CAREER: Privacy-Aware Collaborative Sensing and Control for Cloud-Enabled Automotive Vehicles

职业：支持云的汽车的隐私感知协作传感和控制

• 批准号: 2045436
• 负责人: Zhaojian Li
• 金额: $ 53.38万
• 依托单位: Michigan State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-05-01 至 2026-04-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2045436&HistoricalAwards=false
• 关键词: CAREER; Privacy; Aware; Collaborative; Sensing

This Faculty Early Career Development Program (CAREER) grant will support research that will contribute novel methodologies related to cloud-enabled automotive vehicles, promoting both the progress of science and advancing transportation safety and efficiency. With the advent of 5G technology, cloud computing is expected to revolutionize automotive applications by providing “big data” and real-time, high-fidelity computing capabilities. Despite its promise, the use of cloud computing in automotive vehicle control and sensing still has limited success due to concerns in communication privacy and real-time constraints inherent to many automotive systems. This award supports fundamental research that addresses the major challenges in cloud-based control, collaborative sensing, decentralized optimization, and privacy preservation. The new designs and methodologies will offer a transformative framework in cloud-facilitated collaborative sensing and control that seamlessly integrate cloud and vehicle resources to enable smarter, safer, and greener next-generation automotive systems. This research is synergistic with key societal goals related to developing efficient, secure, and safe transportation systems. Therefore, results from this research will benefit the U.S. economy and life quality. This research involves several disciplines including control theory, machine learning, vehicle dynamics, and privacy preservation. The multi-disciplinary approach also facilitates the participation of underrepresented groups in research and positively impacts engineering education.The cloud-facilitated collaborative sensing and control is expected to greatly enhance vehicle control performance, and achieve improved safety, energy efficiency, and ride comfort. In pursuit of this goal, four closely integrated research objectives are planned: 1) Develop a novel privacy-preserving, learning-based collaborative sensing framework to enable the exploitation of multiple heterogeneous vehicles to iteratively improve the estimation of important road information (e.g., black ice and pothole) while preserving privacy; 2) Formalize and synthesize privacy-aware cloud-facilitated control to seamlessly integrate cloud and onboard controls for enhanced performance without leaking vehicle privacy; 3) Develop a computationally-efficient, privacy-preserving decentralized control framework by explicitly exploiting the sparse communication/constraint topologies in connected vehicles, and 4) Evaluate and validate the frameworks through extensive simulations and experiments. Collectively, advances from these research endeavors are expected to make cloud-based vehicle controls practically viable, and it will create new accuracy-friendly and computationally-efficient privacy mechanisms for time-sensitive dynamical systems.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

这项教师早期职业发展计划（职业）赠款将支持研究，该研究将贡献与支持云的汽车汽车相关的新方法，从而促进科学进步并提高运输安全性和效率。随着5G技术的发展，云计算有望通过提供“大数据”和实时，高保真计算功能来彻底改变汽车应用程序。尽管有希望，但由于对许多汽车系统的沟通隐私和实时约束的担忧，在汽车车辆控制和敏感性中使用云计算仍然有限。该奖项支持基础研究，以解决基于云的控制，协作敏感性，分散优化和隐私保护方面面临的主要挑战。新的设计和方法将在云相关的协作灵敏度和控制中提供一个变革性的框架，无缝集成云和车辆资源，以启用更智能，更安全和更绿色的下一代汽车系统。这项研究与与发展高效，安全和安全的运输系统有关的关键社会目标是协同的。因此，这项研究的结果将使美国的经济和生活质量受益。这项研究涉及多个学科，包括控制理论，机器学习，车辆动态和隐私保护。多学科的方法还促进了代表性不足的群体参与研究的参与，并对工程教育产生积极影响。预计云方的协作敏感性和控制力有望极大地提高车辆控制性能，并提高了安全性，能源效率和骑行舒适性。为了实现这一目标，计划了四个紧密整合的研究目标：1）开发一种新颖的隐私，基于学习的基于学习的协作敏感性框架，以使多种异质车辆的利用以迭代地改善重要道路信息的估计（例如，黑色冰和坑洼），同时保存隐私； 2）正式和合成隐私感知的云偏偏控制，以无缝集成的云和板载控件，以增强性能，而不会泄漏车辆隐私； 3）通过明确利用连接的车辆中的稀疏通信/约束拓扑，并通过广泛的模拟和实验来评估和验证框架，从而开发出一个计算效率，保护隐私化的分散控制框架。总的来说，这些研究努力的进步实际上将使基于云的车辆控制实际上可行，并且它将为时间敏感的动态系统创造新的准确和计算高效的隐私机制。这奖反映了NSF的法定任务，并通过使用基金会的知识优点和广泛的crietia crietia criperia criperia crigity criperia crighia crighia crigitia crighia crighia crigtia criperia criperia criperia criperia criperia criperia criperia scrip criperia scriptiation。

项目成果

Simultaneous Suspension Control and Energy Harvesting Through Novel Design and Control of a New Nonlinear Energy Harvesting Shock Absorber

• DOI: 10.1109/tvt.2022.3159734
• 发表时间: 2021-06
• 期刊: IEEE Transactions on Vehicular Technology
• 影响因子: 6.8
• 作者: Mohammad R. Hajidavalloo;Joel A. Cosner;Zhaojian Li;Wei-Che Tai;Ziyou Song

Privacy-Preserving Collaborative Estimation for Networked Vehicles With Application to Collaborative Road Profile Estimation

• DOI: 10.1109/tits.2022.3154650
• 发表时间: 2022-10
• 期刊: IEEE Transactions on Intelligent Transportation Systems
• 影响因子: 8.5
• 作者: Huan Gao;Zhaojian Li;Yongqiang Wang

Cloud-Assisted Collaborative Road Information Discovery With Gaussian Process: Application to Road Profile Estimation

• DOI: 10.1109/tits.2022.3194093
• 发表时间: 2021-10
• 期刊: IEEE Transactions on Intelligent Transportation Systems
• 影响因子: 8.5
• 作者: Mohammad R. Hajidavalloo;Zhaojian Li;Xin Xia;Ali Louati;Minghui Zheng;Weichao Zhuang

Privacy-Preserving Dynamic Average Consensus via State Decomposition: Case Study on Multi-Robot Formation Control

• DOI: 10.1016/j.automatica.2022.110182
• 发表时间: 2020-08
• 期刊: ArXiv
• 作者: Kaixiang Zhang;Zhaojian Li;Yongqiang Wang;Ali Louati;Jian Chen

Cloud-Assisted Nonlinear Model Predictive Control for Finite-Duration Tasks

• DOI: 10.1109/tac.2022.3219293
• 发表时间: 2021-06
• 期刊: IEEE Transactions on Automatic Control
• 影响因子: 6.8
• 作者: Nan Li;Kaixiang Zhang;Zhaojian Li;Vaibhav Srivastava;Xiang Yin