Hello, I'm Jeongeun Park

I am a Ph.D student at Korea Unversity, where I work with Sungjoon Choi on artificial inteligence and robotics. During Ph.D, I have also spent time at NAVER AI Lab (Korea) and Ingenuity Labs (Canada).

I am particularly interested in the intersection of interactive agents and robotics, especially how foundation models can enhance the natural interaction between humans and robots. My goal is to explore how foundation models can enhance the personality, motion, and contextual understanding of these characters, making their behavior more lifelike and responsive.

Scholar Github Linkedin

News

  • [July 2024]: Our paper about persona-driven human robot interaction Robotics and Automation letters! We are looking forward to presenting our work at ICRA 2025.
  • [May 2024]: Our paper about socially aware navigation has been accepted to RO-MAN 2024.
  • [April 2024 - October 2024]: I have started internship at NAVER Cloud, AI Lab.
  • [January 2024]: Our paper about semi-autonomous teleoperation with physical simulators and large language models has been accepted to ICRA 2024!
  • [November 2023]: Our paper about uncertainty estimation from large language models has been accepted to Robotics and Automation letters! We are looking forward to presenting our work at ICRA 2024.
  • [Feburary 2023]: I am presenting our work about vision-based navigation at NAVER Tech Talk.
  • [January 2023]: Our paper about active visual search has been accepted to ICRA 2023.
  • [September 2022 - December 2022]: I am heading to Queens University, Canada as visiting researcher, advised by Matthew Pan. This program is funded by Mitacs Globalink Research Award to Canada.
  • [May 2023]: Our paper about abnormal driving dataset has been accepted to IROS 2022.
  • [January 2022]: Our paper about semi-autonomous teleoperation for non-prehensile manipulations has been accepted to ICRA 2022.

Publications

Versatile Motion-Language Models for Multi-Turn Interactive Agents

VIM: Versatile Motion-Language Models for Multi-Turn Interactive Agents

Jeongeun Park, Sungjoon Choi, Sangdoo Yun

VIM (Versatile Interactive Motion language model) integrates language and motion modalities to understand, generate, and control interactive motions in multi-turn conversations, addressing the scarcity of multi-turn interactive motion data with a synthetic dataset, INTER-MT2.

Project Page PDF arXiv
Towards Embedding Dynamic Personas in Interactive Robots: Masquerading Animated Social Kinematics (MASK)

Towards Embedding Dynamic Personas in Interactive Robots: Masquerading Animated Social Kinematics (MASK)

Jeongeun Park, Taemoon Jeong, Hyeongsung Kim, Taehyun Byun, Seungyoon Shin, Keunjoon Choi, Jaewoon Kwon, Taeyoon Lee, Matthew Pan, Sungjoon Choi
Robotics and Automation Letters, 2024
International Conference of Robotics and Automation (ICRA), 2025

Employing a persona-driven interactive framework to animate an anthropomorphic robotic system, enhancing audience engagement through non-verbal interactions

Project Page PDF arXiv
SPOTS: Stable Placement of Objects with Reasoning in Semi-Autonomous Teleoperation Systems

SPOTS: Stable Placement of Objects with Reasoning in Semi-Autonomous Teleoperation Systems

Joonhyung Lee, Sangbeom Park, Jeongeun Park, Kyungjae Lee, Sungjoon Choi
International Conference of Robotics and Automation (ICRA), 2024

Introducing a teleoperation framework that enhances the 'place' task in robotics by combining simulation-driven stability verification with semantic reasoning from large language models.

Project Page PDF arXiv
CLARA: Classifying and Disambiguating User Commands for Reliable Interactive Robotic Agents

CLARA: Classifying and Disambiguating User Commands for Reliable Interactive Robotic Agents

Jeongeun Park, Seungwon Lim, Joonhyung Lee, Sangbeom Park, Minsuk Chang, Youngjae Yu, Sungjoon Choi
Robotics and Automation Letters (RA-L), 2024,
International Conference of Robotics and Automation (ICRA), 2024

Introducing a method for interactive robotic agents using large language models (LLMs) to classify user commands as clear, ambiguous, or infeasible, enhancing reliability by leveraging uncertainty estimation, situational awareness, and user interaction for disambiguation.

Project Page PDF arXiv
SOCRATES: Text-based Human Search and Approach using a Robot Dog

Text-based Human Search and Approach using a Robot Dog

Jeongeun Park, Jefferson Silveira, Matthew Pan, Sungjoon Choi
International Conference on Robot and Human Interactive Communication (RO-MAN), 2024.

A robotic system using textual descriptions for human search and approach, combining language models for identifying targets and a hybrid learning framework for generating human-friendly robotic motions

Project Page PDF arXiv
Zero-shot Active Visual Search (ZAVIS): Intelligent Object Search for Robotic Assistants

Zero-shot Active Visual Search (ZAVIS): Intelligent Object Search for Robotic Assistants

Jeongeun Park, Taerim Yoon, Jejoon Hong, Youngjae Yu, Matthew Pan, Sungjoon Choi
International Conference of Robotics and Automation (ICRA), 2023

A mobile robot system that uses free-form text for target object search using commonsene knowledge.

Project Page PDF arXiv
Elucidating Robust Learning with Uncertainty-Aware Corruption Pattern Estimation

Elucidating Robust Learning with Uncertainty-Aware Corruption Pattern Estimation

Jeongeun Park, Seungyoon Shin, Sangheum Hwang, Sungjoon Choi
Pattern Recognition, 2023

Uncertainty-aware robust learning

Code PDF
Towards Defensive Autonomous Driving: Collecting and Probing Driving Demonstrations of Mixed Qualities

Towards Defensive Autonomous Driving: Collecting and Probing Driving Demonstrations of Mixed Qualities

Jeongwoo Oh, Gunmin Lee, Jeongeun Park, Wooseok Oh, Jaeseok Heo, Hojun Chung, DoHyung Kim, Byungkyu Park, ChangGun Lee, Sungjoon Choi Songhwai Oh
The 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022

R3 Driving Dataset, a novel collection of driving data categorizing abnormal behaviors to enhance OOD detection for autonomous driving.

Project Page PDF Dataset Code
Learning Robot Structure and Motion Embeddings using Graph Neural Networks

Learning Robot Structure and Motion Embeddings using Graph Neural Networks

J. Taery Kim, Jeongeun Park, Sungjoon Choi, Sehoon Ha
ICML 2022 Workshop on Machine Learning for Computational Design (ICML'22-ML4CompDesign), 2022

Using graph neural networks (GNN) to find compact, low-dimensional embeddings of a robot’s kinematic structure and pose data.

Project Page PDF
Semi-Autonomous Teleoperation via Learning Non-Prehensile Manipulation Skills

Semi-Autonomous Teleoperation via Learning Non-Prehensile Manipulation Skills

Sangbeom Park, Yoonbyung Chai, Sunghyun Park, Jeongeun Park, Kyungjae Lee, Sungjoon Choi
The 2022 IEEE Conference of Robotics and Automation (ICRA), 2022

Semi-Autonomous Teleoperation framework for non-prehensile manipulation tasks.

PDF

Reviewing activities