{"title":"确保自主四旋翼飞行器控制系统免受网络攻击","authors":"Samuel Belkadi","doi":"arxiv-2409.11897","DOIUrl":null,"url":null,"abstract":"The problem of safety for robotic systems has been extensively studied.\nHowever, little attention has been given to security issues for\nthree-dimensional systems, such as quadrotors. Malicious adversaries can\ncompromise robot sensors and communication networks, causing incidents,\nachieving illegal objectives, or even injuring people. This study first designs\nan intelligent control system for autonomous quadrotors. Then, it investigates\nthe problems of optimal false data injection attack scheduling and\ncountermeasure design for unmanned aerial vehicles. Using a state-of-the-art\ndeep learning-based approach, an optimal false data injection attack scheme is\nproposed to deteriorate a quadrotor's tracking performance with limited attack\nenergy. Subsequently, an optimal tracking control strategy is learned to\nmitigate attacks and recover the quadrotor's tracking performance. We base our\nwork on Agilicious, a state-of-the-art quadrotor recently deployed for\nautonomous settings. This paper is the first in the United Kingdom to deploy\nthis quadrotor and implement reinforcement learning on its platform. Therefore,\nto promote easy reproducibility with minimal engineering overhead, we further\nprovide (1) a comprehensive breakdown of this quadrotor, including software\nstacks and hardware alternatives; (2) a detailed reinforcement-learning\nframework to train autonomous controllers on Agilicious agents; and (3) a new\nopen-source environment that builds upon PyFlyt for future reinforcement\nlearning research on Agilicious platforms. Both simulated and real-world\nexperiments are conducted to show the effectiveness of the proposed frameworks\nin section 5.2.","PeriodicalId":501031,"journal":{"name":"arXiv - CS - Robotics","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Secure Control Systems for Autonomous Quadrotors against Cyber-Attacks\",\"authors\":\"Samuel Belkadi\",\"doi\":\"arxiv-2409.11897\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The problem of safety for robotic systems has been extensively studied.\\nHowever, little attention has been given to security issues for\\nthree-dimensional systems, such as quadrotors. Malicious adversaries can\\ncompromise robot sensors and communication networks, causing incidents,\\nachieving illegal objectives, or even injuring people. This study first designs\\nan intelligent control system for autonomous quadrotors. Then, it investigates\\nthe problems of optimal false data injection attack scheduling and\\ncountermeasure design for unmanned aerial vehicles. Using a state-of-the-art\\ndeep learning-based approach, an optimal false data injection attack scheme is\\nproposed to deteriorate a quadrotor's tracking performance with limited attack\\nenergy. Subsequently, an optimal tracking control strategy is learned to\\nmitigate attacks and recover the quadrotor's tracking performance. We base our\\nwork on Agilicious, a state-of-the-art quadrotor recently deployed for\\nautonomous settings. This paper is the first in the United Kingdom to deploy\\nthis quadrotor and implement reinforcement learning on its platform. Therefore,\\nto promote easy reproducibility with minimal engineering overhead, we further\\nprovide (1) a comprehensive breakdown of this quadrotor, including software\\nstacks and hardware alternatives; (2) a detailed reinforcement-learning\\nframework to train autonomous controllers on Agilicious agents; and (3) a new\\nopen-source environment that builds upon PyFlyt for future reinforcement\\nlearning research on Agilicious platforms. Both simulated and real-world\\nexperiments are conducted to show the effectiveness of the proposed frameworks\\nin section 5.2.\",\"PeriodicalId\":501031,\"journal\":{\"name\":\"arXiv - CS - Robotics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Robotics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.11897\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Robotics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.11897","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Secure Control Systems for Autonomous Quadrotors against Cyber-Attacks
The problem of safety for robotic systems has been extensively studied.
However, little attention has been given to security issues for
three-dimensional systems, such as quadrotors. Malicious adversaries can
compromise robot sensors and communication networks, causing incidents,
achieving illegal objectives, or even injuring people. This study first designs
an intelligent control system for autonomous quadrotors. Then, it investigates
the problems of optimal false data injection attack scheduling and
countermeasure design for unmanned aerial vehicles. Using a state-of-the-art
deep learning-based approach, an optimal false data injection attack scheme is
proposed to deteriorate a quadrotor's tracking performance with limited attack
energy. Subsequently, an optimal tracking control strategy is learned to
mitigate attacks and recover the quadrotor's tracking performance. We base our
work on Agilicious, a state-of-the-art quadrotor recently deployed for
autonomous settings. This paper is the first in the United Kingdom to deploy
this quadrotor and implement reinforcement learning on its platform. Therefore,
to promote easy reproducibility with minimal engineering overhead, we further
provide (1) a comprehensive breakdown of this quadrotor, including software
stacks and hardware alternatives; (2) a detailed reinforcement-learning
framework to train autonomous controllers on Agilicious agents; and (3) a new
open-source environment that builds upon PyFlyt for future reinforcement
learning research on Agilicious platforms. Both simulated and real-world
experiments are conducted to show the effectiveness of the proposed frameworks
in section 5.2.