融合学习与控制的信息物理系统数据驱动方法
Combining Learning and Control for Data-driven Approaches of Cyber-Physical Systems
AI总结:
针对信息物理系统模型偏差、数据动态特性及直接强化学习的安全风险,IDS实验室提出融合学习与控制的数据驱动方法,重点提升出行系统能效、减碳排放。
摘要:
信息物理系统(CPS)在大多数情况下属于系统之系统,具备信息分散式架构,典型应用包括新兴出行系统、网络化控制系统、可持续制造、智能电网、电力系统、出行市场、社交媒体平台、机器人协作以及物联网。为优化这类系统的运行,我们通常会假设一个理想模型。由于模型与实际CPS之间存在差异,这类基于模型的控制方法无法有效生成具备性能保障的最优解。另一方面,大多数CPS中存在大量具有动态特性的数据,这些数据是实时逐步添加到系统中的,而非预先全部提供。因此,传统监督学习方法利用离线获取的数据并非总能生成鲁棒的解。相比之下,将强化学习方法直接应用于实际CPS可能会对系统的安全性和鲁棒运行造成重大影响。信息与决策科学(IDS)实验室的总体目标是,通过在学习与控制的交叉领域开发数据驱动的系统方法,研究如何规避这些挑战。研究重点在于如何在新兴出行系统相关应用(例如网联自动驾驶汽车(CAVs)、共享出行、社会技术系统以及智慧城市)中提升能源效率并减少温室气体排放,从而为地球健康做出贡献。
英文摘要:
Cyber-physical systems (CPS), in most instances, represent systems of systems with an informationally decentralized structure such as emerging mobility systems, networked control systems, sustainable manufacturing, smart power grids, power systems, mobility markets, social media platforms, cooperation of robots, and internet of things. To optimize the operation of such systems, we typically assume an ideal model. Such model-based control approaches cannot effectively facilitate optimal solutions with performance guarantees due to the discrepancy between the model and the actual CPS. On the other hand, in most CPS there is a large volume of data with a dynamic nature which is added to the system gradually in real time and not altogether in advance. Thus, traditional supervised learning approaches cannot always facilitate robust solutions using data derived offline. By contrast, applying reinforcement learning approaches directly to the actual CPS might impose significant implications on the safety and robust operation of the system. The overarching goal of the Information and Decision Science (IDS) Lab is to investigate how to circumvent these challenges by developing data-driven system approaches at the intersection of learning and control. The emphasis is on how to improve energy efficiency and reduce greenhouse gas emissions in applications related to emerging mobility systems, e.g., connected and automated vehicles (CAVs), shared mobility, sociotechnical systems, and smart cities, and thus contribute to the health of the planet.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。