发表机构
Indian Institute of Technology Kharagpur（印度理工学院卡拉格普尔分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对去中心化无人机集群在带宽受限、时变链路下潜空间通信的状态坍缩问题，提出信道感知的AeroLat框架，通过证据注入和显式通信模型，将虚假相似性降低97.5%。
AI 中文摘要
在潜空间中进行通信，为在带宽受限、时变无线链路上运行的去中心化自主无人机（UAV）集群提供了一种引人注目的符号消息替代方案。然而，当同质冻结模型被提示以离散化感知输入时，其广播状态会向共享提示模板坍缩。鉴于此，我们提出AeroLat，一种使用证据注入的信道感知潜语义通信框架。所得潜状态随后通过一个显式通信模型，该模型涵盖带宽受限的序列化、加性噪声和信息陈旧性，从而便于对通信保真度和集群级协调进行联合评估。在多种子模拟中，AeroLat被证明对编解码器选择、故障和不断增大的集群规模保持鲁棒性。它持续再现潜集群异常，而无白化对照组则恢复坍缩。特别是，AeroLat能够将虚假相似性降低97.5%。
英文摘要
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%.
