LiDAR-Based Negative Obstacle Detection for Unmanned Ground Vehicles in Orchards
Author Information
Author(s): Xie Peng, Wang Hongcheng, Huang Yexian, Gao Qiang, Bai Zihao, Zhang Linan, Ye Yunxiang
Primary Institution: Hangzhou Dianzi University
Hypothesis
Can a tilted LiDAR installation improve the detection of negative obstacles in orchard environments?
Conclusion
The proposed LiDAR detection method achieved a 92.7% success rate in identifying negative obstacles in orchards.
Supporting Evidence
- The tilted LiDAR installation reduced the blind spot from 3 m to 0.21 m.
- The point cloud density increased by an order of magnitude with the tilted setup.
- The detection success rate for negative obstacles reached 92.7%.
Takeaway
This study shows that tilting a LiDAR sensor helps robots find hidden dangers like ditches in orchards, making them safer.
Methodology
The study used a tilted installation of solid-state LiDAR to enhance point cloud density and reduce blind spots for detecting negative obstacles.
Limitations
The detection algorithm may produce false alarms in unstructured environments due to irregular point cloud shapes.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website