LiDAR-Based Negative Obstacle Detection for Unmanned Ground Vehicles in Orchards
2024

LiDAR-Based Negative Obstacle Detection for Unmanned Ground Vehicles in Orchards

publication Evidence: high

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)

10.3390/s24247929

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication