Pub Date : 2019-11-01DOI: 10.1109/reduas47371.2019.8999676
{"title":"RED UAS 2019 Committees","authors":"","doi":"10.1109/reduas47371.2019.8999676","DOIUrl":"https://doi.org/10.1109/reduas47371.2019.8999676","url":null,"abstract":"","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":"122501538","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}
Pub Date : 2019-11-01DOI: 10.1109/reduas47371.2019.8999684
{"title":"RED UAS 2019 Keyword Index","authors":"","doi":"10.1109/reduas47371.2019.8999684","DOIUrl":"https://doi.org/10.1109/reduas47371.2019.8999684","url":null,"abstract":"","PeriodicalId":351115,"journal":{"name":"2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS)","volume":"37 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":"115881229","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}
Pub Date : 2019-11-01DOI: 10.1109/REDUAS47371.2019.8999687
Huaming Qian, Pengheng Ding
In order to improve the accuracy of ORB-SLAM2 poses estimation in dynamic environment, an Instance Segmentation method is proposed to remove the moving feature points distributed on the human body and improve the pose accuracy in view of the deception of motion. In this method, ORB feature points are extracted from the input image, and the image is segmented to obtain the position of the pixels in the image. Then the feature points distributed above the human are removed, and the position and attitude are estimated by using the feature points which are relatively stable after the removal. The improved method is used to test on TUM data set. The results show that the improved system can significantly reduce the absolute error and relative drift of pose estimation in dynamic environment, which proves that this method can significantly improve the accuracy of pose estimation in dynamic environment compared with the traditional ORB-SLAM2 system.
{"title":"An Improved ORB-SLAM2 in Dynamic Scene with Instance Segmentation","authors":"Huaming Qian, Pengheng Ding","doi":"10.1109/REDUAS47371.2019.8999687","DOIUrl":"https://doi.org/10.1109/REDUAS47371.2019.8999687","url":null,"abstract":"In order to improve the accuracy of ORB-SLAM2 poses estimation in dynamic environment, an Instance Segmentation method is proposed to remove the moving feature points distributed on the human body and improve the pose accuracy in view of the deception of motion. In this method, ORB feature points are extracted from the input image, and the image is segmented to obtain the position of the pixels in the image. Then the feature points distributed above the human are removed, and the position and attitude are estimated by using the feature points which are relatively stable after the removal. The improved method is used to test on TUM data set. The results show that the improved system can significantly reduce the absolute error and relative drift of pose estimation in dynamic environment, which proves that this method can significantly improve the accuracy of pose estimation in dynamic environment compared with the traditional ORB-SLAM2 system.","PeriodicalId":351115,"journal":{"name":"2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS)","volume":"70 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":"127335533","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}
Pub Date : 2019-11-01DOI: 10.1109/reduas47371.2019.8999716
{"title":"RED UAS 2019 Content List","authors":"","doi":"10.1109/reduas47371.2019.8999716","DOIUrl":"https://doi.org/10.1109/reduas47371.2019.8999716","url":null,"abstract":"","PeriodicalId":351115,"journal":{"name":"2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS)","volume":"6 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":"122113189","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}
Pub Date : 2019-11-01DOI: 10.1109/REDUAS47371.2019.8999709
A. Matus-Vargas, G. Rodríguez-Gómez, J. Martínez-Carranza
Small multirotors are suitable to navigate in complex and confined environments that are otherwise inaccessible to larger drones. In such conditions, airflow interactions between the rotors and nearby surface take place. The most common of these interactions is the ground effect. Besides the increment in thrust efficiency, the ground effect affects the onboard sensors of the vehicle. In this paper, we present a fault diagnosis scheme and a control strategy for a multirotor with sensor faults caused by the ground effect. We assume a hierarchical control structure composed of an external PD controller and an internal PI controller. We consider that sensor faults occur on the inner loop and counteract them in the outer one. The fault diagnosis scheme is designed as a logical process which depends on the weighted residual. The control strategy combines the external controller and a function of the residual. Finally, we evaluate the effectiveness of our controller in simulation.
{"title":"Sensor Fault Mitigation for MAVs under Ground Effect*","authors":"A. Matus-Vargas, G. Rodríguez-Gómez, J. Martínez-Carranza","doi":"10.1109/REDUAS47371.2019.8999709","DOIUrl":"https://doi.org/10.1109/REDUAS47371.2019.8999709","url":null,"abstract":"Small multirotors are suitable to navigate in complex and confined environments that are otherwise inaccessible to larger drones. In such conditions, airflow interactions between the rotors and nearby surface take place. The most common of these interactions is the ground effect. Besides the increment in thrust efficiency, the ground effect affects the onboard sensors of the vehicle. In this paper, we present a fault diagnosis scheme and a control strategy for a multirotor with sensor faults caused by the ground effect. We assume a hierarchical control structure composed of an external PD controller and an internal PI controller. We consider that sensor faults occur on the inner loop and counteract them in the outer one. The fault diagnosis scheme is designed as a logical process which depends on the weighted residual. The control strategy combines the external controller and a function of the residual. Finally, we evaluate the effectiveness of our controller in simulation.","PeriodicalId":351115,"journal":{"name":"2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS)","volume":"41 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":"123093065","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}
Pub Date : 2019-11-01DOI: 10.1109/REDUAS47371.2019.8999706
Shaoming He, Hyo-Sang Shin, W. Ra, A. Tsourdos
This paper proposes a new optimal guidance law to enhance target observability for passive guidance with bearing-only measurement. A performance index that considers terminal miss distance, control effort and target observability criterion in an integrated manner is proposed first. The proposed guidance law is then derived analytically by solving the optimization problem formulated. Under certain conditions, it is proved that the guidance law developed gradually switches from retro proportional navigation guidance to classical proportional navigation guidance as time goes. The closed-form solutions of zero-effort-miss and guidance command are also derived to provide better insights of the proposed guidance law. Nonlinear numerical simulations are conducted to support the analytical findings.
