Urban Drone Navigation: Autoencoder Learning Fusion for Aerodynamics

TL;DR

This paper introduces a novel autonomous drone navigation method for urban SAR that combines multi-objective reinforcement learning with autoencoder-based wind simulation, enabling efficient obstacle avoidance and wind compensation using urban imagery.

Contribution

It presents a new fusion of MORL and autoencoder techniques for urban drone navigation, reducing sensor reliance and improving decision-making in complex environments.

Findings

Enhanced navigation accuracy in urban environments

Effective wind compensation without traditional sensors

Improved SAR operation efficiency in simulations

Abstract

Drones are vital for urban emergency search and rescue (SAR) due to the challenges of navigating dynamic environments with obstacles like buildings and wind. This paper presents a method that combines multi-objective reinforcement learning (MORL) with a convolutional autoencoder to improve drone navigation in urban SAR. The approach uses MORL to achieve multiple goals and the autoencoder for cost-effective wind simulations. By utilizing imagery data of urban layouts, the drone can autonomously make navigation decisions, optimize paths, and counteract wind effects without traditional sensors. Tested on a New York City model, this method enhances drone SAR operations in complex urban settings.