Minsu (Max) Chang, Ph.D. | Research Engineer vCard

About Minsu (Max) Chang, Ph.D.

Robotics Research Engineer (Ph.D.) at Samsung Electronics, SAIT specializing in multi-agent orchestration for Spatial Intelligence, Physical AI, and robotic Task and Motion Planning (TAMP) with foundation models (Gemini Robotics-ER and Gemini 4 Argon).

1st-Place Winner at the Google Gemini 3 Seoul Hackathon 2026 (GeminiSpace), first author at IEEE ICRA 2025 (OPPA) and IEEE TNSRE (AI Therapist), and co-developer of the KFDA-certified lower-limb rehabilitation exoskeleton SUBAR deployed across 6 clinical hospitals.

1st Place
Google Gemini 3
Seoul Hackathon 2026
20 Papers
Publications
ICRA, IEEE TNSRE, JKROS
14 Patents
10 US + 4 KR
AMR, Lab Auto & Exoskeletons
6 Hospitals
KFDA Certified
SUBAR Exoskeleton

Core Research & Engineering Skills

Multi-Agent Orchestration (Gemini Robotics-ER & 4 Argon) Spatial Intelligence & 3D Semantic Grounding Physical AI & Task and Motion Planning (TAMP) NVIDIA Isaac Sim & MuJoCo ROS 2 / MoveIt 2 & Bidirectional Motion Planning Autonomous Mobile Robot Navigation (ICRA OPPA) Nonlinear / Adaptive Impedance Control & HRI Python • C/C++ • MATLAB/Simulink

Research Focus

  • Multi-Agent TAMP & Physical AI

    Closed-loop multi-manipulator task and motion planning in NVIDIA Isaac Sim & ROS 2 orchestrated by Gemini Robotics-ER 2 and Gemini 4 Argon.

  • Spatial Intelligence & Mobile Navigation

    Indoor 2D/3D semantic mapping (GeminiSpace, 1st Place Gemini 3 Hackathon) and online planner parameter adaptation for mobile robots (ICRA 2025 OPPA).

  • Autonomous Lab & Industrial Robotics (SAIT)

    Learning-based bidirectional motion planning (JKROS 2026), safety-margin adaptation, and automated material synthesis systems (10 US Patents).

  • Rehabilitation Exoskeletons & Physical HRI

    KFDA-certified lower-limb exoskeleton SUBAR (6 hospitals), adaptive impedance control, and clinical AI Therapist verbal-cue systems (IEEE TNSRE).

Curriculum Vitae

Professional Research Experience

  1. Staff / Senior Robotics Research Engineer

    2022 — Present
    Samsung Electronics, SAIT (Samsung Advanced Institute of Technology)
    • Autonomous Mobile Navigation & Motion Planning: First author of IEEE ICRA 2025 (OPPA) on online planner parameter adaptation and co-author of JKROS 2026 on learning-based bidirectional motion planning.
    • Spatial Intelligence & Multi-Agent TAMP with Gemini: 1st-Place Winner at Google Gemini 3 Seoul Hackathon 2026 (GeminiSpace); architected multi-agent multi-robot manipulation and React Flow digital twins in NVIDIA Isaac Sim & ROS 2 using Gemini Robotics-ER 2 and Gemini 4 Argon.
    • Autonomous Lab Automation & 10 US Patents: Inventor on granted patent US 12,411,092 B2 and 9 US Patent Applications (`19/305,009`, `19/249,393`, `19/233,597`, `19/068,604`, `19/041,483`, `18/989,808`, `18/968,676`, `18/908,258`, `18/885,072`) across robot path planning, safety-margin control, powder-dispensing manipulation, and material synthesis platforms.

  2. Rehabilitation Robotics Researcher

    2016 — 2022
    Sogang University — Robotics & Control Laboratory (Seoul, Korea)
    • KFDA-Certified Exoskeleton (SUBAR) & Clinical Deployment: Led hardware development and nonlinear/adaptive impedance control for lower-limb rehabilitation exoskeletons, securing KFDA medical device certification and deploying across 6 Korean hospitals.
    • AI Therapist & Smart Prosthetic Control: First author of two IEEE TNSRE journal papers (AI Therapist 2020; Smart Prosthetic Ankle Fuzzy Logic 2019), IEEE BioRob 2020, and IEEE ICORR 2017 (HAT postural stability model).
    • 4 Registered Korean Patents: Inventor on KR 10-2262191, KR 10-2218260, KR 10-2132113, and KR 10-1940901 covering gait rehabilitation actuation and exoskeleton stabilization control.

Education

  1. Ph.D. in Mechanical Engineering (Robotics & Control)

    2018 — 2022
    Sogang University, Seoul, Republic of Korea
    • Research on clinical AI therapists, assist-as-needed impedance control, and human-exoskeleton interaction.

