Related Experiment Video
Updated: Aug 9, 2025

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging
Published on: April 18, 2025
LiDAR-Based Sensor Fusion SLAM and Localization for Autonomous Driving Vehicles in Complex Scenarios.
Kai Dai1, Bohua Sun1, Guanpu Wu1
1State Key Laboratory of Automotive Simulation and Control, Jilin University, Changchun 130025, China.
This study introduces a multi-sensor fusion approach for simultaneous localization and mapping (SLAM) and online localization in autonomous driving. The method enhances map accuracy and localization robustness in complex environments.
Area of Science:
- Robotics and Autonomous Systems
- Geospatial Information Science
Background:
- LiDAR-based SLAM and online localization are crucial for autonomous driving.
- Existing single-sensor methods struggle with map drift and adaptability in complex scenarios.
Purpose of the Study:
- To propose a novel multi-sensor fusion method for SLAM and online localization.
- To enhance the accuracy, robustness, and adaptability of autonomous driving systems.
Main Methods:
- A general framework integrating front-end (NDT registration, loop closure, RTK-GNSS) and back-end (pose graph optimization) for drift-free mapping.
- An error state Kalman filter (ESKF) for fusing LiDAR localization and vehicle states for precise localization.
Main Results:
- Achieved 5-10 cm mapping accuracy and 20-30 cm localization accuracy.
- Demonstrated effective online autonomous driving in complex scenarios using the KITTI dataset and field tests.
Conclusions:
- The proposed multi-sensor fusion SLAM and localization method significantly improves performance.
- This approach offers a robust solution for autonomous driving in challenging environments.
Related Concept Videos
Types of Global Positioning System Surveys
Field Application of Global Positioning System
Design Example: Identifying the Locations of Monuments in the Field Using Global Positioning System Device
Introduction to Global Positioning System
Errors in Global Positioning System
Confocal Fluorescence Microscopy

