# Design of a 3D High-Definition Map Visualizer for Pose Estimation and Autonomous Navigation in Dynamic Environments

## TL;DR

This paper introduces a 3D HD map visualizer that helps autonomous vehicles navigate dynamic environments by integrating visual and LiDAR data in real-time.

## Contribution

The novel contribution is a real-time HD map framework with synchronized multimodal data and a semantic-aware pose estimation module for autonomous navigation.

## Key findings

- The framework generates accurate and interpretable HD maps for autonomous navigation in dynamic environments.
- The semantic-aware visual odometry module performs well under perceptually degraded conditions.
- The system is validated in urban scenarios with intermittent GNSS and can be used as a benchmarking tool.

## Abstract

A high-definition (HD) map development framework providing real-time visualization of multimodal perception data for state estimation, motion planning, and decision-making in autonomous navigation is presented and experimentally validated. The proposed framework integrates synchronized visual and LiDAR data and generates consistent frame transformations to construct accurate and interpretable HD maps suitable for navigation in dynamic environments. In addition, the framework enables flexible customization of essential map elements, including road features and static landmarks, facilitating efficient map generation and visualization. Building upon the developed HD map visualizer, a semantic-aware visual odometry (VO)-based pose estimation module is designed and verified through extensive evaluations and under perceptually degraded conditions. To ensure the reliability of synchronized multimodal data used by downstream perception and pose estimation modules, a sensor health monitoring system is also developed and validated in urban canyon scenarios with intermittent or unavailable global navigation satellite system (GNSS) measurements. Experimental results demonstrate that the proposed HD map visualizer and associated perception modules are transferable for autonomous navigation and can be effectively employed as benchmarking tools for state estimation and motion planning algorithms in autonomous driving.