UAV-Assisted Cooperative Edge Inference for Low-Altitude Economy via MoE-based Hierarchical Deep Reinforcement Learning

2026-05-18

AI Summary

This work addresses the challenge of simultaneously achieving high-precision aerial maneuvers and efficient edge-based intelligent inference for unmanned aerial vehicles (UAVs) in low-altitude economies, a task hindered by stringent operational constraints and wireless throughput bottlenecks. To tackle this, the authors propose HDRL-MoE, a hierarchical deep reinforcement learning framework that decouples slow-varying inference decisions—such as task offloading and feature compression—from fast-varying trajectory control. Leveraging a mixture-of-experts mechanism, the framework jointly optimizes discrete offloading choices and continuous compression ratios within a constrained partially observable Markov decision process (CPOMDP) formulation. Experimental results demonstrate that HDRL-MoE significantly enhances system inference performance while preserving flight task accuracy, outperforming existing baselines in terms of inference accuracy, scalability, and computational efficiency.

Abstract

The low-altitude economy (LAE) is reshaping the industrial landscape by deploying unmanned aerial vehicles (UAVs) to facilitate a wide range of applications demanding flexible aerial mobility. Integrating edge artificial intelligence (AI) into LAE platforms creates a compelling paradigm where UAVs provide real-time AI-driven analysis while simultaneously executing their primary aerial mission duties. However, realizing this paradigm remains challenging due to the strict mission constraints imposed by these primary duties and the throughput bottlenecks of wireless links. To bridge this gap, we propose a UAV-assisted cooperative edge inference framework where UAVs execute mission-critical LAE duties, quantified by trajectory deviations from reference paths, while concurrently supporting ground devices via intermediate feature offloading. Within this framework, UAV trajectories, inference task offloading decisions, and feature compression ratios are jointly optimized to maximize the system performance. We cast this joint optimization task into a constrained partially observable Markov decision process (POMDP) framework. To efficiently solve it, we propose HDRL-MoE, a novel hierarchical deep reinforcement learning framework that decouples the optimization of slow-varying inference decisions from rapidly changing UAV trajectory control. Furthermore, HDRL-MoE integrates a mixture-of-experts (MoE) architecture, where a router network orchestrates discrete offloading decisions while expert networks independently optimize the feature compression ratios. Extensive simulations show that HDRL-MoE achieves significant inference accuracy gains over baselines and exhibits high scalability and efficiency through its MoE design.

Problem

• UAV-assisted edge inference
• low-altitude economy
• feature offloading
• mission constraints
• wireless throughput bottleneck

Innovation

• Hierarchical Deep Reinforcement Learning
• Mixture-of-Experts (MoE)
• UAV-Assisted Edge Inference
• Feature Offloading
• Constrained POMDP