  2. M.S. in Mechanical Engineering

    2016 — 2018
    Sogang University, Seoul, Republic of Korea
    • Thesis: An assist-as-needed control method of a lower limb exoskeletal robot for active gait training (Best Presentation Award, ICCAS 2017).

  3. B.S. in Mechanical Engineering

    2010 — 2016
    Sogang University, Seoul, Republic of Korea

Core Technical Competencies

Spatial Intelligence, Physical AI & Multi-Agent TAMP (Gemini)96%
ROS 2, MoveIt 2, NVIDIA Isaac Sim & Motion Planning95%
Nonlinear, Adaptive Impedance & Exoskeleton Control96%
Autonomous Mobile Robot Navigation & Lab Automation95%

Robotics & Spatial AI Portfolio

01 • 1st Place Gemini 3 HackathonGeminiSpace Spatial AI
Spatial Intelligence • Google Hackathon 1st Place

GeminiSpace: Indoor 2D/3D Semantic Spatial Navigation

1st-Place Winner at Google Gemini 3 Seoul Hackathon 2026 (among 111 finalists / 1,500+ applicants). Transforms indoor photos into an interactive semantic navigation map.

Gemini 3Spatial IntelligenceSemantic Map
02 • 3-Arm FR3 TAMPGemini Robotics ER-2 vs Gemini 4 Argon
Physical AI & Multi-Agent TAMP

Gemini Robotics-ER 2 vs. Gemini 4 Argon: Multi-Robot Task Planner Benchmark

Side-by-side 3-arm Franka FR3 9-block tower assembly in NVIDIA Isaac Sim 6.0 & ROS 2 Jazzy using software-pipelined 10-turn scheduling and symbolic 3D /tf grounding.

Gemini Robotics-ER 2Gemini 4 ArgonIsaac Sim 6.0ROS 2
03 • EP 12 Multi-RobotEP 12 Multi Robot Collaboration
Multi-Robot Manipulation

EP 12. Multi-Robot Collaboration with Gemini Robotics-ER 2 & Isaac Sim

Three Franka FR3 robotic arms cooperatively constructing geometric formations in Isaac Sim with React Flow DAG orchestration and VLA execution.

3x Franka FR3React Flow DAGIsaac Sim
04 • EP 11 Digital TwinEP 11 FR3 React Flow Digital Twin
Digital Twin & TAMP

EP 11. Cooperative FR3 Manipulation & React Flow Digital Twin

Closed-loop multi-robot task planning and real-time React Flow digital twin synchronization in NVIDIA Isaac Sim and ROS 2.

Gemini Robotics-ER 2Digital TwinROS 2
05 • EP 10 VLA ControlEP 10 Natural Language VLA
Vision-Language-Action (VLA)

EP 10. Natural Language to Multi-Robot Execution in Isaac Sim & ROS 2

End-to-end VLA multi-robot control framework translating natural-language commands into collision-free multi-arm trajectories.

VLAIsaac SimROS 2
06 • Imitation LearningMuJoCo robomimic Imitation Learning
Robot Learning & Manipulation

Imitation Learning Manipulation Policy in MuJoCo & robomimic

Demonstration-driven robotic manipulation policy training and physics evaluation in MuJoCo simulation.

MuJoCorobomimicImitation Learning
07 • Autonomous Mobile NavBARN Benchmark Path Planning
Mobile Robot Navigation (ICRA OPPA)

BARN Benchmark Autonomous Navigation & Dynamic Obstacle Avoidance

High-speed mobile robot path planning and online parameter adaptation across dense obstacle environments.

ICRA 2025 OPPABARN BenchmarkROS Nav
08 • IEEE TNSREAI Therapist IEEE TNSRE
Clinical Rehabilitation Robotics

AI Therapist: Expert Verbal Cues for Robot-Assisted Gait Training

Clinical gait rehabilitation exoskeleton system emulating expert physical therapist verbal cues and adaptive parameters (IEEE TNSRE 2020).

IEEE TNSREAI TherapistPhysical HRI
09 • KFDA ExoskeletonVR Lower Limb Exoskeleton
Wearable Medical Robotics

VR-Integrated Lower-Limb Exoskeleton (SUBAR)

KFDA-certified lower-limb exoskeleton synchronized with immersive VR biofeedback and deployed across 6 hospitals.

KFDA CertifiedSUBARVR Biofeedback
10 • Adaptive ImpedanceAdaptive Impedance Control Exoskeleton
Nonlinear & Impedance Control

Assist-as-Needed Adaptive Impedance Exoskeleton Control

Task-oriented lower-limb rehabilitation control using virtual spring-damper tunnels and reinforcement learning impedance adaptation.

