AI
GeoWind2Plan: Mission-Time 3D Urban Wind Prediction for Energy-Efficient UAV Planning
Publication: cs.AI updates on arXiv.org
Author: Shaoxiang Qin, Yucheng Zhao, Fuyuan Lyu, Di Zhou, Jiachen Yao, Xue Liu, Anima Anandkumar, Liangzhu Leon Wang, Xiongye Xiao
Source published: 30/09/2026, 04:00:00 UTC
Briefing created: 30/09/2026, 04:10:56 UTC
Based on a feed excerpt; full article content has not been acquired. Source evidence retrieved 30/09/2026, 04:03:25 UTC.
Briefings
GeoWind2Plan is a framework that converts 3D building geometry into a reference wind frame to predict mission-relevant wind patches for UAVs. It achieves corridor-localized wind inference in approximately 3 seconds, significantly faster than CFD simulations which take hours to days. The system optimizes UAV paths and speeds using a physically grounded energy model, reducing energy consumption by 6.9% to 12.7% in tailwind, headwind, and crosswind missions respectively compared to wind-agnostic planning. Results were validated across held-out urban domains using mission wind-angle regimes.
Key points
- GeoWind2Plan transforms 3D building geometry into a reference wind frame to predict mission-relevant wind patches for UAVs.
- The system achieves corridor-localized wind inference in approximately 3 seconds, compared with roughly 8 hours for CFD simulations.
Context and limitations
Results were validated across held-out urban domains using mission wind-angle regimes; specific building types or urban densities not mentioned in the evidence are not covered.
Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 30/09/2026, 04:10:56 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.
View archived briefing on IPFS
bafybeid3dzvfrzvei5ue6q4pkid5amxhh57r63mrzcvtscarwk3s4tbori