CPS: Medium: Collaborative Research: Data-Driven Modeling and Preview-Based Control for Cyber-Physical System Safety

CPS：中：协作研究：数据驱动的建模和基于预览的网络物理系统安全控制

• 批准号: 1932254
• 负责人: Samet Oymak
• 金额: $ 29万
• 依托单位: University of California-Riverside
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-01-01 至 2023-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1932254&HistoricalAwards=false
• 关键词: CPS; Medium; Collaborative; Research; Data

This project will develop the theory and algorithmic tools for the design of provably-safe controllers that can leverage preview information from different sources. Many autonomous or semi-autonomous cyber-physical systems (CPS) are equipped with mechanisms that provide a window of projecting into the future. These mechanisms can be forward looking sensors like cameras (and corresponding perception algorithms), map information, forecast information, or more complicated predictive models of external agents learned from data. Through these mechanisms, at run-time, the systems have a preview of what lies ahead. Leveraging this information to improve performance of CPS while keeping strong guarantees on their safety, therefore, holds great promise for multiple technologies of national interest. We will use driver-assist systems in connected vehicles as the main application. Education and outreach activities will involve undergraduate and graduate students along with stakeholders from local automotive companies.To develop the theory for learning- and prediction-enabled safety for CPS we will: (i) develop a modeling formalism, namely preview automata, for systems with preview information and correct-by-construction control algorithms that consider structured inaccuracies in the predictions for resilience; (ii) investigate how cooperation can assist in enriching the preview information; (iii) learn, via finite-sample data analysis, trustworthy dynamical models of the behaviors of non-cooperative agents with provable uncertainty bounds; and (iv) design methods for selecting compatible models from the learned dynamical models and for deriving safe controllers in the presence of cooperative and non-cooperative agents. Our innovations will enable safety-critical CPS to take full advantage of emerging technologies on sensing, perception, communication, and learning.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.

该项目将开发用于设计可证明安全控制器的理论和算法工具，该工具可以利用来自不同来源的预览信息。许多自主或半自主的网络物理系统（CP）配备了提供未来窗口的机制。这些机制可以是前瞻性传感器，例如摄像机（以及相应的感知算法），MAP信息，预测信息或从数据中学到的外部试剂的更复杂的预测模型。通过这些机制，在运行时，系统可以预览未来的问题。因此，利用此信息来提高CP的绩效，同时确保其安全性，这对多种国家利益技术具有巨大的希望。我们将在连接的车辆中使用驾驶员辅助系统作为主要应用程序。 Education and outreach activities will involve undergraduate and graduate students along with stakeholders from local automotive companies.To develop the theory for learning- and prediction-enabled safety for CPS we will: (i) develop a modeling formalism, namely preview automata, for systems with preview information and correct-by-construction control algorithms that consider structured inaccuracies in the predictions for resilience; （ii）调查合作如何帮助丰富预览信息； （iii）通过有限样本数据分析学习具有可证明不确定性界限的非合件剂的行为的值得信赖的动力学模型； （iv）设计方法，用于从学到的动力学模型中选择兼容模型，并在存在合作和非合作剂的情况下得出安全控制器。我们的创新将使安全至关重要的CP能够充分利用新兴技术在感知，感知，沟通和学习方面。该奖项反映了NSF的法定任务，并被认为是通过基金会的智力优点和更广泛影响的审查标准通过评估来通过评估来获得支持的。

项目成果

Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks

• DOI: 10.1609/aaai.v35i8.16859
• 发表时间: 2020-12
• 作者: Xiangyu Chang;Yingcong Li;Samet Oymak;Christos Thrampoulidis

Label-Imbalanced and Group-Sensitive Classification under Overparameterization

• 发表时间: 2021-03
• 作者: Ganesh Ramachandra Kini;Orestis Paraskevas;Samet Oymak;Christos Thrampoulidis

Learning a deep convolutional neural network via tensor decomposition

• DOI: 10.1093/imaiai/iaaa042
• 发表时间: 2021-02
• 期刊: Information and Inference: A Journal of the IMA
• 作者: Samet Oymak;M. Soltanolkotabi

Stochastic Contextual Bandits with Long Horizon Rewards

具有长期奖励的随机上下文强盗

• 发表时间: 2023
• 期刊: Proceedings of the AAAI Conference on Artificial Intelligence
• 作者: Qin, Yuzhen;Li, Yingcong;Pasqualetti, Fabio;Fazel, Maryam;Oymak, Samet
• 通讯作者: Oymak, Samet

Unsupervised Paraphrasing via Deep Reinforcement Learning

• DOI: 10.1145/3394486.3403231
• 发表时间: 2020-07
• 期刊: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
• 作者: A.B. Siddique;Samet Oymak;Vagelis Hristidis