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

2025-03-04

AI Summary

To address data privacy leakage and high communication overhead in data-driven feedforward control for multi-agent systems, this paper proposes the first federated learning (FL)-driven framework for collaborative training of distributed neural feedforward controllers. The method enables agents to jointly optimize their controllers without sharing raw private data—only lightweight model updates are exchanged and aggregated centrally. It inherently ensures privacy preservation, communication efficiency, and full decentralization. Technically, the approach integrates FL, neural-network-based feedforward control, distributed optimization, and feedback–feedforward synergy. Evaluated in autonomous driving simulations, the proposed method significantly improves trajectory tracking accuracy over pure feedback control, achieves performance comparable to centralized training, and completely eliminates transmission of vehicle-sensitive data.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Multiagent Systems: Multiagent Learning
• Search and Optimization: Learning to Search

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• Privacy concerns in data-driven feedforward control
• High communication costs in multi-agent systems
• Need for decentralized, privacy-preserving control improvement

Innovation

• Integrates Federated Learning into feedforward control
• Enables privacy-preserving decentralized controller improvement
• Uses local neural controllers with global model updates