SemVecNet: Generalizable Vector Map Generation for Arbitrary Sensor Configurations

arXiv:2405.00250v1 Announce Type: new
Abstract: Vector maps are essential in autonomous driving for tasks like localization and planning, yet their creation and maintenance are notably costly. While recent advances in online vector map generation for autonomous vehicles are promising, current models lack adaptability to different sensor configurations. They tend to overfit to specific sensor poses, leading to decreased performance and higher retraining costs. This limitation hampers their practical use in real-world applications. In response to this challenge, we propose a …

abstract adaptability advances arxiv autonomous autonomous driving autonomous vehicles cs.cv cs.ro current driving localization maintenance map maps planning sensor tasks type vector vehicles while