Visual Marker Search for Autonomous Drone Landing in Diverse Urban Environments

TL;DR

The paper addresses the challenge of robust marker-based landing in GPS-denied urban environments. It introduces a high-fidelity AirSim-based simulation suite with diverse layouts, lighting, and weather to evaluate three navigation strategies—two heuristic coverage patterns and a learning-based E2E-RL agent—using onboard RGB for marker detection and depth for obstacle avoidance. Key contributions include a richly varied, interactive dataset spanning three urban maps, systematic cross-strategy evaluation under scene diversity, and analysis of how exploration strategy and environmental complexity affect success, efficiency, and robustness. The work provides a controlled testbed to advance autonomous aerial navigation in real-world urban deployments and points toward adaptive 3D exploration and richer visual cues as future directions.

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.

Figures (4)

• Figure 2: Drone System
• Figure 3: Examples of Marker Placement Across Environments (Markers Highlighted in Red)
• Figure 4: Parameter Distribution
• Figure : Task Overview