Robust and transferable end-to-end navigation against disturbances and external attacks: an adversarial training approach

Zhiwei Zhang, Saasha Nair, Zhe Liu, Yanzi Miao, Xiaoping Ma
{"title":"Robust and transferable end-to-end navigation against disturbances and external attacks: an adversarial training approach","authors":"Zhiwei Zhang, Saasha Nair, Zhe Liu, Yanzi Miao, Xiaoping Ma","doi":"10.1108/ria-08-2023-0109","DOIUrl":null,"url":null,"abstract":"Purpose\nThis paper aims to facilitate the research and development of resilient navigation approaches, explore the robustness of adversarial training to different interferences and promote their practical applications in real complex environments.\n\nDesign/methodology/approach\nIn this paper, the authors first summarize the real accidents of self-driving cars and develop a set of methods to simulate challenging scenarios by introducing simulated disturbances and attacks into the input sensor data. Then a robust and transferable adversarial training approach is proposed to improve the performance and resilience of current navigation models, followed by a multi-modality fusion-based end-to-end navigation network to demonstrate real-world performance of the methods. In addition, an augmented self-driving simulator with designed evaluation metrics is built to evaluate navigation models.\n\nFindings\nSynthetical experiments in simulator demonstrate the robustness and transferability of the proposed adversarial training strategy. The simulation function flow can also be used for promoting any robust perception or navigation researches. Then a multi-modality fusion-based navigation framework is proposed as a light-weight model to evaluate the adversarial training method in real-world.\n\nOriginality/value\nThe adversarial training approach provides a transferable and robust enhancement for navigation models both in simulation and real-world.\n","PeriodicalId":501194,"journal":{"name":"Robotic Intelligence and Automation","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Robotic Intelligence and Automation","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1108/ria-08-2023-0109","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Purpose This paper aims to facilitate the research and development of resilient navigation approaches, explore the robustness of adversarial training to different interferences and promote their practical applications in real complex environments. Design/methodology/approach In this paper, the authors first summarize the real accidents of self-driving cars and develop a set of methods to simulate challenging scenarios by introducing simulated disturbances and attacks into the input sensor data. Then a robust and transferable adversarial training approach is proposed to improve the performance and resilience of current navigation models, followed by a multi-modality fusion-based end-to-end navigation network to demonstrate real-world performance of the methods. In addition, an augmented self-driving simulator with designed evaluation metrics is built to evaluate navigation models. Findings Synthetical experiments in simulator demonstrate the robustness and transferability of the proposed adversarial training strategy. The simulation function flow can also be used for promoting any robust perception or navigation researches. Then a multi-modality fusion-based navigation framework is proposed as a light-weight model to evaluate the adversarial training method in real-world. Originality/value The adversarial training approach provides a transferable and robust enhancement for navigation models both in simulation and real-world.
针对干扰和外部攻击的稳健、可转移的端到端导航:一种对抗性训练方法
本文作者首先总结了自动驾驶汽车的真实事故,并通过在输入传感器数据中引入模拟干扰和攻击,开发了一套模拟挑战性场景的方法。然后,作者提出了一种鲁棒且可转移的对抗训练方法,以提高当前导航模型的性能和复原力,随后又提出了一种基于多模态融合的端到端导航网络,以展示这些方法在真实世界中的性能。研究结果在模拟器中进行的模拟实验证明了所提出的对抗训练策略的鲁棒性和可移植性。模拟功能流也可用于促进任何鲁棒感知或导航研究。然后,提出了一个基于多模态融合的导航框架,作为在现实世界中评估对抗训练方法的轻量级模型。原创性/价值对抗训练方法在模拟和现实世界中都为导航模型提供了可移植性和鲁棒性增强。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信