Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards Robust Autonomous Landing Systems: Iterative Solutions and Key Lessons Learned

Sebastian Schroder, Yao Deng, Alice James, Avishkar Seth, Kye Morton, Subhas Mukhopadhyay, Richard Han, Xi Zheng

TL;DR

The work addresses robust autonomous UAV landing using a marker-based approach within a multi-module onboard system. It combines a deep-learning marker detector (TPH-YOLOv5IY), an OctoMap-based occupancy mapper, and an OMPL-based RRT* planner to achieve collision-free landings. Across SIL, HIL, and real-world tests, MLS-V3 consistently outperforms earlier generations, reducing collisions and increasing landing success, while exposing edge-computing and GPS/mapping challenges that guide future improvements. The findings offer practical guidance for deploying marker-based autonomous landings and motivate formal verification and neurosymbolic approaches for safety-critical UAV autonomy.

Abstract

Uncrewed Aerial Vehicles (UAVs) have become a focal point of research, with both established companies and startups investing heavily in their development. This paper presents our iterative process in developing a robust autonomous marker-based landing system, highlighting the key challenges encountered and the solutions implemented. It reviews existing systems for autonomous landing processes, and through this aims to contribute to the community by sharing insights and challenges faced during development and testing.

Towards Robust Autonomous Landing Systems: Iterative Solutions and Key Lessons Learned

TL;DR

The work addresses robust autonomous UAV landing using a marker-based approach within a multi-module onboard system. It combines a deep-learning marker detector (TPH-YOLOv5IY), an OctoMap-based occupancy mapper, and an OMPL-based RRT* planner to achieve collision-free landings. Across SIL, HIL, and real-world tests, MLS-V3 consistently outperforms earlier generations, reducing collisions and increasing landing success, while exposing edge-computing and GPS/mapping challenges that guide future improvements. The findings offer practical guidance for deploying marker-based autonomous landings and motivate formal verification and neurosymbolic approaches for safety-critical UAV autonomy.

Abstract

Uncrewed Aerial Vehicles (UAVs) have become a focal point of research, with both established companies and startups investing heavily in their development. This paper presents our iterative process in developing a robust autonomous marker-based landing system, highlighting the key challenges encountered and the solutions implemented. It reviews existing systems for autonomous landing processes, and through this aims to contribute to the community by sharing insights and challenges faced during development and testing.
Paper Structure (23 sections, 7 figures, 3 tables)

This paper contains 23 sections, 7 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Marker Detection
  4. Path Planning
  5. Methodology
  6. Marker Detection Module
  7. Mapping Module
  8. Path Planning Module
  9. Decision-making Module
  10. Experiments
  11. Research Questions
  12. Benchmark
  13. Simulation Environments
  14. Autonomous Landing Systems
  15. Experiment Settings
  16. ...and 8 more sections

Figures (7)

  • Figure 1: Software Architecture of Autonomous Landing System
  • Figure 2: Decision Making Module State Machine
  • Figure 3: Workflow of the marker-based autonomous landing system
  • Figure 4: Examples of marker detection results. The top row is from OpenCV and the bottom row is from TPH-YOLO
  • Figure 5: Various issues experienced during testing
  • ...and 2 more figures