Improved LiDAR Odometry and Mapping using Deep Semantic Segmentation and Novel Outliers Detection

arXiv:2403.03111v1 Announce Type: new
Abstract: Perception is a key element for enabling intelligent autonomous navigation. Understanding the semantics of the surrounding environment and accurate vehicle pose estimation are essential capabilities for autonomous vehicles, including self-driving cars and mobile robots that perform complex tasks. Fast moving platforms like self-driving cars impose a hard challenge for localization and mapping algorithms. In this work, we propose a novel framework for real-time LiDAR odometry and mapping based on LOAM architecture for fast moving platforms. …

abstract arxiv autonomous autonomous vehicles capabilities cars cs.ai cs.cv cs.ro detection driving element enabling environment intelligent key lidar mapping mobile moving navigation novel outliers perception platforms robots segmentation self-driving semantic semantics tasks type understanding vehicles