Visual Marker Search for Autonomous Drone Landing in Diverse Urban Environments

2026-01-16

AI Summary

This study addresses the limited robustness of existing vision-based drone landing methods in complex urban environments, where performance is often degraded by varying illumination, adverse weather, and occlusions. To systematically evaluate such approaches, the authors develop a high-fidelity simulation platform using AirSim that realistically models diverse urban layouts and environmental conditions. The system integrates onboard RGB and depth sensors to enable fiducial marker detection and obstacle avoidance, and compares the exploration efficacy of heuristic coverage strategies against reinforcement learning agents. This work presents the first comprehensive assessment of visual landing techniques within a highly complex and systematically varied urban simulation environment, quantifying success rates, path efficiency, and robustness across different strategies. The findings highlight the critical influence of environmental complexity and sensor realism on reliable autonomous landing performance.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Vision for Robotics & Autonomous Driving

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

Marker-based landing is widely used in drone delivery and return-to-base systems for its simplicity and reliability. However, most approaches assume idealized landing site visibility and sensor performance, limiting robustness in complex urban settings. We present a simulation-based evaluation suite on the AirSim platform with systematically varied urban layouts, lighting, and weather to replicate realistic operational diversity. Using onboard camera sensors (RGB for marker detection and depth for obstacle avoidance), we benchmark two heuristic coverage patterns and a reinforcement learning-based agent, analyzing how exploration strategy and scene complexity affect success rate, path efficiency, and robustness. Results underscore the need to evaluate marker-based autonomous landing under diverse, sensor-relevant conditions to guide the development of reliable aerial navigation systems.

Problem

• autonomous drone landing
• visual marker
• urban environments
• sensor robustness
• realistic conditions

Innovation

• simulation-based evaluation
• urban autonomous landing
• reinforcement learning
• visual marker detection
• sensor-aware navigation