The Autonomous Systems and Decision-making (ASDL) Laboratory focuses on developing autonomous agents and improving their sequential decision-making capabilities. Research interests include multi-agent reinforcement learning, representation learning, robot learning, and lifelong learning, with applications to defense systems, smart manufacturing, and complex network systems.

Autonomous Systems and Decision-making (ASDL) 연구실은 자율 에이전트 개발 및 순차적 의사 결정 능력 향상에 중점을 둔다. 주요 연구 분야는 다중 에이전트 강화 학습, 표현 학습, 로봇 학습 및 평생 학습이며, 국방 시스템, 스마트 제조 및 복잡한 네트워크 시스템에 적용된다.

Multi-agent Reinforcement Learning Considering Agent Priority for Weapon-Target Assignment

Weapon–target assignment by reinforcement learning with pointer network

Midcourse guidance strategy for multistage interceptors with coasting phase

Optimal arrangement of missile defense systems considering kill probability

Framework to operate multiple ship defense missiles under uncertain evasive maneuvers of target

Assessment of architectural options for a dual-mode disaster monitoring constellation supported by on-orbit propellant depots

Cross-entropy-based Framework for Preliminary Design of a Multi-stage Interceptor Considering Engagement Boundary

Modeling and Simulation for Effectiveness Analysis of Anti-Ballistic Warfare in Naval Vessels

Remote Version Switching Controller for Identification Friend or Foe Mode-5 Integration Test System

Semantic-aware Wasserstein Policy Regularization for Large Language Model Alignment

AC-Sampler: Accelerate and Correct Diffusion Sampling with Metropolis-Hastings Algorithm

Simulation Analysis of Sensor Placement and Target Interaction in DEVS Formalism

Trajectory-Class-Aware Multi-agent Reinforcement Learning

Noniterative Flight Path Angle Control for Exo-atmospheric Midcourse Guidance

LAGMA: LAtent Goal-guided Multi-agent Reinforcement Learning

DPO-Finetuned Large Multi-Modal Planner with Retrieval-Augmented Generation

Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning

Time-Efficient Weapon-Target Assignment by Actor-Critic Reinforcement

Virtual Impact Point based Midcourse Guidance for Exo-Atmospheric Interception

Optimal Coasting Time Determination of a Multi-stage Interceptor Considering Engagement Zone

Operation of a dual-mode disaster monitoring constellation supported by an on-orbit supply depot

Cost-benefit analysis of a dual-mode satellite constellation with on-orbit servicing depot

Cost-benefit analysis of global disaster monitoring architectures with an on-orbit servicing depot

Study on guidance methods for the minimization of passive seeker’s interference between multiple missiles

Design of the High-Mobility Disaster Monitoring Satellite Constellation Using the Orbiting Depot

Deep Reinforcement Learning-Based Radar-Target Assignment for Enhanced Tracking Accuracy in Multi-Target Environments

Simulation Design of AI-based Weapon-Target Assignment Algorithm for Missile Defense Systems

Estimation of Impact Factors for Missile Interception Probability Improvement in Missile Defense Engagements

Policy gradient-based Reinforcement Learning for Weapon-Target Assignment considering Enhancing Time-Efficiency

Developing Air-to-Air Missile Engagement-Level Simulator with Engineering Detail

Systematic Simulation Design for Battle Experiments in Theater Defense Scenarios

Weapon-Target Assignment for Ballistic Missile Defense Operation considering Battery Allocation

Weapon-Target Assignment by Reinforcement Learning with Attention Mechanism

Optimal Operation Strategy of Thruster Burn-Time Considering Predicted Miss Distance

Bore-sight Antenna Direction Optimization of Multi-function Radar for Target Tracking

Range safety security of Anti-ballistic missile system using MS

Cueing Information System Development for Test and Evaluation of the Anti-Ballistic Missile System

Development of Test System to Test and Evaluate the Ballistic Missile Defense System

A Study on the Method of Calculating Optimal Time of Warhead Detonation

Evaluation and Optimization Framework for the Operation Strategy of Multiple Anti Anti-Ship Missiles

LAGMA: LAtent Goal-guided Multi-Agent Reinforcement Learning

Time-efficient weapon-target assignment by actor-critic reinforcement

Trajectory-Class-Aware Multi-Agent Reinforcement Learning

Optimal coasting time determination of a multi-stage interceptor considering engagement zone

Study on guidance methods for the minimization of passive seeker's interference between multiple missiles

Simulation Analysis on Sensor Placement and Target Interaction in DEVS Formalism

Multi-agent reinforcement learning with semantic embedding and memory-based incentive

Noniterative Flight Path Angle Control for Exo-Atmospheric Midcourse Guidance

Il-Chul Moon

Jaemyung Ahn

SeungBum Hong

Byeonghu Na

Jang Won Bae

Minsang Park

Hyungho Na

Assistant Professor, Department of Industrial Engineering (Joint Appointment with Artificial Intelligence Graduate School)

Autonomous Systems and Decision-making Laboratory (ASDL)

교수님 소개

나형호

연구실 소개

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Multi-agent Reinforcement Learning Considering Agent Priority for Weapon-Target Assignment

Semantic-aware Wasserstein Policy Regularization for Large Language Model Alignment

AC-Sampler: Accelerate and Correct Diffusion Sampling with Metropolis-Hastings Algorithm

연구실 보유 특허

대학별 입시끈

우리 연구실 모집

교수님 소개

나형호

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Multi-agent Reinforcement Learning Considering Agent Priority for Weapon-Target Assignment

Semantic-aware Wasserstein Policy Regularization for Large Language Model Alignment

AC-Sampler: Accelerate and Correct Diffusion Sampling with Metropolis-Hastings Algorithm

연구실 보유 특허

최근 3년간 연구실적 높은 연구실

대학별 입시끈

우리 연구실 모집