MAVRL: Learn to Fly in Cluttered Environments with Varying Speed

TL;DR

This paper presents a reinforcement learning-based obstacle avoidance system for drones that adapts speed to environmental complexity and uses a novel memory-augmented latent space to improve performance in cluttered environments, successfully deploying on real drones.

Contribution

Introduces a reinforcement learning pipeline with a novel memory-augmented latent space for improved drone obstacle avoidance in cluttered environments.

Findings

Varying speed improves success rate and agility.

Memory-augmented latent space outperforms standard latent representations.

Successful deployment on real drone after minimal fine-tuning.

Abstract

Many existing obstacle avoidance algorithms overlook the crucial balance between safety and agility, especially in environments of varying complexity. In our study, we introduce an obstacle avoidance pipeline based on reinforcement learning. This pipeline enables drones to adapt their flying speed according to the environmental complexity. Moreover, to improve the obstacle avoidance performance in cluttered environments, we propose a novel latent space. The latent space in this representation is explicitly trained to retain memory of previous depth map observations. Our findings confirm that varying speed leads to a superior balance of success rate and agility in cluttered environments. Additionally, our memory-augmented latent representation outperforms the latent representation commonly used in reinforcement learning. Finally, after minimal fine-tuning, we successfully deployed our network on a real drone for enhanced obstacle avoidance.