Terrain Perception for Agricultural UAVs in Complex Farmland via Rotating mmWave Radar
Terrain Perception for Agricultural UAVs in Complex Farmland via Rotating mmWave Radar
This research presents a low-cost rotating millimeter-wave radar framework designed to improve terrain perception for uncrewed aerial vehicles (UAVs) operating in complex agricultural environments. The system addresses challenges such as occlusions and dynamic flight conditions by utilizing a mechanically rotating sensing design to expand spatial coverage. A pose-consistent terrain reconstruction pipeline is developed to handle sparse and noisy radar data, enabling reliable ground extraction. Deployed on a real agricultural UAV platform, the system was evaluated through extensive field experiments, achieving an F1 score of 94.42% for ground segmentation, outperforming existing rival systems that achieved 90.48%. The work demonstrates the viability of rotating mmWave radar as a robust sensing modality for terrain-following flight in adverse conditions.
The authors introduce a mechanically rotating mmWave radar system to overcome the limited field of view of fixed sensors, achieving an F1 score of 94.42% in field tests on agricultural UAVs.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
urface estimation in challenging agricultural scenarios. The complete system is deployed on a real agricultural UAV platform and evaluated through extensive field experiments. Experimental results demonstrate improved terrain coverage and estimation accuracy, achieving an F1 score of 94.42% for ground segmentation, while the closest rival only achieves 90.48%.
Open source S5
hanically rotating sensing design is introduced to enlarge spatial coverage and improve terrain observability beyond the limitations of fixed-view radar under dynamic low-altitude flight. Building upon this sensing capability, we further design a pose-consistent terrain reconstruction pipeline tailored for sparse, noisy, and partially observable radar data, enabling reliable ground extraction and continuous terrain s
Open source S4
Source：arXiv Robotics — research abstracts · arxiv.org