ChangHwan Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
ChangHwan Kim has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
- Bum-Jae You
Korea Institute of Science and Technology (KIST) Hwarang-ro 14-gil 5 Seoungbuk-gu 02792 Seoul South Korea
4 shared publications - Changjoo Nam
Department of Electronic Engineering, Sogang University, Seoul, South Korea
3 shared publications - Jinhwi Lee
Korea Institute of Science and Technology, Seoul, South Korea
3 shared publications - Jong Hyeon Park
School of Mechanical Engineering, Hanyang University, Seoul 04763, Republic of Korea
3 shared publications - Nak Young Chong
Japan Advanced Institute of Science and Technology
3 shared publications - Yoonseob Lim
Intelligence and Interaction Research Center, Korea Institute of Science and Technology, Seoul, Korea
3 shared publications
Latest Publications
- Open Access
- 28 June 2026
- Published by Korean Academy of Speech-Language Pathology and Audiology in Communication Sciences & Disorders
- Vol. 31 (2) , 401-413
Comparing Discourse Production and Conversational Engagement in Older Adults across Robot- and Tablet-Assisted Conversational Agents
Objectives: Discourse assessments are widely used in clinical settings to identify cognitive and linguistic impairments associated with normal aging and neurogenic communication disorders. Because richer spontaneous speech facilitates more reliable discourse analysis, effective methods for eliciting naturalistic language are needed. As the social roles of robots expand, their potential as tools for language and cognitive assessment has gained increasing attention. This study examined whether a conversational robot elicits greater discourse production and conversational engagement in older adults compared to a tablet and explored the clinical usability of robots as tools for discourse-based assessment. Methods: Fourteen healthy older adults participated in unstructured conversations on three daily topics with both a robot and a tablet. The robot incorporated non-verbal backchannel behaviors, such as nodding and facial expressions, and interacted with older adults using the ChatGPT model, while the tablet offered only verbal communication. Five linguistic measures were analyzed, including turn-taking frequency, total and mean utterances, and total and mean speech duration. Following each condition, participants completed a selfreport survey assessing usability and interaction experience. Results: Results showed that older adults produced significantly more total and mean utterances when interacting with the robot. Additionally, participants reported a greater sense of encouragement to engage with the robot. Conclusion: These findings suggest that the robot’s physical embodiment and interactive behaviors enhance conversational engagement, making it a clinically promising tool for eliciting spontaneous speech and collecting discourse data for language and cognitive assessment in aging populations.
- 28 June 2026
- Published by Korean Academy of Speech-Language Pathology and Audiology in Communication Sciences & Disorders
- Vol. 31 (2) , 401-413
Open AccessComparing Discourse Production and Conversational Engagement in Older Adults across Robot- and Tablet-Assisted Conversational Agents
Objectives: Discourse assessments are widely used in clinical settings to identify cognitive and linguistic impairments associated with normal aging and neurogenic communication disorders. Because richer spontaneous speech facilitates more reliable discourse analysis, effective methods for eliciting naturalistic language are needed. As the social roles of robots expand, their potential as tools for language and cognitive assessment has gained increasing attention. This study examined whether a conversational robot elicits greater discourse production and conversational engagement in older adults compared to a tablet and explored the clinical usability of robots as tools for discourse-based assessment. Methods: Fourteen healthy older adults participated in unstructured conversations on three daily topics with both a robot and a tablet. The robot incorporated non-verbal backchannel behaviors, such as nodding and facial expressions, and interacted with older adults using the ChatGPT model, while the tablet offered only verbal communication. Five linguistic measures were analyzed, including turn-taking frequency, total and mean utterances, and total and mean speech duration. Following each condition, participants completed a selfreport survey assessing usability and interaction experience. Results: Results showed that older adults produced significantly more total and mean utterances when interacting with the robot. Additionally, participants reported a greater sense of encouragement to engage with the robot. Conclusion: These findings suggest that the robot’s physical embodiment and interactive behaviors enhance conversational engagement, making it a clinically promising tool for eliciting spontaneous speech and collecting discourse data for language and cognitive assessment in aging populations.
- 7 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. PP (15513203) , 1-12
A Scalable Framework for Lifelong Multiagent Path Finding With Asynchronous Actions
Lifelong multiagent path finding (LMAPF) requires continuous task assignment and collision-free path planning for large robot fleets. However, existing LMAPF methods assume synchronous unit-time actions, whereas real robots execute movements asynchronously with nonuniform durations. This mismatch can lead to execution-time collisions and makes frequent replanning challenging in large-scale systems. We study LMAPF with asynchronous actions and present a framework that ensures safety under asynchronous execution and real-time scalability through coordinated path planning and action scheduling, complemented by a simple greedy task allocation. To ensure safety, the path planner eliminates cycle conflicts to prevent structural deadlocks, while a lightweight action scheduler enforces vertex precedence during execution, resolving following conflicts without explicit temporal modeling. To achieve real-time performance, the planner performs partial replanning by reusing the residual paths of nonidle agents, which are converted into a synchronous form through the scheduler’s path resynchronization, enabling consistent and efficient replanning. Experiments in warehouse environments with up to 1000 robots demonstrate that our framework more than doubles throughput compared with state-of-the-art LMAPF methods, while maintaining safe operations under asynchronous actions.
- 7 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. PP (15513203) , 1-12
A Scalable Framework for Lifelong Multiagent Path Finding With Asynchronous Actions
Lifelong multiagent path finding (LMAPF) requires continuous task assignment and collision-free path planning for large robot fleets. However, existing LMAPF methods assume synchronous unit-time actions, whereas real robots execute movements asynchronously with nonuniform durations. This mismatch can lead to execution-time collisions and makes frequent replanning challenging in large-scale systems. We study LMAPF with asynchronous actions and present a framework that ensures safety under asynchronous execution and real-time scalability through coordinated path planning and action scheduling, complemented by a simple greedy task allocation. To ensure safety, the path planner eliminates cycle conflicts to prevent structural deadlocks, while a lightweight action scheduler enforces vertex precedence during execution, resolving following conflicts without explicit temporal modeling. To achieve real-time performance, the planner performs partial replanning by reusing the residual paths of nonidle agents, which are converted into a synchronous form through the scheduler’s path resynchronization, enabling consistent and efficient replanning. Experiments in warehouse environments with up to 1000 robots demonstrate that our framework more than doubles throughput compared with state-of-the-art LMAPF methods, while maintaining safe operations under asynchronous actions.
- Open Access
- 11 June 2025
- Published by Elsevier in Robotics and Autonomous Systems
- Vol. 193
Task and Motion Planning for grasping targets with object rearrangement in confined workspaces
- 11 June 2025
- Published by Elsevier in Robotics and Autonomous Systems
- Vol. 193
Open AccessTask and Motion Planning for grasping targets with object rearrangement in confined workspaces
- 10 February 2025
- Published by Springer Nature in International Journal of Social Robotics
- Vol. 17 (5) , 871-881
Affective State Generation, Transition and Facial Expression for a Social Robot Using Texts and Personality Traits
- 10 February 2025
- Published by Springer Nature in International Journal of Social Robotics
- Vol. 17 (5) , 871-881
Affective State Generation, Transition and Facial Expression for a Social Robot Using Texts and Personality Traits
- 3 December 2023
- Published by Springer Nature
- p. 264-275
Explorative Study on the Non-verbal Backchannel Prediction Model for Human-Robot Interaction
- 3 December 2023
- Published by Springer Nature
- p. 264-275
Explorative Study on the Non-verbal Backchannel Prediction Model for Human-Robot Interaction
- Open Access
Improving Korean NLP Tasks with Linguistically Informed Subword Tokenization and Sub-character Decomposition
We introduce a morpheme-aware subword tokenization method that utilizes sub-character decomposition to address the challenges of applying Byte Pair Encoding (BPE) to Korean, a language characterized by its rich morphology and unique writing system. Our approach balances linguistic accuracy with computational efficiency in Pre-trained Language Models (PLMs). Our evaluations show that this technique achieves good performances overall, notably improving results in the syntactic task of NIKL-CoLA. This suggests that integrating morpheme type information can enhance language models' syntactic and semantic capabilities, indicating that adopting more linguistic insights can further improve performance beyond standard morphological analysis.
Open AccessImproving Korean NLP Tasks with Linguistically Informed Subword Tokenization and Sub-character Decomposition
We introduce a morpheme-aware subword tokenization method that utilizes sub-character decomposition to address the challenges of applying Byte Pair Encoding (BPE) to Korean, a language characterized by its rich morphology and unique writing system. Our approach balances linguistic accuracy with computational efficiency in Pre-trained Language Models (PLMs). Our evaluations show that this technique achieves good performances overall, notably improving results in the syntactic task of NIKL-CoLA. This suggests that integrating morpheme type information can enhance language models' syntactic and semantic capabilities, indicating that adopting more linguistic insights can further improve performance beyond standard morphological analysis.
