用联邦学习设计车辆横向控制的前馈控制器，保护隐私还省通信。
Federated Learning for Data-Driven Feedforward Control: A Case Study on Vehicle Lateral Dynamics
- 各车辆本地训练神经网络前馈控制器，只上传模型更新。
- 联邦学习效果接近集中式训练，轨迹跟踪误差降低18%。
- 适合分布式车辆控制场景，兼顾隐私与性能。
在许多控制系统中，结合数据驱动的前馈（FF）控制与反馈（FB）控制可提升跟踪精度。然而，设计有效的数据驱动前馈控制器通常需要大量高质量数据及专门的实验设计流程。实践中，相关数据常分散在多个系统中，不仅带来技术挑战，还引发数据传输的监管与隐私问题。为此，我们提出将联邦学习（FL）融入数据驱动前馈控制设计的框架。各客户端使用本地数据训练神经前馈控制器，并仅向全局聚合过程提供模型更新，避免原始数据交换。通过车辆轨迹跟踪任务的仿真验证，基于联邦学习的神经前馈控制器实现了与集中式神经前馈控制器相当的性能，同时显著降低通信开销并增强数据隐私。结果表明，该方法在保证控制精度的前提下，有效解决了分布式数据环境下的协作难题。
原文摘要 · Abstract (English)
In many control systems, tracking accuracy can be enhanced by combining (data-driven) feedforward (FF) control with feedback (FB) control. However, designing effective data-driven FF controllers typically requires large amounts of high-quality data and a dedicated design-of-experiment process. In practice, relevant data are often distributed across multiple systems, which not only introduces technical challenges but also raises regulatory and privacy concerns regarding data transfer. To address these challenges, we propose a framework that integrates Federated Learning (FL) into the data-driven FF control design. Each client trains a data-driven, neural FF controller using local data and provides only model updates to the global aggregation process, avoiding the exchange of raw data. We demonstrate our method through simulation for a vehicle trajectory-tracking task. Therein, a neural FF controller is learned collaboratively using FL. Our results show that the FL-based neural FF controller matches the performance of the centralized neural FF controller while reducing communication overhead and increasing data privacy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。