{"title":"Observability-Enhancement Optimal Guidance Law","authors":"Shaoming He, Hyo-Sang Shin, W. Ra, A. Tsourdos","doi":"10.1109/REDUAS47371.2019.8999706","DOIUrl":"https://doi.org/10.1109/REDUAS47371.2019.8999706","url":null,"abstract":"This paper proposes a new optimal guidance law to enhance target observability for passive guidance with bearing-only measurement. A performance index that considers terminal miss distance, control effort and target observability criterion in an integrated manner is proposed first. The proposed guidance law is then derived analytically by solving the optimization problem formulated. Under certain conditions, it is proved that the guidance law developed gradually switches from retro proportional navigation guidance to classical proportional navigation guidance as time goes. The closed-form solutions of zero-effort-miss and guidance command are also derived to provide better insights of the proposed guidance law. Nonlinear numerical simulations are conducted to support the analytical findings.","PeriodicalId":351115,"journal":{"name":"2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS)","volume":"41 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":"128283482","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}
Pub Date : 2019-11-01DOI: 10.1109/REDUAS47371.2019.8999700
Johannes Autenrieb, Hyo-Sang Shin, M. Bacic
This paper presents an adaptive control strategy for a tilt-wing vertical take-off and landing (VTOL) aircraft system. To solve the highly nonlinear control problem, a time-scale separated nonlinear dynamic inversion (NDI) control scheme is proposed to regulate a VTOL aircraft system. In order to handle the existing model uncertainties, an adaptive neural network (ANN) is additionally introduced to the flight control strategy. Due to the fact that the tilt-wing aircraft is able to operate in a conventional take-off and landing (CTOL) mode as well as in a multi-copter VTOL mode, two distinct flight control systems for each mode have been implemented. In order to ensure a safe transition between both modes, a tilt angle-depending linear control mixing approach is applied. The performance of the suggested control approach is investigated by utilising a high fidelity nonlinear flight dynamics model of the tilt-wing system. The results presented demonstrate that the proposed approach provides significant benefits for the robust control of the tilt-wing system.
{"title":"Development of a Neural Network-based Adaptive Nonlinear Dynamic Inversion Controller for a Tilt-wing VTOL Aircraft","authors":"Johannes Autenrieb, Hyo-Sang Shin, M. Bacic","doi":"10.1109/REDUAS47371.2019.8999700","DOIUrl":"https://doi.org/10.1109/REDUAS47371.2019.8999700","url":null,"abstract":"This paper presents an adaptive control strategy for a tilt-wing vertical take-off and landing (VTOL) aircraft system. To solve the highly nonlinear control problem, a time-scale separated nonlinear dynamic inversion (NDI) control scheme is proposed to regulate a VTOL aircraft system. In order to handle the existing model uncertainties, an adaptive neural network (ANN) is additionally introduced to the flight control strategy. Due to the fact that the tilt-wing aircraft is able to operate in a conventional take-off and landing (CTOL) mode as well as in a multi-copter VTOL mode, two distinct flight control systems for each mode have been implemented. In order to ensure a safe transition between both modes, a tilt angle-depending linear control mixing approach is applied. The performance of the suggested control approach is investigated by utilising a high fidelity nonlinear flight dynamics model of the tilt-wing system. The results presented demonstrate that the proposed approach provides significant benefits for the robust control of the tilt-wing system.","PeriodicalId":351115,"journal":{"name":"2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS)","volume":"39 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":"126773125","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}
Pub Date : 2019-11-01DOI: 10.1109/REDUAS47371.2019.8999713
A. Cabrera-Ponce, J. Martínez-Carranza
The Global Position System (GPS) has become an essential sensor for drones. Autonomous flight in outdoor areas is possible thanks to the use of GPS that enables the drone to obtain its position in latitude and longitude coordinates. However, GPS may become unreliable when the drone flies in environments where the signal may get occluded. Malicious attacks may also compromise the GPS signal, aiming at blocking the signal or replacing it with spurious data. Motivated by these scenarios, we present preliminary results of a methodology aimed at estimating the GPS position of a drone using Convolutional Neural Networks (CNN) and a learning-based strategy. For the latter, we have adopted the PoseNet CNN architecture, originally proposed to address the relocalisation or kidnapping camera problem for facing forward cameras. First we trained PoseNet with a set of aerial images captured with an on-board camera, providing X, Y and Z coordinates as labels, which are obtained from converting GPS coordinates into metres for X and Y, and using the altimeter for Z. Then we perform validation flights where the vehicle follows a different trajectory to that used for collecting the training datasets. Even when the terrain includes bushes and repetitive texture, the CNN returns predictions with an error around the 2.5 metres and a processing speed of 15 milliseconds on average. We argue that a system such as this could be used as an emergency option to return the drone to home in the event of GPS failure. To our knowledge, this is the first time PoseNet is tested to address the problem of geo-localisation of aerial images.
