Robotics PhD Student, Georgia Tech

Yunhai Han

I study structured robot learning for manipulation in complex, unstructured environments, with a focus on dexterity learning from human video, robot behavior models, and tactile manipulation.

I am advised by Prof. Harish Ravichandar at Georgia Tech. I have also been fortunate to work with Prof. Sehoon Ha, Prof. Zsolt Kira, and Prof. Danfei Xu. I received my M.S. and B.S. in Mechanical Engineering from UC San Diego and Yanshan University.

My interest in robotics started with Code Geass, and I wanted to build a mecha in high school. Now, the robots I work on are smaller than the mecha I imagined, but the motivation has stayed with me.

Email CV GitHub Google Scholar LinkedIn

Research Focus

I build robot-learning systems that turn human videos, sparse demonstrations, and real-world explorative interactions into deployable manipulation skills.

Learning from human videos

Robot learning from motion and interaction priors extracted from human videos.

Visuo-dexterity learning

Learning temporally coherent visuo-dexterity skills with behavioral dynamics.

Tactile adaptation

Using touch to adapt visual policies when contact details matter most.

By integrating these directions, I aim to build open-world robot-learning agents that autonomously acquire robust dexterous skills from watching human users at deployment time and generalize across diverse operating environments, objects, tasks, and robot platforms.

I am not yet sure whether robotics' GPT-like moment will arrive as one monolithic policy distilled from all available data, or as a self-sufficient learning framework that keeps acquiring skills autonomously in the wild; I lean toward the latter.

Recent news

A short log of current research milestones, talks, internships, and fellowship updates.

  1. Research intern at NVIDIA Seattle Robotics Lab, studying humanoid robot learning from offline human manipulation videos.
  2. Invited talk at the Georgia Tech RoboGrads Student Seminar (poster).
  3. