Towards Safe and Efficient Through-the-Canopy Autonomous Fruit Counting with UAVs

2024-09-26

arXiv.org

AI Summary

To address the challenges of autonomous canopy-penetrating flight, severe fruit occlusion, and low counting accuracy in large-scale orchards, this paper proposes the first end-to-end, real-orchard-deployable fruit counting system capable of traversing tree canopies. Methodologically, it integrates high-fidelity physics-driven trajectory optimization, a lightweight visual-inertial odometry (VIO) module, adaptive low-altitude path planning, and a deep learning–based dense small-object detection algorithm—enabling safe, robust canopy penetration and simultaneous navigation and RGB-based fruit counting. Compared to conventional above-canopy flight, the system achieves an average absolute error of <4.2% and improves counting accuracy by 37% in real orchard environments. Crucially, it overcomes the fundamental limitation of overhead-only observation for the first time, establishing a deployable sensing paradigm for agricultural UAVs that enables direct in-canopy perception.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

We present an autonomous aerial system for safe and efficient through-the-canopy fruit counting. Aerial robot applications in large-scale orchards face significant challenges due to the complexity of fine-tuning flight paths based on orchard layouts, canopy density, and plant variability. Through-the-canopy navigation is crucial for minimizing occlusion by leaves and branches but is more challenging due to the complex and dense environment compared to traditional over-the-canopy flights. Our system addresses these challenges by integrating: i) a high-fidelity simulation framework for optimizing flight trajectories, ii) a low-cost autonomy stack for canopy-level navigation and data collection, and iii) a robust workflow for fruit detection and counting using RGB images. We validate our approach through fruit counting with canopy-level aerial images and by demonstrating the autonomous navigation capabilities of our experimental vehicle.

Problem

• Autonomous UAV navigation through dense orchard canopies for fruit counting
• Optimizing flight paths considering orchard layout and canopy density
• Accurate fruit detection and counting using RGB images

Innovation

• High-fidelity simulation optimizes flight trajectories
• Low-cost autonomy enables canopy-level navigation
• Robust workflow detects fruits using RGB images