Research Groups

Since the establishment of our laboratory in 1996, we established the Intelligent Vehicle IT Research Center funded by the Korean Government, and we started the intelligent vehicle research. Now we are conducting various types of research for the intelligent vehicle. The research focuses on autonomous driving not only in structured environments like urban areas but also in unstructured environments such as off-road areas. We engage in full-stack development and research, starting from hardware components like sensors and vehicles to embedded software. We strive to create a safer and high-performance autonomous driving system by utilizing both simulation and real-world environments simultaneously. Our research lab is committed to efficiently addressing the complex problem of autonomous driving by separating it into manageable components. We aim for all parts to work together optimally, leading to the development of a perfect autonomous driving system. Through these efforts, we have carried out large-scale national/corporate tasks and have numerous demonstration experiences within the laboratory, and have consistently published results in many domestic and international journals/conferences, including RA-L, ICRA, IROS, ICRA, ICML, and T-ITS.

* Research Field
- Environment Perception for Autonomous Vehicles
- Localization and Mapping for Autonomous Vehicles
- Planning for Autonomous Vehicles
- Decision Making for Autonomous Vehicles
- UAV & UGV Cooperative Driving for Intelligent Vehicles

* Research Keyword
- Object Detection / Semantic Segmentation / 3D Scene Reconstruction / 3D Scene Segmentation
- Reinforcement Learning / Inverse Reincforcement Learning / Imitation Learning
- Sensor Fusion / Decision Making / Interactive Path Planning / Safety-Critical-Systems Control
- Simultaneous Localization and Mapping (SLAM) / Active SLAM / Visual SLAM
- Representation Learning / Incremental Learning

1. Sang-Hyun Lee, Seung-Woo Seo, "Unsupervised Skill Discovery for Learning Shared Structures across Changing Environments", Proceedings of the 40th International Conference on Machine Learning (ICML), PMLR, pp. 19185-19199, 2023.
2. Min-Kook Suh and Seung-Woo Seo, "Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels", Proceedings of the 40th International Conference on Machine Learning (ICML), PMLR, pp. 32770-32782, 2023.
3. Chan Kim, Jaekyung Cho, Christophe Bobda, Seung-Woo Seo, Seong-Woo Kim, "SeRO: Self-Supervised Reinforcement Learning for Recovery from Out-of-Distribution Situations", International Joint Conference on Artificial Intelligence(IJCAI), pp. 3884-3892, 2023
4. Se-Wook Yoo, Chan Kim, Jinwoo Choi, Seong-Woo Kim, Seung-Woo Seo, "GIN: Graph-based Interaction-aware Constraint Policy Optimization for Autonomous Driving", IEEE Robotics and Automation Letter 8.2 (RA-L), pp. 464-471, 2023
5. Yurim Jeon, Hwichang Kim, Seung-Woo Seo, "ABCD: Attentive Bilateral Convolutional Network for Robust Depth Completion", IEEE Robotics and Automation Letter 7.1 (RA-L), pp. 81-87, 2023
6. Chan Kim, JaeKyung Cho, Hyung-Suk Yoon, Seung-Woo Seo, Seong-Woo Kim, "UNICON: Uncertainty-Conditioned Policy for Robust Behavior in Unfamiliar Scenarios", IEEE Robotics Autom. Lett. 7.4, (RA-L), pp. 9099-9106, 2022
7. Younghwa Jung, Seung-Woo Seo, and Seong-Woo Kim, "Fast Point Clouds Upsampling with Uncertainty Quantification for Autonomous Vehicles", International Conference on Robotics and Automation (ICRA). IEEE, 2022
8. Se-Wook Yoo, Seung-Woo Seo, "Learning Multi-Task Transferable Rewards via Variational Inverse Reinforcement Learning", International Conference on Robotics and Automation (ICRA). IEEE, 2022
9. Yurim Jeon, Seung-Woo Seo, "EFGHNet: A Versatile Image-to-Point Cloud Registration Network for Extreme Outdoor Environment", IEEE Robotics Autom. Lett. 7.3 (RA-L), pp. 7511-7517, 2022