# HKUST-Aerial-Robotics/FUEL

An Efficient Framework for Fast UAV Exploration

Repository: https://github.com/HKUST-Aerial-Robotics/FUEL
Canonical: https://ross.abutalabs.com/products/hkust-aerial-robotics-fuel
Language: C++
License: GPL-3.0
License Family: copyleft
Topics: uav, motion-planning, aerial-robotics, autonomous-robots, autonomous-navigation
Last push: 2024-11-19T06:06:55+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2145, "days_push": 652, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1461, forks 251 (observed 2026-08-28T04:04:47.419179+00:00)

## What it is
FUEL is a C++/ROS framework for fast autonomous UAV exploration, built around an incremental Frontier Information Structure and hierarchical planning that generates coverage paths, local viewpoints, and minimum-time trajectories. It claims 3-8x faster exploration than prior state-of-the-art approaches and runs in CPU-based simulation without requiring CUDA.

## Use cases
- plan autonomous exploration paths for a quadrotor in unknown environments
- simulate fast UAV exploration of indoor and outdoor spaces
- research frontier-based exploration planning for drones
- generate minimum-time trajectories for aerial robots
- benchmark exploration planners against state-of-the-art methods
- build a drone that autonomously maps an unknown area

## When to choose
- you need a proven, fast autonomous exploration stack for a quadrotor
- you want a research-grade baseline for UAV exploration planning papers
- you need CPU-only simulation of exploration without CUDA dependencies
- you want incremental frontier structure maintenance integrated with online mapping

## When to avoid
- you need multi-UAV decentralized exploration - use the companion RACER project instead
- you target non-ROS or non-Linux platforms
- you need ground robots or other non-aerial platforms without adaptation
- you want a production-ready commercial autopilot rather than research code

## Facets
- artifact type: library
- maturity: stable
- function: simulation, robotics
- domain: robotics, autonomous-vehicles, simulation
- platform: cpp
- tags: uav, aerial-robotics, exploration, frontier-based-planning, quadrotor, motion-planning, autonomous-navigation, research-code, linux, ros

## Member repositories
- HKUST-Aerial-Robotics/FUEL (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:47.419179+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:35:19.215214+00:00, confidence not recorded.
  - readme: https://github.com/HKUST-Aerial-Robotics/FUEL (fetched 2026-08-28T04:04:47.419179+00:00, sha 066b4d72ad05)
- Data as of 2026-08-30T08:39:29.467469+00:00.