Zero-Shot Scalable Resilience in UAV Swarms: A Decentralized Imitation Learning Framework with Physics-Informed Graph Interactions

TL;DR

This paper introduces PhyGAIL, a decentralized imitation learning framework for UAV swarms that maintains high performance in large-scale, fragmented networks by leveraging physics-informed graph neural networks and scenario-adaptive training.

Contribution

The paper proposes a novel physics-informed graph adversarial imitation learning algorithm that enables scalable, resilient UAV swarm recovery without fine-tuning for different swarm sizes.

Findings

Policy trained on 20-UAV swarms transfers to 500-UAV swarms without fine-tuning.

Achieves better reconnection reliability, recovery speed, and safety than baselines.

Maintains performance under severe fragmentation and variable conditions.

Abstract

Large-scale Unmanned Aerial Vehicle (UAV) failures can split an unmanned aerial vehicle swarm network into disconnected sub-networks, making decentralized recovery both urgent and difficult. Centralized recovery methods depend on global topology information and become communication-heavy after severe fragmentation. Decentralized heuristics and multi-agent reinforcement learning methods are easier to deploy, but their performance often degrades when the swarm scale and damage severity vary. We present Physics-informed Graph Adversarial Imitation Learning algorithm (PhyGAIL) that adopts centralized training with decentralized execution. PhyGAIL builds bounded local interaction graphs from heterogeneous observations, and uses physics-informed graph neural network to encode directional local interactions as gated message passing with explicit attraction and repulsion. This gives the policy a physically grounded coordination bias while keeping local observations scale-invariant. It also uses scenario-adaptive imitation learning to improve training under fragmented topologies and variable-length recovery episodes. Our analysis establishes bounded local graph amplification, bounded interaction dynamics, and controlled variance of the terminal success signal. A policy trained on 20-UAV swarms transfers directly to swarms of up to 500 UAVs without fine-tuning, and achieves better performance across reconnection reliability, recovery speed, motion safety, and runtime efficiency than representative baselines.