Donghwi Jung

About

Donghwi Jung is a researcher at the forefront of deep learning for robotic perception, with a primary focus on LiDAR-based odometry and localization. His most notable contribution is the development of **LoRCoN-LO**, a novel LiDAR odometry method that leverages a **Long-term Recurrent Convolutional Network (LRCN)**. This architecture uniquely integrates Convolutional Neural Networks (CNNs) for spatial feature extraction with Long Short-Term Memory (LSTM) networks for temporal sequence learning, enabling the system to process spatial and temporal information simultaneously. This innovation significantly enhances the robustness and accuracy of pose estimation in complex, long-duration autonomous navigation tasks. While his work is early in its citation lifecycle, with LoRCoN-LO already accumulating 3 citations since 2023, it represents a promising direction for real-time SLAM systems. Jung’s research addresses a critical challenge in robotics: achieving reliable odometry without relying on traditional handcrafted features. His work is particularly relevant for students and researchers interested in deep learning for 3D perception, sensor fusion, and end-to-end learning for autonomous vehicles.

Research Focus

Key Achievements

Top Papers

1. 1
   LoRCoN-LO: Long-term Recurrent Convolutional Network-based LiDAR Odometry

   3 citations · 2023

Key Collaborators

Contact & Links