Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

UAV-VLPA*: A Vision-Language-Path-Action System for Optimal Route Generation on a Large Scales

Oleg Sautenkov, Aibek Akhmetkazy, Yasheerah Yaqoot, Muhammad Ahsan Mustafa, Grik Tadevosyan, Artem Lykov, Dzmitry Tsetserukou

TL;DR

UAV-VLPA* addresses autonomous UAV route planning by integrating vision-language perception with global route optimization and local obstacle avoidance using satellite imagery and natural language commands. The method combines a 2-opt Traveling Salesman Problem (TSP) route construction with A* refinement to produce globally efficient and obstacle-safe flight paths. Experimental results on the UAV-VLPA-nano-30 benchmark show substantial improvements in trajectory efficiency and planning speed, with the combined TSP+A* approach outperforming human references. The framework demonstrates scalable, environment-agnostic UAV mission generation suitable for large-scale real-world deployment and future real-time extensions.

Abstract

The UAV-VLPA* (Visual-Language-Planning-and-Action) system represents a cutting-edge advancement in aerial robotics, designed to enhance communication and operational efficiency for unmanned aerial vehicles (UAVs). By integrating advanced planning capabilities, the system addresses the Traveling Salesman Problem (TSP) to optimize flight paths, reducing the total trajectory length by 18.5\% compared to traditional methods. Additionally, the incorporation of the A* algorithm enables robust obstacle avoidance, ensuring safe and efficient navigation in complex environments. The system leverages satellite imagery processing combined with the Visual Language Model (VLM) and GPT's natural language processing capabilities, allowing users to generate detailed flight plans through simple text commands. This seamless fusion of visual and linguistic analysis empowers precise decision-making and mission planning, making UAV-VLPA* a transformative tool for modern aerial operations. With its unmatched operational efficiency, navigational safety, and user-friendly functionality, UAV-VLPA* sets a new standard in autonomous aerial robotics, paving the way for future innovations in the field.

UAV-VLPA*: A Vision-Language-Path-Action System for Optimal Route Generation on a Large Scales

TL;DR

UAV-VLPA* addresses autonomous UAV route planning by integrating vision-language perception with global route optimization and local obstacle avoidance using satellite imagery and natural language commands. The method combines a 2-opt Traveling Salesman Problem (TSP) route construction with A* refinement to produce globally efficient and obstacle-safe flight paths. Experimental results on the UAV-VLPA-nano-30 benchmark show substantial improvements in trajectory efficiency and planning speed, with the combined TSP+A* approach outperforming human references. The framework demonstrates scalable, environment-agnostic UAV mission generation suitable for large-scale real-world deployment and future real-time extensions.

Abstract

The UAV-VLPA* (Visual-Language-Planning-and-Action) system represents a cutting-edge advancement in aerial robotics, designed to enhance communication and operational efficiency for unmanned aerial vehicles (UAVs). By integrating advanced planning capabilities, the system addresses the Traveling Salesman Problem (TSP) to optimize flight paths, reducing the total trajectory length by 18.5\% compared to traditional methods. Additionally, the incorporation of the A* algorithm enables robust obstacle avoidance, ensuring safe and efficient navigation in complex environments. The system leverages satellite imagery processing combined with the Visual Language Model (VLM) and GPT's natural language processing capabilities, allowing users to generate detailed flight plans through simple text commands. This seamless fusion of visual and linguistic analysis empowers precise decision-making and mission planning, making UAV-VLPA* a transformative tool for modern aerial operations. With its unmatched operational efficiency, navigational safety, and user-friendly functionality, UAV-VLPA* sets a new standard in autonomous aerial robotics, paving the way for future innovations in the field.

Paper Structure

This paper contains 14 sections, 2 equations, 9 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. System Overview
  4. System Workflow
  5. Traveling Salesman Problem
  6. Path Planning and Obstacle Avoidance
  7. Path Planning and Obstacle Avoidance with Traveling Salesman Problem
  8. Experimental Setup
  9. Experimental Results
  10. Evaluation of TSP Integration on UAV-VLA results
  11. Evaluation of A* Path Planning
  12. Combined TSP and A* Path Planning: UAV-VLPA* System
  13. Conclusion
  14. Future Work

Figures (9)

  • Figure 1: The pipeline of the UAV-VLPA* system.
  • Figure 5: Trajectory length comparison: UAV-VLA with TSP vs. human expert.
  • Figure 6: Error distribution of UAV-VLA with TSP against ground truth.
  • Figure 7: Trajectory length comparison: UAV-VLA with A* vs. human expert.
  • Figure 8: Error distribution of UAV-VLA with A* path planning.
  • ...and 4 more figures