Yunwoo Lee

I am a Tenure-track Assistant Professor at DGIST EECS, South Korea. Before joining DGIST, I was a Postdoctoral Fellow at Carnegie Mellon University Robotics Institute (CMU RI), where I work with Prof. Sebastian Scherer in AirLab. I did my Ph.D. from Seoul National University (SNU) under the supervision of Prof. H. Jin Kim. One of my work received 2025 IEEE T-ASE Best New Application Paper Award at ICRA 2026.

Email  /  CV  /  Scholar  / 

Research

I'm interested in Multi-Robot Autonomy, Motion Generation, and, Robotic Applications.

This work introduces SCOPE, a field-of-view-aware planner that certifies the robot’s full safety volume before execution, enabling safe goal-directed navigation in unknown 3D environments.

This paper presents a asynchronous&distributed multi-robot trajectory planning framework that enables deadlock-free and collision-free quadrotor swarm with no communication during flight.

This paper presents a asynchronous&distributed multi-robot trajectory planning framework that enables deadlock-free and collision-free quadrotor swarm with no communication during flight.

This paper presents a distributed trajectory planning method for multi-agent aerial tracking that enables collision-free and occlusion-aware tracking of a moving target in challenging environments.

This paper presents a decentralized trajectory planning method for quadrotor swarms that enables collision-free navigation in cluttered environments while guaranteeing convergence to assigned goals.

This paper presents a versatile aerial target tracking framework using Bernstein polynomial motion primitives for fast, collision-free, and occlusion-aware tracking in complex environments with dynamic obstacles and multiple targets.

This paper presents a monocular-camera-only target chasing framework for drones that leverages cross-modal learning to enable robust target tracking and navigation in dense environments.

This paper presents a distributed multi-agent trajectory planning method using linear safe corridors for collision-free navigation in maze-like dynamic environments.

This paper presents an autonomous aerial dual-target following framework that enables a drone to track two moving targets while handling obstacles, limited field of view, and inter-target occlusions.

This paper presents a polynomial trajectory planning method for MAV teams that maintains continuous target visibility.

This paper presents a method for collaborative monocular SLAM using rendezvous strategies.

This paper presents a navigation-assistant path planning method in which a supporting MAV actively plans its path to improve the localization and navigation performance of a main MAV.

This paper presents an integrated motion planning framework for autonomous aerial videography that combines target motion prediction with visibility-aware trajectory planning to safely follow a moving target in dense environments.