Federated Learning for Privacy-Preserving Feedforward Control in Multi-Agent Systems

TL;DR

This paper tackles privacy and communication challenges in data-driven feedforward control for multi-agent systems by integrating Federated Learning (FL) to train neural FF controllers without sharing raw data. It presents a full FL-based neural FF framework and demonstrates it in an autonomous driving trajectory-tracking scenario, showing results comparable to centralized FF controllers while preserving data privacy. The study provides a centralized neural FF baseline, an FL training protocol with FedAvg, and extensive experiments analyzing global rounds and local epochs, as well as comparisons to locally trained FF models. The findings indicate that FL-based neural FF control enables scalable, privacy-preserving learning with effective tracking performance, suggesting practical implications for privacy-conscious, distributed autonomous systems.

Abstract

Feedforward control (FF) is often combined with feedback control (FB) in many control systems, improving tracking performance, efficiency, and stability. However, designing effective data-driven FF controllers in multi-agent systems requires significant data collection, including transferring private or proprietary data, which raises privacy concerns and incurs high communication costs. Therefore, we propose a novel approach integrating Federated Learning (FL) into FF control to address these challenges. This approach enables privacy-preserving, communication-efficient, and decentralized continuous improvement of FF controllers across multiple agents without sharing personal or proprietary data. By leveraging FL, each agent learns a local, neural FF controller using its data and contributes only model updates to a global aggregation process, ensuring data privacy and scalability. We demonstrate the effectiveness of our method in an autonomous driving use case. Therein, vehicles equipped with a trajectory-tracking feedback controller are enhanced by FL-based neural FF control. Simulations highlight significant improvements in tracking performance compared to pure FB control, analogous to model-based FF control. We achieve comparable tracking performance without exchanging private vehicle-specific data compared to a centralized neural FF control. Our results underscore the potential of FL-based neural FF control to enable privacy-preserving learning in multi-agent control systems, paving the way for scalable and efficient autonomous systems applications.

Figures (12)

• Figure 1: FL-based neural feedforward controller.
• Figure 2: Block diagram of control concept.
• Figure 3: Error definition for the feedback controller presented in althoff2014_online_verification_automated_road_vehicles.
• Figure 4: Tracking performance of FB + FF for client IV.
• Figure 5: Tracking performance of FB + FF for client XI.