Faculty Research Profile
Hyungho Na
학력
· 2025: Ph.D. in Aerospace Engineering, KAIST
· 2013: M.S. in Aerospace Engineering, KAIST
· 2011: B.S. in Aerospace Engineering, KAIST
주요 경력
· 2025~present: Assistant Professor, UNIST
· 2025: Postdoctoral Researcher, KI Robotics, KAIST
· 2019~2021: Senior Researcher, Agency for Defense Development
· 2013~2018: Researcher, Agency for Defense Development
수상/학회/외부활동
· 2025: Global Leadership Awards (Challenge), KAIST
· 2024: Character Scholarship (Merit Category), KAIST
· 2024: Outstanding Champion & Innovation Award, Team AAILAB, Multi-modal Foundation Model meets Embodied AI (MFM-EAI) Workshop, ICML
· 2023: Achievement Award: Theater Defense Research Center, Agency for Defense Development
자율 시스템 및 의사결정 연구실
Autonomous Systems and Decision-making Lab
AI 대전환 시대에, 제조, 금융, 국방, 항공우주 등 다양한 분야에서 인공지능을 융합하여 자율적 의사결정 능력을 강화하려는 연구가 활발히 이루어지고 있습니다. 이러한 흐름 속에서 자율 시스템 및 의사결정 연구실은 자율시스템의 개발과 의사결정 능력의 고도화를 목표로 하고 있습니다. 우리 연구실은 강화 학습, 다중 에이전트 강화 학습, 표현 학습, 로봇 학습, 지속 학습 등 인공지능 기초 연구뿐만 아니라 국방 시스템, 스마트 제조, 복잡 네트워크 시스템 에 적용을 위한 인공지능 응용 연구를 함께 수행합니다.
In this era of AI transformation, a wide range of research is actively integrating AI into domains such as manufacturing, finance, defense, and aerospace, with a strong focus on autonomous decision-making. Within this trend, ASDL aims to develop autonomous systems and enhance decision-making capabilities across diverse domains. Our lab conducts research in both AI foundations (e.g., reinforcement learning, multi-agent reinforcement learning, representation learning, robot learning, and lifelong learning) and AI applications (e.g., defense systems, smart manufacturing, and complex network systems)
In this era of AI transformation, a wide range of research is actively integrating AI into domains such as manufacturing, finance, defense, and aerospace, with a strong focus on autonomous decision-making. Within this trend, ASDL aims to develop autonomous systems and enhance decision-making capabilities across diverse domains. Our lab conducts research in both AI foundations (e.g., reinforcement learning, multi-agent reinforcement learning, representation learning, robot learning, and lifelong learning) and AI applications (e.g., defense systems, smart manufacturing, and complex network systems)
연구분야
강화 학습, 다중 에이전트 시스템, AI 기반 의사결정, 자율 시스템 및 운용 / Reinforcement Learning, Multi-Agent Systems, AI-based Decision-Making, Autonomous Systems and Operations
Reinforcement Learning, Multi-Agent Systems, AI-based Decision-Making, Autonomous Systems and Operations
연구 희망분야
로봇 학습, 피지컬 인공지능, 자율 협동 시스템 / Robot Learning, Physical AI, Autonomous Cooperative Systems
Robot Learning, Physical AI, Autonomous Cooperative Systems
연구주제
강화 학습, 다중 에이전트 시스템, 표현 학습, 지속 학습, 샘플 효율적 학습, 로봇 학습, 대규모 언어모델 미세조정, 순차적 의사결정, 임무 계획 및 수행, AI 기반 국방 시스템, 복잡 네트워크 시스템을 위한 AI 기반 운용 최적화, 유도 및 제어, 복잡 시스템 최적화
Reinforcement Learning, Multi-agent Systems, Representation learning, Lifelong Learning, Sample Efficient Training, Robot Learning, LLM Finetuning, Sequential Decision-making, Mission Planning and Execution, AI-Transformed Defense Systems, AI-Enhanced Operations for Complex Network Systems, Guidance and Control, Optimization for Complex Systems
Reinforcement Learning, Multi-agent Systems, Representation learning, Lifelong Learning, Sample Efficient Training, Robot Learning, LLM Finetuning, Sequential Decision-making, Mission Planning and Execution, AI-Transformed Defense Systems, AI-Enhanced Operations for Complex Network Systems, Guidance and Control, Optimization for Complex Systems
국가연구개발사업 기술 분류체계
국가과학기술표준분류
EE. 정보/통신 > EE01. 정보이론 > EE0108. 인공지능
논문
· LAGMA: LAtent Goal-guided Multi-agent Reinforcement Learning, Proceedings of the forty-first International Conference on Machine Learning (ICML), Hyungho Na and Il-Chul Moon, (2024.07)
· Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning,The Twelfth International Conference on Learning Representations (ICLR) (Oral Presentation [Top 1.2 %]), Hyungho Na, Yunkyeong Seo, and Il-Chul Moon, (2024.05)
· Weapon–target assignment by reinforcement learning with pointer network, Journal of Aerospace Information Systems, 20(1), pp.53-59, Hyungho Na, Jaemyung Ahn, and Il-Chul Moon, (2023.01)
특허
[Domestic] System and Method for Ballistic Missile Engagement Simulation Using Simulated Cueing Information, Hyungho Na, Kyoung-Rok Song, Namsoo Park, and Jin-Ik Lee, (2018.04)
[Domestic] Method and Apparatus to Determine the Predicted Intercept Point of a Weaving Target, Insung Hwang, Lynn Huh, and Hyungho Na, (2018.01)