cs.CVNov 17, 2026

GRID-UAV: Geometry and Ray-depth Integrated Decision-making for Unmanned Aerial Vehicles

Authors: Anas Anwarul Haq Khan, Amrin Kareem, Muhammad Umer Sheikh, Biplab Banerjee, Muhammad Haris Khan

Organizations: Mohamed bin Zayed University of Artificial Intelligence, UAE · CSRE, IIT Bombay, India

Abstract

Vision-language-action models (VLAs) encode images with 2D encoders that capture little 3D structure. A common approach is to feed the policy estimated depth, but a UAV chooses its own altitude, must judge distances tens of meters away, where monocular depth is less reliable, and must relate its forward and downward views. On long aerial routes, adding depth features directly brings no significant gain (42.5% vs. 42.6% success), so we study how 3D information should be given to the policy. Analyzing flight failures, we find that two forms of 3D grounding fail in opposite ways: explicit 3D lifting of depth collides less on the way but more often fails to finish at the target, while implicit alignment with a 3D geometry model finishes more often but collides more. We propose GRID, which combines both: (1) it lifts monocular depth into ray-corrected 3D positions in the UAV's frame for both cameras, and (2) during training only, it aligns its visual features with a frozen multi-view geometry model, at no inference cost. GRID adding explicit lifting to implicit alignment significantly increases how often the policy reaches the target (61.5%→69.5%61.5\% \rightarrow 69.5\%, p<0.001p<0.001), and adding implicit alignment to explicit lifting significantly increases how often it completes the task once there (57.7%→61.4%57.7\% \rightarrow 61.4\%, p<0.05p<0.05). On TravelUAV (3,005 test episodes), GRID achieves the best success rate on every split, with relative gains over the state of the art of 9.5% (seen), 17.1% (unseen objects) and 25.4% (unseen map).

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. SpatialFly: Implicit 3D Prior-Guided Visual Reparameterization for Continuous UAV Vision-and-Language Navigation

    Mar 22, 2026Wen Jiang, Kangyao Huang, Li Wang +9Visual Representation Learning3D Spatial Reasoning

  2. CosFly-VLA: A Spatially Aware Vision-Language-Action Model for UAV Tracking

    Jul 16, 2026Ruilong Ren, Songsheng Cheng, Yunpeng Zhou +9Aerial RoboticsVisual Object Tracking

  3. See-and-Reach: Precise Vision-Language Navigation for UAVs within the Field of View

    Jun 18, 2026Fanfu Xue, En Yu, Yantian Shen +5UAV NavigationVision-Language Navigation