Enhanced LiDAR-Based Localization via Multiresolution Iterative Closest Point Algorithms and Feature Extraction
- 5 November 2024
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 6 (3) , 738-746
Abstract
Vehicle localization is a critical component in autonomous driving systems, and LiDAR-based methods have become increasingly popular for this task. In this paper, we present a novel vehicle localization approach based on the point cloud map generated from LiDAR data. In particular, our approach first uses semantic segmentation and feature point extraction techniques to create an efficient feature point map and a long-lasting map from LiDAR sequences with corresponding poses. We then introduce a map-based online localization method that achieves precise vehicle localization using both LiDAR scans and the two point cloud maps, along with a multi-resolution ICP strategy. Comprehensive evaluations are conducted on the KITTI odometry dataset and the collected results demonstrate superior performance over the existing literature in both odometry metrics and absolute translation error. Our multi-resolution ICP-based method holds significant potential for map-based vehicle localization, offering promising prospects for application in autonomous driving and associated domains.Keywords
This publication has 65 references indexed in Scilit:
- Low‐cost solid‐state LiDAR/inertial‐based localization with prior map for autonomous systems in urban scenariosIET Intelligent Transport Systems, 2022
- Global-Map-Registered Local Visual Odometry Using On-the-Fly Pose Graph Updates2020
- LiDAR-based vehicle localization on the satellite image via a neural networkRobotics and Autonomous Systems, 2020
- Multimodal localization: Stereo over LiDAR mapJournal of Field Robotics, 2020
- Geographically Local Representation Learning with a Spatial Prior for Visual Localization2020
- RTAB‐Map as an open‐source lidar and visual simultaneous localization and mapping library for large‐scale and long‐term online operationJournal of Field Robotics, 2018
- Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry2018
- Iterative Global Similarity Points: A Robust Coarse-to-Fine Integration Solution for Pairwise 3D Point Cloud Registration2018
- Global localization of 3D point clouds in building outline maps of urban outdoor environmentsInternational Journal of Intelligent Robotics and Applications, 2017
- Analysis and modeling GPS NLOS effect in highly urbanized areaGPS Solutions, 2017