NAVREN-RL: Learning to fly in real environment via end-to-end deep reinforcement learning using monocular images

TL;DR

NAVREN-RL enables micro drones to autonomously navigate indoor environments using end-to-end deep reinforcement learning with monocular images, emphasizing minimal sensing and efficient learning.

Contribution

The paper introduces NAVREN-RL, a novel RL-based method for indoor drone navigation using monocular images and minimal sensors, with integrated expert data for faster convergence.

Findings

Successful obstacle avoidance in indoor arenas

Effective navigation with minimal sensing modalities

Improved convergence through expert data integration

Abstract

We present NAVREN-RL, an approach to NAVigate an unmanned aerial vehicle in an indoor Real ENvironment via end-to-end reinforcement learning RL. A suitable reward function is designed keeping in mind the cost and weight constraints for micro drone with minimum number of sensing modalities. Collection of small number of expert data and knowledge based data aggregation is integrated into the RL process to aid convergence. Experimentation is carried out on a Parrot AR drone in different indoor arenas and the results are compared with other baseline technologies. We demonstrate how the drone successfully avoids obstacles and navigates across different arenas.