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

2025-08-04

AI Summary

To address the challenges of autonomous navigation and robust obstacle avoidance for UAVs in GPS-denied environments—such as orchards—this paper proposes an end-to-end visual navigation framework integrating a Variational Autoencoder (VAE) with intervention-aware imitation learning. Leveraging monocular camera data collected in real orchard settings, we design a lightweight VAE-based latent-space controller that learns navigation policies from minimal human demonstrations. A dynamic intervention mechanism is introduced to balance safety-critical oversight with operational autonomy. Experimental results demonstrate substantial improvements: flight distance and autonomy rate increase significantly under GPS-denied conditions; obstacle avoidance success rate rises by 12.7% over state-of-the-art methods; and the approach exhibits strong generalization across unseen environments, varying illumination conditions, and speed changes, while maintaining closed-loop stability.

Technology Category

• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

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.

Problem

• Autonomous UAV navigation in GPS-denied orchard environments
• Vision-based obstacle avoidance using imitation learning
• Generalizing navigation policies to varying orchard conditions

Innovation

• VAE-based controller for UAV navigation
• Intervention-based learning from human experience
• Vision-based policy generalizes to new environments