P-AgNav: Range View-Based Autonomous Navigation System for Cornfields
Kitae Kim, Aarya Deb, David Cappelleri
AI summary
Problem
GNSS signals and camera-based navigation fail under dense corn canopies due to signal blockage and varying illumination, leaving a gap for reliable, multi-row autonomous navigation.
Approach
The system converts 3D LiDAR point clouds into 2D range view images and processes them through a four-stage pipeline using blob detection and model predictive control to steer the robot safely through rows and across gaps.
Key results
- Reliable multi-row navigation without GNSS or pre-defined waypoints
- Minimal collisions with corn plants via stalk-focused detection
- Successful adaptation of 3D LiDAR range views to agricultural robotics
- Validated performance in both simulation and real cornfield environments
Why it matters
Provides a robust, sensor-efficient navigation solution for under-canopy agricultural robots, advancing automated crop monitoring and sampling in precision farming.
Abstract
In this paper, we present an in-row and under- canopy autonomous navigation system for cornfields, called the Purdue Agricultural Navigation System or P-AgNav. Our navigation framework is primarily based on range view images from a 3D light detection and ranging (LiDAR) sensor. P- AgNav is designed for an autonomous robot to navigate in the corn rows with collision avoidance and to switch between rows without GNSS assistance or pre-defined waypoints. The system enables robots, which are intended to monitor crops or conduct physical sampling, to autonomously navigate multiple crop rows with minimal human intervention, thereby increasing crop management efficiency. The capabilities of P-AgNav have been validated through experiments in both simulation and real cornfield environments.