CAREER: Towards a Theory of Robust Learning & Control for Safety-Critical Autonomous Systems

职业生涯：迈向稳健学习理论

• 批准号: 2045834
• 负责人: Nikolai Matni
• 金额: $ 50万
• 依托单位: University of Pennsylvania
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-02-15 至 2026-01-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2045834&HistoricalAwards=false
• 关键词: CAREER; Towards; Theory; Robust; Learning

Future autonomous systems, such as self-driving cars and agile robots, will be tasked with performing sophisticated and complex tasks under continuously evolving and uncertain conditions, using information gleaned from complex, high-dimensional, rich perceptual sensing modalities (e.g., cameras). Due to this ubiquitous uncertainty and complexity, feedback control loops are and will continue to be pervasive in autonomous systems. Classical control theory techniques require intricate and detailed models of dynamical systems, and assume that information is provided by simple, single output sensing devices (e.g., accelerometers), assumptions that clearly fail in the scenarios envisioned for future autonomous systems. Conversely, while techniques from machine and reinforcement learning can accommodate both uncertain dynamic conditions and rich perceptual sensing modalities, they tend to either focus solely on performance and ignore safety/robustness concerns, or if they do address safety, are only applicable to a limited class of systems. Despite recent progress in principled integration of learning and control, there still exists a wide gap between the class of systems that can be certified as safe, robust, and high-performing, and real-world autonomous systems. This project aims to develop a research plan that builds the foundations of a novel theory of robust learning and robust control that simultaneously addresses the challenges of safety and performance across a wide range of safety-critical real-world autonomous systems. The research outcomes of this project will be integrated into a synergistic education plan which includes developing both graduate and undergraduate courses at the University of Pennsylvania aimed at enriching the curriculum for teaching autonomy and control systems to engineers. Publicly available education platforms and outreach programs within the University of Pennsylvania will also be leveraged to build a pipeline for STEM majors entering college, to increase representation among underrepresented minorities, to advance public communication around autonomy and control systems, and to disseminate research results.This proposal argues that a novel cross-disciplinary perspective on robust control and robust machine learning is required to unlock the true potential of learning-based control in safety-critical complex, dynamic, and uncertain scenarios. Thrusts will develop novel robust learning-based control strategies that explicitly characterize and account for the effects of uncertainty in the learning and control pipeline. The first thrust focuses on learning to control an unknown dynamical system using contemporary high-capacity models, such as deep neural networks, through a synergistic integration of robust learning and robust control techniques aimed at mitigating the deleterious effects of distribution shift on closed-loop performance. The second thrust focuses on extending the robustness and stability guarantees of control theory to systems with complex, high-dimensional sensing modalities such as cameras, by developing tools that allow for such complex perceptual sensors to be abstractly viewed as “noisy-virtual sensors” that are amenable to traditional robust control methods. Finally, the third thrust initiates a study of the fundamental limits of the robustness and sample-complexity of learning-enabled controllers, using perception-based control as a case study. Thus, through an interdisciplinary mix of tools from control theory, machine & reinforcement learning, statistical learning theory, and robust optimization, this project will develop novel broadly applicable joint robust learning and robust control tools that come with strong guarantees of performance, robustness, safety, and sample-efficiency.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.

