Multimodal Mixture-of-Experts for ISAC in Low-Altitude Wireless Networks

TL;DR

This paper introduces a mixture-of-experts framework for multimodal integrated sensing and communication in low-altitude wireless networks, enabling adaptive, efficient fusion of heterogeneous sensing modalities to enhance environmental perception and robustness.

Contribution

It proposes a novel adaptive fusion method using a mixture-of-experts model with a gating mechanism, including a sparse variant for energy-efficient deployment in aerial platforms.

Findings

Outperforms traditional fusion methods in simulation tasks

Improves learning performance and sample efficiency

Reduces computational overhead with sparse MoE

Abstract

Integrated sensing and communication (ISAC) is a key enabler for low-altitude wireless networks (LAWNs), providing simultaneous environmental perception and data transmission in complex aerial scenarios. By combining heterogeneous sensing modalities such as visual, radar, lidar, and positional information, multimodal ISAC can improve both situational awareness and robustness of LAWNs. However, most existing multimodal fusion approaches use static fusion strategies that treat all modalities equally and cannot adapt to channel heterogeneity or time-varying modality reliability in dynamic low-altitude environments. To address this fundamental limitation, we propose a mixture-of-experts (MoE) framework for multimodal ISAC in LAWNs. Each modality is processed by a dedicated expert network, and a lightweight gating module adaptively assigns fusion weights according to the instantaneous informativeness and reliability of each modality. To improve scalability under the stringent energy constraints of aerial platforms, we further develop a sparse MoE variant that selectively activates only a subset of experts, thereby reducing computation overhead while preserving the benefits of adaptive fusion. Comprehensive simulations on three typical ISAC tasks in LAWNs demonstrate that the proposed frameworks consistently outperform conventional multimodal fusion baselines in terms of learning performance and training sample efficiency.