Real-time windrow detection from onboard tractor sensors for automated following
Lorenz Gunreben, Nico Heider, Sebastian Zürner, Martin Schieck, Bogdan Franczyk
TLDR
This paper presents an open-source, real-time windrow detection system using stereo vision and LiDAR for autonomous forage harvesting.
Key contributions
- Released a multi-modal dataset combining stereo vision and LiDAR from real baling operations, partly as ROS2 bags.
- Implemented a real-time (>20 Hz) centroid-based windrow-following method on an NVIDIA Jetson AGX Orin.
- Demonstrated low-cost stereo sensors can approach LiDAR performance for windrow depth (0.965 +/- 0.021).
- Provided an open-source ROS 2 pipeline for reproducible, GPS-free windrow detection benchmarks.
Why it matters
This paper addresses the lack of transparency in commercial windrow-detection systems by providing an open-source solution and dataset. It enables reproducible research and development of practical, GPS-free autonomous forage-harvesting systems. This advances agricultural automation significantly.
Original Abstract
Proprietary design in commercial windrow-detection systems restricts transparency and limits progress in open autonomous forage-harvesting research. We present a multi-modal dataset combining stereo vision and LiDAR from tractor-mounted sensors during real baling operations. The dataset includes synchronized sensor data with GNSS trajectories, partly released as ROS2 Humble bags on Zenodo, with additional data available on request. Using this dataset, we implement a real-time (>20 Hz) centroid-based windrow-following method on an NVIDIA Jetson AGX Orin. Across the critical 4-10 m guidance range, stereo and LiDAR depth measurements show strong agreement (0.965 +/- 0.021), indicating that low-cost stereo sensors can approach LiDAR performance. Our open-source ROS 2 pipeline provides a reproducible benchmark for GPS-free windrow detection and supports development of practical autonomous forage-harvesting systems. Dataset: https://zenodo.org/records/17486318
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.