SOURCE-LINKED INTELLIGENCE

AeroLat: Channel-Aware Latent Space Semantic Communication for Decentralized UAV Swarms

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

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 ban

Read original source ↗ Open in workspace

recordType

paper

region

Global