Autonomous Agricultural Robot LABINM

Self-localizing robotic system with mapping and AI capabilities for crop monitoring (FONDECYT 171-2020)

Project Overview

This government-funded research project (FONDECYT 171-2020) developed an autonomous mobile robot capable of self-localization, environment mapping, and AI-powered data processing to improve agricultural yield projections for crops in the La Libertad region of Peru.

The project addressed a critical challenge in blueberry pre-harvest operations: the sampling process for yield projections requires specialized labor and is prone to errors, leading to supply chain disruptions and economic losses when projections differ from reality.

Left: The LABINM mobile robot designed for agricultural environments. Center: Blueberry cultivation in Trujillo, Peru with sandy, uneven terrain. Right: Simulated blueberry farm environment in Gazebo.

The Robot Platform

The LABINM robot was designed specifically for navigation in challenging agricultural terrain found in coastal agro-industrial fields of Peru and Chile. Key specifications include:

Component Specification
Drive System Skid Steering (4-wheel differential)
Wheel Diameter 33 cm
Dimensions 1.40m × 1.10m × 0.62m (L × W × H)
LiDAR Sensor Ouster OS1-32 (3D, 32-channel)
Compute Units NVIDIA Jetson + Raspberry Pi
Suspension Active suspension system
Motor Controllers ODrive

The following figure shows the robot model in the Gazebo simulator showing the dimensions and the Ouster OS1-32 LiDAR mounted on top.

Virtual robot model in Gazebo simulator.

The autonomous navigation system was built on the ROS Navigation Stack, while also integrating and testing multiple algorithms for robust operation in multiple environments:

Core Components

  • Mapping: Gmapping (2D SLAM) and LeGO-LOAM (3D LiDAR Odometry)
  • Localization: Adaptive Monte Carlo Localization (AMCL), LeGO-LOAM, and Advanced Localization System (ALS)
  • Global Planning: A* algorithm
  • Local Planning: Dynamic Window Approach (DWA)

This is a demo of the navigation system in action.

Left: Overview of the LABINM robot's autonomous navigation capabilities in agricultural environments. Right: Complementary video for the Workshop on Robotics in Agriculture (WRIA) at IEEE/RSJ IROS 2023.

Publications

This project resulted in the following peer-reviewed publications:

  1. Comparative Analysis of LiDAR Inertial Odometry Algorithms in Blueberry Crops (2025)
    • R. Huaman, C. Gonzalez, and S. Prado
    • III International Congress on Technology and Innovation in Engineering and Computing
    • DOI: 10.3390/engproc2025083009
  2. Performance Evaluation of the ROS Navigation Stack Using LeGO-LOAM (2024)
  3. Linear Quadratic Regulator (LQR) Control for the Active Suspension System of a Four-Wheeled Agricultural Robot (2023)
    • J. A. Bazan Quispe, R. J. Huaman Kemper, and S. R. Prado Gardini
    • IEEE XXX International Conference on Electronics, Electrical Engineering and Computing (INTERCON)
    • DOI: 10.1109/INTERCON59652.2023.10326049
  4. Autonomous Navigation of a Four-Wheeled Robot in a Simulated Blueberry Farm Environment (2022)

Workshop Presentations

  • Comparative Analysis of LiDAR Odometry Algorithms in Blueberry Crops (2023)
    • C. A. Gonzalez, R. J. Huaman Kemper, and S. R. Prado Gardini
    • Workshop on Robotics in Agriculture: Present and Future of Agricultural Robotics and Technologies
    • IEEE/RSJ IROS 2023, Detroit, USA
    • Workshop Website

Acknowledgments

This research was funded by FONDECYT (Fondo Nacional de Desarrollo Científico, Tecnológico y de Innovación Tecnológica) under project 171-2020-FONDECYT and conducted at the Laboratorio de Investigación Multidisciplinaria (LABINM) at Universidad Privada Antenor Orrego (UPAO), Trujillo, Peru.