Harin Jang

About

Harin Jang is a researcher at the forefront of autonomous driving and robotics perception, with a core focus on sensor fusion and semantic environment mapping. Their most influential work, "Dynamic Occupancy Grid Map with Semantic Information Using Deep Learning-Based BEVFusion Method with Camera and LiDAR Fusion" (2024), addresses a critical limitation in traditional LiDAR-based dynamic occupancy grid maps (DOGMs). By integrating camera data through a bird’s-eye-view (BEV) fusion deep learning framework, Jang’s approach enriches DOGMs with semantic information—such as object classification—alongside position and velocity data. This innovation enhances the robustness and interpretability of environmental representations for autonomous systems. With 7 citations already in a short time, the paper signals growing impact in the field. Jang’s work bridges the gap between geometric mapping and semantic understanding, offering a more holistic solution for real-time navigation in complex scenes. Their contributions are particularly valuable for advancing safe and intelligent autonomous vehicles, where accurate fusion of multi-modal sensor data is essential.

Research Focus

Key Achievements

Top Papers

1. 1
   Dynamic Occupancy Grid Map with Semantic Information Using Deep Learning-Based BEVFusion Method with Camera and LiDAR Fusion

   7 citations · 2024

Key Collaborators

Contact & Links