A channel-aware latent semantic communication framework that uses evidence injection, AeroLat, which consistently reproduces the latent-swarm anomaly, while no-whitening controls recover the collapse.
Abstract
Communication in latent space offers an intriguing alternative to symbolic messages for decentralized autonomous Unmanned Aerial Vehicle (UAV) swarms operating over bandwidth-constrained, time-varying wireless links. However, when homogeneous frozen models are prompted with discretized perceptual inputs, their broadcast states collapse toward the shared prompt template. In view of this, we propose AeroLat, a channel-aware latent semantic communication framework that uses evidence injection. The resulting latent states are then passed through an explicit communication model that encompasses bandwidth-limited serialization, additive noise and information staleness, which facilitates a joint assessment of communication fidelity and swarm-level coordination. Across multi-seed simulations, AeroLat provably remains resilient to codec choice, faults and increasing swarm size. It consistently reproduces the latent-swarm anomaly, while no-whitening controls recover the collapse. In particular, AeroLat is capable of reducing false similarity by 97.5%.
Unmanned aerial vehicle (UAV) swarms increasingly rely on language-model agents to provide adaptive mission-level reasoning in uncertain environments. Fully distributed control, in which each UAV hosts an independent Small Language Model (SLM), removes reliance on a centralized coordinator but introduces an information...
Andrea Iannoli, Ivan D. Zyrianoff, A. Trotta et al.· 0 citations
Autonomous swarms use multiple communication, sensing, and service layers, so capability loss can displace tasks and amplify risk through load redistribution. This paper develops a task-migration framework for dependent agent and layer failures. A Clayton copula models within-epoch dependence, and a dimensionless load-...
Pan Li, Xiu-Yi Zhao, Tian-Yu Zuo et al.· IEEE Transactions on Automat...· 0 citations
The emerging low-altitude economy demands unmanned aerial vehicle (UAV)-enabled integrated sensing and communication (ISAC) for reliable connectivity and environmental awareness. In particular, embodied UAV agents offer a promising means of supporting autonomous operations through a closed loop linking perception, deci...
Jia-Heng Guo, Jun Du, Chun-Xiao Jiang et al.· 0 citations
This paper proposes AERIS, an offline policy improvement framework for multi-UAV ISAC that learns from fixed flight logs under centralized training and decentralized execution and designs STAR-CRDT, an offline multi-agent RL algorithm that performs support-aware local action rectification and distills only trusted impr...
Ziyuan Wang, Yi-Fan Sui, Wei Wei et al.· 0 citations
In recent years, UAV cluster architectures have evolved into multiplex networked structures, where UAVs are organized into tightly coupled subnets according to task demands or spatial distribution. These subnets operate under heterogeneous environmental conditions and interference patterns, resulting in highly dynamic...
Tian-Yu Zuo, Pan Li, Zheng-Yi An et al.· ACM transactions on sensor n...· 0 citations
Unmanned Aerial Vehicles (UAVs) are envisioned as key enablers for time-sensitive data collection in 6G cognitive networks. Semantic communication offers a promising solution to overcome bandwidth scarcity by transmitting only essential information. However, the heavy computational burden of semantic extraction is ofte...
Zhi-Long Kou, Xiang-Dong Jia, Jun Lan et al.· IEEE Wireless Communications...· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 13, 2026
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
With $2.1 million funding from Google.org, the open-source Public Transit Intelligence Hub will unify public transit monitoring, operations, and passenger communication.
