An Improved PointPillars-Based Dual-LiDAR Method for Aircraft Relative Pose Estimation in Towbarless Towing Vehicles †

Yu Zhu, Falian Li, Hongfeng Yan, Liang Cui · 2026

Read An Improved PointPillars-Based Dual-LiDAR Method for Aircraft Relative Pose Estimation in Towbarless Towing Vehicles † by Yu Zhu, Falian Li, Hongfeng Yan, Liang Cui (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13611816.txt.

Description

Yu Zhu, Falian Li, Hongfeng Yan, and Liang Cui sharpen laser sensing so tow vehicles can gauge an aircraft's pose. Towbarless tractors risk oversteering while hauling planes on the ground. Two LiDAR units watch the rear wheels from angles that dodge blockage by the nose gear. A PointPillars detector, tuned for small wheel shapes, finds both wheels in the point cloud.

Height-spread encoding and a mixed convolution-attention backbone lift the reads. Detection scores rose about eight and a half points over the base method. The model stays small at about four million parameters and runs near thirty-eight frames per second. Wheel spots then fix the fuselage angle within safe bounds.

Catalog record

CREATORYu Zhu, Falian Li, Hongfeng Yan, Liang Cui
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE52 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13611816

Browse the full library · About the Tower of Babel