A research team led by Professor Lee SeongWon of the Department of Electrical Engineering at Kookmin University (President Jeong Seung Ryul) has published a paper in the 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026), an international academic conference in the field of robotics. This achievement follows the team’s previous publication at the IEEE International Conference on Robotics and Automation (ICRA 2026) and serves as further confirmation of the Kookmin University research team’s capabilities in the fields of robotics and artificial intelligence.

This achievement is also aligned with the direction of “KMU VISION 2035: EDGE,” which Kookmin University announced in celebration of its 80th anniversary. Kookmin University is strengthening its future competitiveness by focusing on eight specialized fields, and the publication of this paper at IROS 2026 demonstrates how the research capabilities accumulated in the robotics and AI+X fields are translating into achievements at international academic conferences.

This research is particularly significant because Kim Jun-ho (Class of 2019, Department of Electrical Engineering) served as the first author. Kim Jun-ho previously served as a lead author on the “VG3T: Visual Geometry Grounded Gaussian Transformer” study, which was accepted at ICRA 2026, and has now published papers at world-class international conferences consecutively while still an undergraduate.

IROS is one of the leading international conferences in the fields of robotics, autonomous driving, and AI-based intelligent systems, serving as a platform for presenting the latest research achievements from universities and research institutions worldwide. Due to its rigorous review criteria and high competition rate, the mere acceptance of a paper is considered a significant research achievement in itself.

The paper accepted this time is titled “RayOcc: Occlusion-Agnostic Ray Occupancy Estimation via Gaussian Mixture Intensity,” which proposes a robust ray-based occupancy estimation technique for addressing occlusion problems that arise in complex 3D environments. The research team designed a new framework that utilizes Gaussian Mixture Intensity to effectively estimate spatial occupancy information even when visual information is limited or certain areas are obscured.

This research addresses the problem of 3D spatial understanding—essential for autonomous driving and robotics systems—and demonstrates the technical feasibility of addressing observational uncertainties and occlusion phenomena that frequently occur in real-world environments. In particular, as it can serve as a foundational technology enabling more stable environmental perception even in complex real-world environments, it is expected to make broad contributions to the fields of autonomous driving and intelligent robotics in the future.

This research was conducted at Kookmin University’s CILAB (Computer Intelligence Lab) under the guidance of Professor Lee SeongWon’s research team, with student Kim Jun-ho playing a leading role in all aspects of the project—from research design to implementation and experimentation. This achievement is also significant as it represents a case where an undergraduate student participated throughout the entire research process and secured publication in an international academic conference.

Student Kim Jun-ho said, “I find it very meaningful that the research I participated in as an undergraduate has been recognized at IROS following its acceptance at ICRA,” adding, “Based on my experience spanning from research design to implementation and experimentation, I would like to continue conducting AI research that can contribute to real-world robots and autonomous driving systems.”

Meanwhile, this paper is scheduled to be presented at IROS 2026, to be held in Pittsburgh, USA, in September 2026.

△ (From left) Student Kim Jun-ho, Professor Lee SeongWon, IROS 2026 emblem