End-to-End Crop Row Navigation via LiDAR-Based Deep Reinforcement Learning
This addresses navigation challenges for agricultural robots in cluttered, GNSS-unreliable settings, but is incremental as it builds on existing simulation-based reinforcement learning methods.
The paper tackled the problem of reliable navigation in under-canopy agricultural environments by developing an end-to-end deep reinforcement learning system that maps raw 3D LiDAR data to control commands, achieving a 100% success rate in straight-row plantations in simulation.
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.