Lessons from Deploying CropFollow++: Under-Canopy Agricultural Navigation with Keypoints
This work addresses the problem of reliable robot navigation in dense agricultural environments for farmers and roboticists, though it appears incremental as it builds on prior keypoint-based methods.
The authors tackled autonomous under-canopy agricultural navigation by developing CropFollow++, a vision-based system using semantic keypoints, and deployed it on robots covering 25 km in various field conditions, achieving successful navigation despite challenges like tight crop spacing and sensor noise.
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.