Impedance ControlAssist-as-NeededExoskeleton

Research Publications (20) & Patents (14)

Frontier Journals & Flagship IEEE Conferences (Highlighted)

ICRA 2025
★ Flagship IEEE Conf · 1st AuthorOPPA: Online Planner's Parameter Adaptation for Enhanced Mobile Robot Navigation
M. Chang, J. Jang, D. Han, W. Choi, S. Kim, H. Park, H. Choi • IEEE International Conference on Robotics and Automation (ICRA), pp. 3861–3867, Atlanta, USA, 2025
IEEE ↗
TNSRE 2020
★ Frontier IEEE Journal · 1st AuthorAI Therapist realizing Expert Verbal Cues for Effective Robot-Assisted Gait Training
M. Chang, T.W. Kim, J. Beom, S. Won, D. Jeon • IEEE Transactions on Neural Systems and Rehabilitation Engineering (TNSRE), Vol. 28, No. 12, 2020
IEEE ↗
TNSRE 2019
★ Frontier IEEE Journal · 1st AuthorResearch on Terrain Identification of the Smart Prosthetic Ankle by Fuzzy Logic
M. Chang, K. Kim, D. Jeon • IEEE Transactions on Neural Systems and Rehabilitation Engineering (TNSRE), Vol. 27, No. 9, 2019
IEEE ↗
JKROS 2026
★ Robotics Journal · 2026Learning-Based Sampling Strategies Leveraging Bidirectional Motion Planning Characteristics
S. Jeon, M. Kim, J. Jang, M. Chang, J. Park • The Journal of Korea Robotics Society (JKROS), Vol. 21, No. 2, pp. 164–171, 2026
Scholar ↗
BioRob 2020
★ Flagship IEEE Conf · 1st AuthorDevelopment of the AI therapist estimating the Borg scale of stroke patients in robot-assisted gait training
M. Chang, D. Jeon • IEEE RAS/EMBS Int. Conf. on Biomedical Robotics and Biomechatronics (BioRob), New York, 2020
Scholar ↗
ICORR 2017
★ Flagship IEEE Conf · 1st AuthorA research on the postural stability of a person wearing the lower limb exoskeletal robot by the HAT model
M. Chang, Y. Kim, Y. Lee, D. Jeon • IEEE International Conference on Rehabilitation Robotics (ICORR), pp. 369–374, London, 2017
IEEE ↗
SCIE 2019
★ SCIE JournalPrecise flowrate control of fluid gear pumps in automated painting systems using a repetitive controller
K. Park, M. Chang, D. Jeon • Applied Sciences, Vol. 9, No. 16, 3413, 2019
MDPI ↗

Additional Peer-Reviewed Conferences, Preprints & Thesis (13)

arXiv 2025
The Realization of Virtual Environments in the Lower Limb Exoskeletal Robot
M. Chang, D. Jeon • arXiv preprint arXiv:2503.16459, 2025
arXiv ↗
ICCAS 2019
Intelligent Impedance Control Using Reinforcement Learning for the effective Robot-Assisted Rehabilitation
M. Chang, D. Jeon • 19th Int. Conf. on Control, Automation and Systems (ICCAS), 2019
Scholar ↗
ICCAS 2019
AI Therapist realizing the Expert's Verbal Cue for the Effective Robotic Gait Rehabilitation
M. Chang, D. Jeon • 19th Int. Conf. on Control, Automation and Systems (ICCAS), 2019
Scholar ↗
INRS 2019
Development of the AI Therapist realizing the Expert's Verbal Cue for the Effective Robotic Gait Rehabilitation
M. Chang, D. Jeon • RehabWeek, Int. Neurorehabilitation Symposium (INRS), Toronto, 2019
Scholar ↗
ICNR 2018
The AI supervisor for the effective treadmill training system of rehabilitation and exercise
J. Kim, M. Chang, D. Jeon • 4th Int. Conf. on NeuroRehabilitation (ICNR), Pisa, 2018
Scholar ↗
ICCAS 2018
An Expert System for the Effective Treadmill Training System of Rehabilitation and Exercise by using ANFIS
M. Chang, D. Jeon • 18th Int. Conf. on Control, Automation and Systems (ICCAS), 2018
Scholar ↗
Thesis 2018
능동보행훈련을 위한 하지외골격로봇의 필요에 따른 보조 제어 방법 (An assist-as-needed control method of a lower limb exoskeletal robot for active gait training)
장민수 (M. Chang) • Sogang University Graduate School, 2018
Scholar ↗
ICCAS 2017
The Effective Rehabilitation Method Realizing Various Environments in Robot-assisted Gait Training (Best Presentation Award)
M. Chang, D. Jeon • 17th Int. Conf. on Control, Automation and Systems (ICCAS), Jeju, 2017
Scholar ↗
ICCAS 2017
A method of specific muscle group training of lower limb using an exoskeletal robot
M. Chang, D. Jeon • 17th Int. Conf. on Control, Automation and Systems (ICCAS), Jeju, 2017
Archive ↗
ICCAS 2017
Realization of Virtual Impedance in the Lower Limb Assistive Robot SUBAR
Y. Kim, M. Chang, D. Jeon • 17th Int. Conf. on Control, Automation and Systems (ICCAS), Jeju, 2017
Archive ↗
INRS 2017
Realization of the Effects of Various Environments in Robot-assisted Gait Training
M. Chang, D. Jeon • RehabWeek, Int. Neurorehabilitation Symposium (INRS), London, 2017
Archive ↗
KSPE 2016
하지외골격로봇 착용자의 자세 안정성 분석을 위한 HAT Model 의 실험적 검증
장민수 (M. Chang), 전도영 (D. Jeon) • 한국정밀공학회 학술발표대회 논문집 (KSPE), 83–84, 2016
Scholar ↗
KROS 2016
보행재활로봇의 개발 경험과 이슈 (Development Experience and Issues of Gait Rehabilitation Robots)
장민수 (M. Chang), 전도영 (D. Jeon) • 로봇과 인간 (Robotics and Human), 13(2), 14–20, 2016
DBpia ↗

