adding guards does not impact application software performance since the monitor automata are implemented in configurable hardware. In order to remove all dependencies on software, input/output controllers and drivers may also be implemented in configurable hardware. A reporting or corrective action may be taken when a guard is triggered. This architecture is consistent with the guidance prescribed in ASTM F3269-17, Methods to Safely Bound Behavior of Unmanned Aircraft Systems Containing Complex Functions. The monitor and input/output subsystem’s minimal and isolated implementations are amenable to model checking since all components are independent finite state machines. Because this approach makes no assumptions about the root cause of deviation from specifications, it can detect and mitigate: malware threats; sensor and network attacks; software bugs; sensor, actuator and communication faults; and inadvertent or malicious operator errors. We demonstrate this approach with rules defining a virtual cage for a commercially available drone.","PeriodicalId":351115,"journal":{"name":"2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124995792","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

Target Detection, Tracking and Avoidance System for Low-cost UAVs using AI-Based Approaches 基于人工智能方法的低成本无人机目标检测、跟踪与回避系统

2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS) Pub Date : 2019-11-01 DOI: 10.1109/REDUAS47371.2019.8999683

Vinorth Varatharasan, Alice Shuang Shuang Rao, Eric Toutounji, Ju-Hyeon Hong, Hyo-Sang Shin

引用次数: 3

Vision-based system for a real-time detection and following of UAV 基于视觉的无人机实时检测与跟踪系统

2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS) Pub Date : 2019-11-01 DOI: 10.1109/REDUAS47371.2019.8999675

A. Barišić, Marko Car, S. Bogdan

引用次数: 16

Artificial Neural Network-Assisted Controller for Fast and Agile UAV Flight: Onboard Implementation and Experimental Results 无人机快速敏捷飞行的人工神经网络辅助控制器:机载实现与实验结果

2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS) Pub Date : 2019-11-01 DOI: 10.1109/REDUAS47371.2019.8999677

Siddharth Patel, Andriy Sarabakha, Dogan Kircali, Giuseppe Loianno, E. Kayacan

{"title":"Artificial Neural Network-Assisted Controller for Fast and Agile UAV Flight: Onboard Implementation and Experimental Results","authors":"Siddharth Patel, Andriy Sarabakha, Dogan Kircali, Giuseppe Loianno, E. Kayacan","doi":"10.1109/REDUAS47371.2019.8999677","DOIUrl":"https://doi.org/10.1109/REDUAS47371.2019.8999677","url":null,"abstract":"In this work, we address fast and agile manoeuvre control problem of unmanned aerial vehicles (UAVs) using an artificial neural network (ANN)-assisted conventional controller. Whereas the need for having almost perfect control accuracy for UAVs pushes the operation to boundaries of the performance envelope, safety and reliability concerns enforce researchers to be more conservative in tuning their controllers. As an alternative solution to the aforementioned trade-off, a reliable yet accurate controller is designed for the trajectory tracking of UAVs by learning system dynamics online over the trajectory. What is more, the proposed online learning mechanism helps us to deal with unmodelled dynamics and operational uncertainties. Experimental results validate the proposed approach and show the superiority of our method compared to the conventional controller for fast and agile manoeuvres, at speeds as high as 20m/s. An onboard implementation of the sliding mode control theory-based adaptation rules for the training of the proposed ANN is computationally efficient which allows us to learn system dynamics and operational variations instantly using a low-cost and low-power computer.","PeriodicalId":351115,"journal":{"name":"2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134602185","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

UAS Education at the French Civil Aviation University 法国民航大学的无人机教育

2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS) Pub Date : 2019-11-01 DOI: 10.1109/REDUAS47371.2019.8999693

J. Sharples, G. Hattenberger

引用次数: 0

End-effector force estimation method for an unmanned aerial manipulator 无人机机械臂末端力估计方法

2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS) Pub Date : 2019-11-01 DOI: 10.1109/REDUAS47371.2019.8999670

Kresimir Turkovic, Marko Car, Mark Orsag

引用次数: 4

A Review of Existing Evaluation Methods for Point Clouds Quality 现有点云质量评价方法综述

2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS) Pub Date : 2019-11-01 DOI: 10.1109/REDUAS47371.2019.8999725

H. Fretes, M. Gomez-Redondo, E. Paiva, J. Rodas, R. Gregor

引用次数: 3