CAREER: A Universal Framework for Safety-Aware Data-Driven Control and Estimation

职业：安全意识数据驱动控制和估计的通用框架

• 批准号: 2340089
• 负责人: Luis Duffaut Espinosa
• 金额: $ 58.13万
• 依托单位: University of Vermont & State Agricultural College
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2024
• 资助国家: 美国
• 起止时间: 2024-06-01 至 2029-05-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2340089&HistoricalAwards=false
• 关键词: CAREER; Universal; Framework; Safety; Aware

This Faculty Early Career Development Program (CAREER) award supports research that enables safe data-driven control and estimation methods for robotics and power systems, thereby promoting the progress of science, advancing prosperity and welfare, and securing the national defense. This research will develop a universal framework for the simultaneous design of control policies and safety measures based on recent advances in the mathematical modeling of dynamical systems. In this context, the intersection between safety, control systems, and data-driven methodologies is still nascent and there are major hurdles to overcome for the adoption and acceptance of the safe data-driven paradigm despite the immense progress in data processing capabilities. This project will solve these challenges through the automatic synthesis of safety-aware control laws for highly complex systems as a function of their real-time input-output information. The outcomes of this work will be well-suited for a variety of applications in engineering, biology, and manufacturing that are of essential significance for the economic development and the competitiveness of the nation on the global stage. The project’s research objectives are complemented by a methodical industry outreach and pedagogical plan aimed at blending research and education, strengthening industry collaboration, and boosting the participation of underrepresented communities for the benefit of society at large.The researched framework leverages the algebraic structure of a novel framework for system representation that systematically encodes its input-output behavior, namely the Chen-Fliess framework. This encoding naturally fits the underpinnings of the data-driven paradigm for control and estimation. This methodology essentially enables the use of algebraic optimization routines on the system’s information, by eliminating the need for a state-space coordinate frame that otherwise will require over-parametrizations that can lead to infeasibility. Consequently, faster and less power-consuming optimization algorithms are researched with the capability of retaining the system’s input-output behavior. Thus, reachability analysis and synthesis of the control barrier functions will then be performed under this algebraic framework to advance these methodologies in the data-driven setting. The specific objectives of this project are to (1) provide an algebraic framework for the analysis and optimization of data-driven control systems, (2) develop input-output reachability analysis in the Chen-Fliess framework, and (3) develop data-driven methods for the synthesis of safe control laws based on reachability analysis and control barrier functions in the Chen-Fliess framework. The researched work will be validated on autonomous vehicles, a multi-robot system performing simultaneous localization and mapping, and a data-driven power system regulation problem.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）奖支持了对机器人和电力系统的安全数据驱动控制和估算方法的研究，从而促进了科学的进步，促进繁荣和福利，并确保国防。这项研究将根据动态系统的数学建模的最新进展，为控制政策和安全措施的简单设计开发一个通用框架。在这种情况下，安全，控制系统和数据驱动方法之间的交集仍然很新生，并且要克服采用和接受安全数据驱动的范式目的地的主要障碍，这是数据处理能力的巨大进展。该项目将通过自动合成高度复杂系统的安全性控制法律来解决这些挑战，这是其实时输入输出信息的函数。这项工作的结果将非常适合各种在工程，生物学和制造业中的应用，这对于在全球阶段的经济发展和国家的竞争力至关重要。 The project’s research objectives are completed by a methodical industry outreach and pedagogical plan aimed at blending research and education, strengthening industry collaboration, and boosting the participation of underrepresented communities for the benefits of society at large.The researched framework leverages the algebraic structure of a novel Framework for system representation that systematically encodes its input-output behavior, namely the Chen-Fliess framework.该编码自然符合数据驱动的范式的基础，以进行控制和估计。该方法基本上可以通过消除对状态空间坐标框架的需求，否则可以在系统的信息上使用代数优化程序，否则该框架将需要过度参数，这可能会导致不可行。因此，研究了更快，更少的功率优化算法，并具有保留系统输入输出行为的能力。然后，将在该代数框架下执行控制屏障函数的反应分析和合成，以在数据驱动的设置中推进这些方法。该项目的具体目标是（1）提供了一个代数框架，用于分析和优化数据驱动的控制系统，（2）在Chen-Fliess框架中开发输入输出反应分析，（（3）开发数据驱动的方法，用于合成基于响应响应分析和控制障碍功能的安全控制法的合成的数据驱动方法。研究的工作将在自动驾驶汽车，执行同时本地化和映射的多机器人系统以及数据驱动的电力系统调节问题上进行验证。该奖项反映了NSF的法定任务，并被认为是值得通过基金会的知识分子优点和更广泛影响的审查标准来通过评估来获得支持的。