UAV-VLA: Vision-Language-Action System for Large Scale Aerial Mission Generation

Oleg Sautenkov, Yasheerah Yaqoot, Artem Lykov, Muhammad Ahsan Mustafa, Grik Tadevosyan +5 more
1/9/2025
cs.ROcs.AIcs.CV

No official code found. Best implementation: Sautenich/UAV-VLA (150 stars, MIT, last commit 2026-02-26).

Abstract

The UAV-VLA (Visual-Language-Action) system is a tool designed to facilitate communication with aerial robots. By integrating satellite imagery processing with the Visual Language Model (VLM) and the powerful capabilities of GPT, UAV-VLA enables users to generate general flight paths-and-action plans through simple text requests. This system leverages the rich contextual information provided by satellite images, allowing for enhanced decision-making and mission planning. The combination of visual analysis by VLM and natural language processing by GPT can provide the user with the path-and-action set, making aerial operations more efficient and accessible. The newly developed method showed the difference in the length of the created trajectory in 22% and the mean error in finding the objects of interest on a map in 34.22 m by Euclidean distance in the K-Nearest Neighbors (KNN) approach.

View on arXivView PDF

Code Implementations(1)

Sautenich/UAV-VLACommunity100%
MIT

Official repo to UAV-VLA HRI 2025 paper

15010PythonJan 14, 20257 months agoMIT

Similar Papers

DroneVLA: VLA based Aerial Manipulation

84% match2026

See, Point, Fly: A Learning-Free VLM Framework for Universal Unmanned Aerial Navigation

83% match3 repos1472025

VLN-Pilot: Large Vision-Language Model as an Autonomous Indoor Drone Operator

81% match2026

Efficient Few-Shot Learning in Remote Sensing: Fusing Vision and Vision-Language Models

80% match2025

AirNav: A Large-Scale Real-World UAV Vision-and-Language Navigation Dataset with Natural and Diverse Instructions

80% match2026

Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology

80% match2024

Cite this paper

@article{sautenkov2025uavvla,
  title  = {UAV-VLA: Vision-Language-Action System for Large Scale Aerial Mission Generation},
  author = {Oleg Sautenkov and Yasheerah Yaqoot and Artem Lykov and Muhammad Ahsan Mustafa and Grik Tadevosyan and Aibek Akhmetkazy and Miguel Altamirano Cabrera and Mikhail Martynov and Sausar Karaf and Dzmitry Tsetserukou},
  year   = {2025},
  eprint = {2501.05014},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2501.05014v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2501.05014.svg)](https://codeofpaper.com/paper/2501.05014)

Discussion