Rotation-Equivariant Feature Learning on Polar BEV for Robust LiDAR Place Recognition

LiDAR-based place recognition is critical for long-term autonomous navigation in Global Navigation Satellite System (GNSS)-denied environments, yet existing methods struggle to balance accuracy and efficiency under substantial yaw rotations. This paper proposes a robust framework based on a multi-ch...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Zhenhuan Yuan, Youchun Xu, Zhichao Zhang, Yuan Zhu, Jianshi Li, Feng Lu, Le Wang, Jinsheng Chen, Wei Lei
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2026-06-01
Colecção:	Applied Sciences
Assuntos:	LiDAR place recognition rotation invariance bird’s eye view deep learning autonomous driving simultaneous localization and mapping
Acesso em linha:	https://www.mdpi.com/2076-3417/16/12/6155
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!