End-to-End Crop Row Navigation via LiDAR-Based Deep Reinforcement Learning

2025/09/23 by Mineiro, Ana Luiza, Affonso, Francisco, Becker, Marcelo
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Robotics (cs.RO)

paper · doi:10.48550/arxiv.2509.18608

Abstract

Reliable navigation in under-canopy agricultural environments remains a challenge due to GNSS unreliability, cluttered rows, and variable lighting. To address these limitations, we present an end-to-end learning-based navigation system that maps raw 3D LiDAR data directly to control commands using a deep reinforcement learning policy trained entirely in simulation. Our method includes a voxel-based downsampling strategy that reduces LiDAR input size by 95.83%, enabling efficient policy learning without relying on labeled datasets or manually designed control interfaces. The policy was validated in simulation, achieving a 100% success rate in straight-row plantations and showing a gradual decline in performance as row curvature increased, tested across varying sinusoidal frequencies and amplitudes.

Citations

• RSL-RL: A Learning Library for Robotics Research
• CaRL: Learning Scalable Planning Policies with Simple Rewards
• Autonomous Navigation of 4WIS4WID Agricultural Field Mobile Robot using Deep Reinforcement Learning
• Goal-Driven Autonomous Exploration Through Deep Reinforcement Learning
• Proximal Policy Optimization Algorithms

Related

• Towards Over-Canopy Autonomous Navigation: Crop-Agnostic LiDAR-Based Crop-Row Detection in Arable Fields
• A Deep Learning Driven Algorithmic Pipeline for Autonomous Navigation in Row-Based Crops
• Lessons from Deploying CropFollow++: Under-Canopy Agricultural Navigation with Keypoints
• Deep learning-based Crop Row Detection for Infield Navigation of Agri-Robots
• AdaCropFollow: Self-Supervised Online Adaptation for Visual Under-Canopy Navigation