AgroBot: AI-Powered Smart Robotic Lawn Mower

Abstract: Autonomous lawn mowers represent a significant advancement in agricultural robotics, offering labor reduction and precision maintenance for residential and commercial applications. This paper presents the design, implementation, and field validation of AgroBot, a low-cost autonomous lawn mower incorporating GPS navigation, LiDAR-based obstacle avoidance, and AI-powered weed detection capabilities. The system employs a Raspberry Pi 4 as the primary computing platform running ROS Noetic, integrated with Pixhawk 2.4.8 for motion control and sensor fusion. Field testing conducted over a 500 m² area demonstrated 90.0% average coverage efficiency across five missions, with robust obstacle avoidance (100% success rate) and AI-based weed detection achieving 87.3% mean Average Precision (mAP). The complete system cost of ₹58,450 represents a 51-71% cost reduction compared to commercial alternatives while providing superior customizability and research extensibility. Performance metrics include 150-minute operational runtime, 0.85m GPS-EKF positioning accuracy, and autonomous operation through Boustrophedon path planning with real-time dynamic obstacle avoidance.

Keywords: Autonomous Navigation, Lawn Mower Robot, SLAM, YOLOv5, Coverage Path Planning, ROS, Sensor Fusion, Mobile Robotics, Agricultural Robotics