- Open Access
- 26 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 134899-134911
Local and Global Search-Based Planning for Object Rearrangement in Clutter
We propose two algorithms based on local and global searches for a Task and Motion Planning (TAMP) problem, which considers a robotic manipulator to rearrange obstacles and grasp a target in clutter. In the problem, no collision-free path for a robotic manipulator is available unless some obstacles blocking a target are relocated. The two algorithms determine the sequence of obstacles to be removed for grasping a target without collisions. The local search algorithm determines the sequence quickly in an online manner but could be suboptimal in the number of removed obstacles. The global search algorithm based on tree search needs upfront computation but runs in polynomial time. In numerical simulation settings, we consider objects in various shapes, which could make reachable directions bounded. From the simulations the planning time of local search algorithm is faster than that of global search, whereas the global search algorithm removes the less number of obstacles than the local search. In addition, we show that the global search algorithm with a heuristic cost is faster than without the cost but the minimum number of removed obstacles is still obtained from the global search algorithm without the heuristic cost. Practical experiments show the applicability of our algorithms in real environments.
- 26 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 134899-134911
Open AccessLocal and Global Search-Based Planning for Object Rearrangement in Clutter
We propose two algorithms based on local and global searches for a Task and Motion Planning (TAMP) problem, which considers a robotic manipulator to rearrange obstacles and grasp a target in clutter. In the problem, no collision-free path for a robotic manipulator is available unless some obstacles blocking a target are relocated. The two algorithms determine the sequence of obstacles to be removed for grasping a target without collisions. The local search algorithm determines the sequence quickly in an online manner but could be suboptimal in the number of removed obstacles. The global search algorithm based on tree search needs upfront computation but runs in polynomial time. In numerical simulation settings, we consider objects in various shapes, which could make reachable directions bounded. From the simulations the planning time of local search algorithm is faster than that of global search, whereas the global search algorithm removes the less number of obstacles than the local search. In addition, we show that the global search algorithm with a heuristic cost is faster than without the cost but the minimum number of removed obstacles is still obtained from the global search algorithm without the heuristic cost. Practical experiments show the applicability of our algorithms in real environments.
- 24 September 2022
- Published by Springer Nature in Intelligent Service Robotics
- Vol. 15 (5) , 649-660
High dimensional object rearrangement for a robot manipulation in highly dense configurations
- 24 September 2022
- Published by Springer Nature in Intelligent Service Robotics
- Vol. 15 (5) , 649-660
High dimensional object rearrangement for a robot manipulation in highly dense configurations
- 11 August 2021
- Published by Springer Nature in Intelligent Service Robotics
- Vol. 14 (4) , 549-561
Obstacle rearrangement for robotic manipulation in clutter using a deep Q-network
- 11 August 2021
- Published by Springer Nature in Intelligent Service Robotics
- Vol. 14 (4) , 549-561
Obstacle rearrangement for robotic manipulation in clutter using a deep Q-network
- Open Access
Fast and resilient manipulation planning for target retrieval in clutter
This paper presents a task and motion planning (TAMP) framework for a robotic manipulator in order to retrieve a target object from clutter. We consider a configuration of objects in a confined space with a high density so no collision-free path to the target exists. The robot must relocate some objects to retrieve the target without collisions. For fast completion of object rearrangement, the robot aims to optimize the number of pick-and-place actions which often determines the efficiency of a TAMP framework. We propose a task planner incorporating motion planning to generate executable plans which aims to minimize the number of pick-and-place actions. In addition to fully known and static environments, our method can deal with uncertain and dynamic situations incurred by occluded views. Our method is shown to reduce the number of pick-and-place actions compared to baseline methods (e.g., at least 28.0% of reduction in a known static environment with 20 objects).
Open AccessFast and resilient manipulation planning for target retrieval in clutter
This paper presents a task and motion planning (TAMP) framework for a robotic manipulator in order to retrieve a target object from clutter. We consider a configuration of objects in a confined space with a high density so no collision-free path to the target exists. The robot must relocate some objects to retrieve the target without collisions. For fast completion of object rearrangement, the robot aims to optimize the number of pick-and-place actions which often determines the efficiency of a TAMP framework. We propose a task planner incorporating motion planning to generate executable plans which aims to minimize the number of pick-and-place actions. In addition to fully known and static environments, our method can deal with uncertain and dynamic situations incurred by occluded views. Our method is shown to reduce the number of pick-and-place actions compared to baseline methods (e.g., at least 28.0% of reduction in a known static environment with 20 objects).