Claim · model-written summary
Fusion precision gained 29.44% versus baseline methods.
Not reportedMaterialGeneCompoundOrgan / stageInteractorInteractor roleSecond interactorSecond interactor roleTreatmentSettingQualifier
Verbatim
e0“a 29.44% gain vs baseline methods”
t0“orchard”
Title
An integrated perception and navigation system for autonomous orchard vehicle
Yanyan Lin; Xingyu Lin; Zhengkun Cheng AIP Advances 2026. doi:10.1063/5.0312312
Other claims from this paper (12)
- Method / resource Point cloud preprocessing reduced computational load by 68%.
- Method / resource YOLOv7 achieved 95.9% precision on the orchard test set.
- Method / resource YOLOv7 achieved 95.7% recall on the orchard test set.
- Method / resource YOLOv7 achieved 75.2% mAP@0.5:0.95 on the orchard test set.
- Method / resource The fusion system achieved 97.80% precision in a simulated orchard.
- Method / resource The fusion system achieved 96.50% recall in a simulated orchard.
- Method / resource Fusion precision improved by 4.36% over enhanced single-sensor approaches.
- Method / resource The system processed each frame in 41 ms.
- Method / resource The system processed 24.4 FPS.
- Method / resource The effective perception range was 10 m.
- Method / resource Across 100-frame sequences, perfect detection reached 69%, above single-sensor methods.
- Method / resource Field trials found fusion perception sufficient for practical autonomous navigation.