未来的自主系统，如自动驾驶汽车和敏捷机器人，将负责在不断发展和不确定的条件下执行复杂和复杂的任务，使用从复杂的，高维的，丰富的感知感知模态（例如，照相机）。 由于这种无处不在的不确定性和复杂性，反馈控制回路在自治系统中是并将继续是普遍存在的。 经典控制理论技术需要复杂和详细的动态系统模型，并假设信息是由简单的单输出传感设备（例如，加速度计），这些假设在未来自主系统的设想中显然失败。 相反，虽然机器和强化学习的技术可以适应不确定的动态条件和丰富的感知感知方式，但它们往往只关注性能而忽略安全性/鲁棒性问题，或者如果它们确实解决了安全性问题，则仅适用于有限的一类系统。 尽管最近在学习和控制的原则性集成方面取得了进展，但在可以被认证为安全，鲁棒和高性能的系统与现实世界的自主系统之间仍然存在很大的差距。 该项目旨在制定一项研究计划，为鲁棒学习和鲁棒控制的新理论奠定基础，同时解决各种安全关键现实自治系统的安全和性能挑战。 该项目的研究成果将被整合到一个协同教育计划中，其中包括在宾夕法尼亚大学开发研究生和本科课程，旨在丰富工程师自主和控制系统教学课程。 宾夕法尼亚大学内部的公共教育平台和外展计划也将被用来为进入大学的STEM专业建立一个管道，以增加代表性不足的少数民族的代表性，促进围绕自治和控制系统的公共沟通，并传播研究成果。这项建议认为，一种新的交叉-需要从鲁棒控制和鲁棒机器学习的学科角度来释放基于学习的控制在安全关键的复杂、动态和不确定场景中的真正潜力。 Thrusts将开发新的基于学习的鲁棒控制策略，明确描述和解释学习和控制管道中不确定性的影响。 第一个重点是使用当代高容量模型（如深度神经网络）学习控制未知动态系统，通过鲁棒学习和鲁棒控制技术的协同集成，旨在减轻分布偏移对闭环性能的有害影响。 第二个重点是扩展控制理论的鲁棒性和稳定性的保证，系统具有复杂的，高维的传感模式，如相机，通过开发工具，允许这样复杂的感知传感器被抽象地视为“噪声虚拟传感器”，是服从传统的鲁棒控制方法。 最后，第三推力启动学习使能控制器的鲁棒性和样本复杂性的基本限制的研究，使用基于感知的控制作为案例研究。 因此，通过控制理论、机器强化学习、统计学习理论和鲁棒优化等跨学科的工具组合，开发出新型的、广泛适用的鲁棒学习和鲁棒控制联合工具，并在性能、鲁棒性、安全性和样本效率方面提供强有力的保证。该奖项反映了NSF的法定使命，通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Performance-Robustness Tradeoffs in Adversarially Robust Linear-Quadratic Control

• DOI: 10.1109/cdc51059.2022.9992393
• 发表时间: 2022-03
• 期刊: 2022 IEEE 61st Conference on Decision and Control (CDC)
• 作者: Bruce Lee;Thomas Zhang;Hamed Hassani;N. Matni

Single Trajectory Nonparametric Learning of Nonlinear Dynamics

• 发表时间: 2022-02
• 期刊: ArXiv
• 作者: Ingvar M. Ziemann;H. Sandberg;N. Matni

How are policy gradient methods affected by the limits of control?

政策梯度方法如何受到控制限制的影响？

• DOI: 10.1109/cdc51059.2022.9992612
• 发表时间: 2022
• 期刊: 2022 IEEE 61st Conference on Decision and Control (CDC
• 作者: Ziemann, Ingvar;Tsiamis, Anastasios;Sandberg, Henrik;Matni, Nikolai
• 通讯作者: Matni, Nikolai

Distributed Optimal Control of Graph Symmetric Systems via Graph Filters

通过图滤波器的图对称系统的分布式最优控制

• DOI: 10.1109/cdc51059.2022.9992547
• 发表时间: 2022
• 期刊: 2022 IEEE 61st Conference on Decision and Control (CDC
• 作者: Yang, Fengjun;Gama, Fernando;Sojoudi, Somayeh;Matni, Nikolai
• 通讯作者: Matni, Nikolai

The Fundamental Limitations of Learning Linear-Quadratic Regulators

学习线性二次调节器的基本局限性

• DOI: 10.1109/cdc49753.2023.10383608
• 发表时间: 2023
• 期刊: IEEE
• 作者: Lee, Bruce D.;Ziemann, Ingvar;Tsiamis, Anastasios;Sandberg, Henrik;Matni, Nikolai
• 通讯作者: Matni, Nikolai