{"title":"Aerial Geo-Localisation for MAVs using PoseNet","authors":"A. Cabrera-Ponce, J. Martínez-Carranza","doi":"10.1109/REDUAS47371.2019.8999713","DOIUrl":"https://doi.org/10.1109/REDUAS47371.2019.8999713","url":null,"abstract":"The Global Position System (GPS) has become an essential sensor for drones. Autonomous flight in outdoor areas is possible thanks to the use of GPS that enables the drone to obtain its position in latitude and longitude coordinates. However, GPS may become unreliable when the drone flies in environments where the signal may get occluded. Malicious attacks may also compromise the GPS signal, aiming at blocking the signal or replacing it with spurious data. Motivated by these scenarios, we present preliminary results of a methodology aimed at estimating the GPS position of a drone using Convolutional Neural Networks (CNN) and a learning-based strategy. For the latter, we have adopted the PoseNet CNN architecture, originally proposed to address the relocalisation or kidnapping camera problem for facing forward cameras. First we trained PoseNet with a set of aerial images captured with an on-board camera, providing X, Y and Z coordinates as labels, which are obtained from converting GPS coordinates into metres for X and Y, and using the altimeter for Z. Then we perform validation flights where the vehicle follows a different trajectory to that used for collecting the training datasets. Even when the terrain includes bushes and repetitive texture, the CNN returns predictions with an error around the 2.5 metres and a processing speed of 15 milliseconds on average. We argue that a system such as this could be used as an emergency option to return the drone to home in the event of GPS failure. To our knowledge, this is the first time PoseNet is tested to address the problem of geo-localisation of aerial images.","PeriodicalId":351115,"journal":{"name":"2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS)","volume":"47 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":"126941184","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}
Pub Date : 2019-11-01DOI: 10.1109/REDUAS47371.2019.8999696
A. Kapitonov, Ivan Berman, Vadim Manaenko, Vyacheslav Rzhevskiy, Vitaly Bulatov, A. Zenkin
The article describes the concept of a decentralized architecture of a traffic management system for mobile vehicles and is a continuation of the results presented in the previous article “Blockchain-based protocol of autonomous business activity for multi-agent systems consisting of UAVs.. Robonomic protocol is the basis for the system architecture — a combination of the decentralized Ethereum computer, the IPFS distributed file system, Robot Operating System and market mechanisms. In particular, its focused on the principle of communication between nodes of the traffic management system and the stages of the unmanned mission. As a proof of concept, two experiments on the integration of the proposed architecture are presented: air quality measurements using unmanned aerial systems (UAS) and water quality measurements using unmanned surface vessels (USV). Our work demonstrates that distributed ledger and smart contracts technologies are applicable to the traffic management system and increases the transparency and immutability of the data.
{"title":"Robonomics as a Blockchain-based Platform for Unmanned Traffic Management of Mobile Vehicles","authors":"A. Kapitonov, Ivan Berman, Vadim Manaenko, Vyacheslav Rzhevskiy, Vitaly Bulatov, A. Zenkin","doi":"10.1109/REDUAS47371.2019.8999696","DOIUrl":"https://doi.org/10.1109/REDUAS47371.2019.8999696","url":null,"abstract":"The article describes the concept of a decentralized architecture of a traffic management system for mobile vehicles and is a continuation of the results presented in the previous article “Blockchain-based protocol of autonomous business activity for multi-agent systems consisting of UAVs.. Robonomic protocol is the basis for the system architecture — a combination of the decentralized Ethereum computer, the IPFS distributed file system, Robot Operating System and market mechanisms. In particular, its focused on the principle of communication between nodes of the traffic management system and the stages of the unmanned mission. As a proof of concept, two experiments on the integration of the proposed architecture are presented: air quality measurements using unmanned aerial systems (UAS) and water quality measurements using unmanned surface vessels (USV). Our work demonstrates that distributed ledger and smart contracts technologies are applicable to the traffic management system and increases the transparency and immutability of the data.","PeriodicalId":351115,"journal":{"name":"2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS)","volume":"75 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":"130646316","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}
Pub Date : 2019-11-01DOI: 10.1109/reduas47371.2019.8999682
{"title":"RED UAS 2019 Book of Abstracts","authors":"","doi":"10.1109/reduas47371.2019.8999682","DOIUrl":"https://doi.org/10.1109/reduas47371.2019.8999682","url":null,"abstract":"","PeriodicalId":351115,"journal":{"name":"2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS)","volume":"238 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":"132061881","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：