Patents — 10 US Patents/Applications & 4 KR Registered Patents (14 Total)

P01 • 2026
Open-close type spatula, powder-dispensing apparatus including the same, and method of controlling powder-dispensing apparatus
M. CHANG, J. Jun-Won, H. Do CHOI, G. Ki-Won, W.J. CHOI, D. Han • US Patent App. 19/233,597 (2026)
Scholar ↗
P02 • 2026
Electronic device and method of planning moving path of robot
J. Jun-Won, J. Park, S. Jeon, M. Kim, M. CHANG • US Patent App. 19/249,393 (2026)
Scholar ↗
P03 • 2026
Mobile machine for adjusting safety margin and moving method thereof
M. CHANG, S.Y. Kim, J. Jun-Won, W.J. CHOI, D. Han, H. Park • US Patent App. 19/305,009 / US20260072439A1 (2026)
Patent ↗
P04 • 2026
Transfer system
M. CHANG, S.Y. Kim, J. Jun-Won, D. Han, H. Do CHOI, T. Ha • US Patent App. 19/041,483 / US20260028212A1 (2026)
Patent ↗
P05 • 2025
Separation and purification module and automated material reaction system including the same
H. Do CHOI, J. Kim, H. Kwon, B. Kim, J.W. Kim, D. Lee, S. Lee, M. CHANG, et al. • US Patent App. 19/068,604 (2025)
Scholar ↗
P06 • 2025
Optical monitoring device
W. Hong, H. Kwon, G. Kim, W.S. Oh, H. Jeon, H. Do CHOI, M. CHANG, Y. Choi • US Granted Patent 12,411,092 B2 (2025)
Patent ↗
P07 • 2025
Material synthesis device, material synthesis platform, and method of operating material synthesis device
S. Lee, D. Lee, M. CHANG, J. Chang, J. Jang, T. Ha • US Patent App. 18/989,808 / US20250232845A1 (2025)
Patent ↗
P08 • 2025
Automatic evaporator system
H. Do CHOI, B. Kim, S.Y. Kim, S. Seo, M. CHANG, J.W. Jang, H. Jeon, W. Hong • US Patent App. 18/968,676 / US20250180449A1 (2025)
Patent ↗
P09 • 2025
Liquid processing apparatus and liquid processing system including the same
S.Y. Kim, B. Kim, S. Seo, M. CHANG, J.W. Jang, H. Jeon, H. Do CHOI, D. Heo, W. Hong • US Patent App. 18/885,072 / US20250180450A1 (2025)
Patent ↗
P10 • 2025
Platform system
D. Han, S.Y. Kim, M. CHANG, J.W. Jang, T. Ha • US Patent App. 18/908,258 / US20250122061A1 (2025)
Patent ↗
P11 • KR
Robot of assisting to exercise one's lower body, the production method of it, and the controlling method of it
D.Y. Jeon, M.S. CHANG • KR Registered Patent No. 10-2262191 (Pub. KR20200142384A)
Patent ↗
P12 • KR
Robot for assisting muscular strength in walking
D.Y. Jeon, M.S. CHANG • KR Registered Patent No. 10-2218260 (Pub. KR20200142347A)
Patent ↗
P13 • KR
Rehabilitation robot for gait assistant driven by a motor
M.S. CHANG, D.Y. Jeon • KR Registered Patent No. 10-2132113 (KR102132113B1)
Patent ↗
P14 • KR
Stabilization control method for exoskeleton robot of legs
C.H. Seo, D.Y. Jeon, M.S. CHANG • KR Registered Patent No. 10-1940901 (KR101940901B1)
Patent ↗