Vision-based Navigation of Unmanned Aerial Vehicles in Orchards: An Imitation Learning Approach

TL;DR

This paper presents a novel vision-based UAV navigation system in orchards using a VAE-based controller trained via imitation learning, enabling autonomous obstacle avoidance and longer flights with minimal human input.

Contribution

Introduces a VAE-based visuomotor policy trained with intervention learning for orchard UAV navigation, demonstrating effective real-world performance and generalization.

Findings

UAV can autonomously navigate orchard rows after few training iterations

Controller achieves superior obstacle avoidance compared to existing methods

Policy generalizes well to new environments and varying conditions

Abstract

Autonomous unmanned aerial vehicle (UAV) navigation in orchards presents significant challenges due to obstacles and GPS-deprived environments. In this work, we introduce a learning-based approach to achieve vision-based navigation of UAVs within orchard rows. Our method employs a variational autoencoder (VAE)-based controller, trained with an intervention-based learning framework that allows the UAV to learn a visuomotor policy from human experience. We validate our approach in real orchard environments with a custom-built quadrotor platform. Field experiments demonstrate that after only a few iterations of training, the proposed VAE-based controller can autonomously navigate the UAV based on a front-mounted camera stream. The controller exhibits strong obstacle avoidance performance, achieves longer flying distances with less human assistance, and outperforms existing algorithms. Furthermore, we show that the policy generalizes effectively to novel environments and maintains competitive performance across varying conditions and speeds. This research not only advances UAV autonomy but also holds significant potential for precision agriculture, improving efficiency in orchard monitoring and management.