Research Analyzer
← Back ICRA 2026

Autonomous Flights Inside Narrow Tunnels

Luqi Wang, Yan Ning, Hongming Chen, Peize Liu, Yang Xu, Hao Xu, Ximin Lyu and Shaojie Shen

PDF

AI summary

Key figure (auto-extracted from paper)
First autonomous quadrotor system to safely navigate real, arbitrarily directed tunnels as narrow as 0.5 meters, outperforming human pilots.
Narrow tunnel navigation autonomous quadrotor ego-airflow disturbance virtual omni-directional perception motion planning confined space robotics

Problem

Multirotors struggle to navigate extremely narrow, featureless tunnels due to severe perception limitations (lack of light and geometry, restricted field of view) and intense ego-airflow disturbances that disrupt control stability.

Approach

A compact quadrotor platform featuring a virtual omni-directional perception module and a novel motion planner that integrates real-time tunnel mapping with computational fluid dynamics-based airflow disturbance modeling.

Key results

  • Virtual omni-directional perception module for state estimation and centerline extraction
  • Perception-and-disturbance-aware motion planning framework for safe trajectory generation
  • Complete real-time autonomous flight system integrated on a custom lightweight quadrotor
  • Extensive real-world validation demonstrating superior navigation performance over human pilots

Why it matters

Enables reliable autonomous inspection and search-and-rescue operations in previously inaccessible confined infrastructure, advancing field robotics and UAV deployment.

Abstract

Multirotors are usually desired to enter confined narrow tunnels that are barely accessible to humans in various applications including inspection, search and rescue, and so on. This task is extremely challenging since the lack of geometric features and illuminations, together with the limited field of view, cause problems in perception; the restricted space and significant ego airflow disturbances induce control issues. This paper introduces an autonomous aerial system designed for navigation through tunnels as narrow as 0.5 m in diameter. The real-time and online system includes a virtual omni-directional perception module tailored for the mission and a novel motion planner that incorporates perception and ego airflow disturbance factors modeled using camera projections and computational fluid dynamics analyses, respectively. Extensive flight experiments on a custom-designed quadrotor are conducted in multiple realistic narrow tunnels to validate the superior performance of the system, even over human pilots, proving its potential for real applications. Additionally, a deployment pipeline on other multirotor platforms is outlined and open-source packages are provided for future developments1.

Index terms

Aerial Systems: Applications Motion and Path Planning Autonomous Vehicle Navigation Field Robots

Related papers