Reinforcement Learning-Based Monocular Vision Approach for Autonomous UAV Landing

TL;DR

This paper presents a reinforcement learning-based method for autonomous UAV landing using only a monocular camera, leveraging visual cues to estimate altitude and depth without specialized sensors.

Contribution

It introduces a novel approach that uses reinforcement learning to interpret visual features for UAV landing, eliminating the need for depth cameras.

Findings

Effective in simulation and real-world experiments

Achieves accurate landing without depth sensors

Demonstrates robustness under varying conditions

Abstract

This paper introduces an innovative approach for the autonomous landing of Unmanned Aerial Vehicles (UAVs) using only a front-facing monocular camera, therefore obviating the requirement for depth estimation cameras. Drawing on the inherent human estimating process, the proposed method reframes the landing task as an optimization problem. The UAV employs variations in the visual characteristics of a specially designed lenticular circle on the landing pad, where the perceived color and form provide critical information for estimating both altitude and depth. Reinforcement learning algorithms are utilized to approximate the functions governing these estimations, enabling the UAV to ascertain ideal landing settings via training. This method's efficacy is assessed by simulations and experiments, showcasing its potential for robust and accurate autonomous landing without dependence on complex sensor setups. This research contributes to the advancement of cost-effective and efficient UAV landing solutions, paving the way for wider applicability across various fields.