SPARROW: Smart Precision Agriculture Robot for Ridding of Weeds

TL;DR

SPARROW addresses the challenge of reducing herbicide usage while maintaining crop yield by integrating a vision-based weed detection system with autonomous crop-row navigation and a dual-trajectory sprayer planner. The approach employs YOLOv8n for weed detection on a lightweight hardware stack and a ROS-based perception/navigation loop to enable autonomous spray actions, achieving real-time operation on a low-cost platform. Trajectory planning combines nearest-neighbor and Christofides algorithms, yielding comparative efficiencies: $ \Phi_N = \lambda_O/\lambda_N \approx 0.9399$ (93.99%) for NN and $ \Phi_C = \lambda_O/\lambda_C \approx 0.9322$ (93.22%) for Christofides, with strategy selection depending on weed distribution. Overall, the system demonstrates viable autonomous weed detection and spot spraying with a cost-effective, scalable vision-based framework for precision agriculture.

Abstract

The advancements in precision agriculture are vital to support the increasing demand for global food supply. Precision spot spraying is a major step towards reducing chemical usage for pest and weed control in agriculture. A novel spot spraying algorithm that autonomously detects weeds and performs trajectory planning for the sprayer nozzle has been proposed. Furthermore, this research introduces a vision-based autonomous navigation system that operates through the detected crop row, effectively synchronizing with an autonomous spraying algorithm. This proposed system is characterized by its cost effectiveness that enable the autonomous spraying of herbicides onto detected weeds.

Figures (11)

• Figure 1: Design of the SPARROW.
• Figure 2: System diagram of the SPARROW.
• Figure 3: Design of the herbicides sprayer.
• Figure 4: Output of weed detection system. a: Typical condition, b,c: Sunny condition, d: Shadowed condition.
• Figure 5: Precision-Recall curve.