Jae-Kyung Cho

About

Jae-Kyung Cho is a researcher advancing the field of autonomous navigation through deep learning-based LiDAR odometry. Their key research areas include 3D perception, sensor fusion, and long-term sequential modeling for robotics. Cho’s major contribution is the development of LoRCoN-LO (Long-term Recurrent Convolutional Network-based LiDAR Odometry), a novel framework that integrates convolutional neural networks (CNNs) and long short-term memory (LSTM) layers to simultaneously process spatial and temporal information from LiDAR data. This approach significantly improves odometry estimation accuracy over long trajectories, addressing a critical challenge in autonomous driving and mobile robotics. With 3 citations since its 2023 publication, Cho’s work is gaining recognition for its innovative use of recurrent convolutional architectures to enhance localization robustness. Notably, LoRCoN-LO demonstrates how deep learning can replace traditional geometric methods, offering a more adaptive solution for complex environments. Cho’s research continues to inspire new directions in real-time, learning-based odometry, making them a promising voice in the intersection of computer vision and robotics.

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