Lessons from Deploying CropFollow++: Under-Canopy Agricultural Navigation with Keypoints

TL;DR

CropFollow++ is a vision-based navigation system for under-canopy agricultural robots that uses semantic keypoints, addressing challenges like tight crop spacing and sensor noise, and has been successfully deployed over 25 km in real fields.

Contribution

The paper introduces CropFollow++, a modular perception system using semantic keypoints for under-canopy robot navigation, with large-scale deployment and practical insights.

Findings

Deployed over 25 km of autonomous navigation in real fields.

Demonstrated robustness of the system across various field conditions.

Provided key lessons for future under-canopy robotic navigation.

Abstract

We present a vision-based navigation system for under-canopy agricultural robots using semantic keypoints. Autonomous under-canopy navigation is challenging due to the tight spacing between the crop rows ($\sim 0.75$ m), degradation in RTK-GPS accuracy due to multipath error, and noise in LiDAR measurements from the excessive clutter. Our system, CropFollow++, introduces modular and interpretable perception architecture with a learned semantic keypoint representation. We deployed CropFollow++ in multiple under-canopy cover crop planting robots on a large scale (25 km in total) in various field conditions and we discuss the key lessons learned from this.