On-Device Federated Continual Learning on RISC-V-based Ultra-Low-Power SoC for Intelligent Nano-Drone Swarms

2025-03-21

AI Summary

Edge-side federated continual learning for nano-drone swarms faces critical challenges: severe resource constraints on RISC-V ultra-low-power SoCs, limited battery lifetime, and catastrophic forgetting. To address these, we propose the first regularization-based federated continual learning algorithm tailored to this setting, integrating Elastic Weight Consolidation (EWC) constraints, a lightweight CNN architecture, embedded model compression, and multi-core RISC-V inference optimization. Our framework enables privacy-preserving distributed face recognition on a 10-core RISC-V SoC. Compared to naive fine-tuning, it improves classification accuracy by 24%, reduces per-round local training time to 178 ms, and limits global communication latency to 10.5 s—significantly enhancing energy efficiency, real-time performance, and device longevity. This work establishes a deployable paradigm for continual collaborative learning on extremely resource-constrained edge devices.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Learning & Optimization for CV
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

RISC-V-based architectures are paving the way for efficient On-Device Learning (ODL) in smart edge devices. When applied across multiple nodes, ODL enables the creation of intelligent sensor networks that preserve data privacy. However, developing ODL-capable, battery-operated embedded platforms presents significant challenges due to constrained computational resources and limited device lifetime, besides intrinsic learning issues such as catastrophic forgetting. We face these challenges by proposing a regularization-based On-Device Federated Continual Learning algorithm tailored for multiple nano-drones performing face recognition tasks. We demonstrate our approach on a RISC-V-based 10-core ultra-low-power SoC, optimizing the ODL computational requirements. We improve the classification accuracy by 24% over naive fine-tuning, requiring 178 ms per local epoch and 10.5 s per global epoch, demonstrating the effectiveness of the architecture for this task.

Problem

• Enable on-device federated continual learning
• Overcome computational and energy constraints
• Prevent catastrophic forgetting in face recognition

Innovation

• On-Device Federated Continual Learning algorithm
• RISC-V-based ultra-low-power SoC
• Optimized computational requirements for ODL