An Efficient Ground-aerial Transportation System for Pest Control Enabled by AI-based Autonomous Nano-UAVs

2025-02-20

AI Summary

To address the challenge of collaborative pest detection and treatment by nano-UAVs under extreme resource constraints, this paper proposes an aerial-ground cooperative intelligent crop-protection system. We design an ultra-lightweight CNN (0.58 GOps/frame) tailored for nano-UAVs, achieving real-time pest detection with 79% mAP at 33 mW power consumption on the GAP9 SoC. The system integrates global A* path planning with high-frequency local obstacle avoidance, enabling dynamic navigation under milliwatt-level computational budgets. A multi-agent coordinated scheduling mechanism orchestrates ground-based heavy vehicles for precise, targeted pesticide application. In a 200×200 m vineyard simulation, 25 UAVs collaboratively inspect the field and optimize ground vehicle routes, reducing total operation time by 20 hours compared to conventional single-UAV workflows. This work pioneers an integrated architecture unifying ultra-low-power visual perception, dynamic navigation, and mission-level coordination—setting a new benchmark for energy-efficient agricultural robotics.

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Learning & Optimization for CV

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Efficient crop production requires early detection of pest outbreaks and timely treatments; we consider a solution based on a fleet of multiple autonomous miniaturized unmanned aerial vehicles (nano-UAVs) to visually detect pests and a single slower heavy vehicle that visits the detected outbreaks to deliver treatments. To cope with the extreme limitations aboard nano-UAVs, e.g., low-resolution sensors and sub-100 mW computational power budget, we design, fine-tune, and optimize a tiny image-based convolutional neural network (CNN) for pest detection. Despite the small size of our CNN (i.e., 0.58 GOps/inference), on our dataset, it scores a mean average precision (mAP) of 0.79 in detecting harmful bugs, i.e., 14% lower mAP but 32x fewer operations than the best-performing CNN in the literature. Our CNN runs in real-time at 6.8 frame/s, requiring 33 mW on a GWT GAP9 System-on-Chip aboard a Crazyflie nano-UAV. Then, to cope with in-field unexpected obstacles, we leverage a global+local path planner based on the A* algorithm. The global path planner determines the best route for the nano-UAV to sweep the entire area, while the local one runs up to 50 Hz aboard our nano-UAV and prevents collision by adjusting the short-distance path. Finally, we demonstrate with in-simulator experiments that once a 25 nano-UAVs fleet has combed a 200x200 m vineyard, collected information can be used to plan the best path for the tractor, visiting all and only required hotspots. In this scenario, our efficient transportation system, compared to a traditional single-ground vehicle performing both inspection and treatment, can save up to 20 h working time.

Problem

• AI-based nano-UAVs for pest detection
• Optimized CNN for low-power pest detection
• Efficient path planning for crop treatment

Innovation

• AI-based nano-UAVs for pest detection
• Tiny CNN optimized for low-power UAVs
• Global+local A* path planning system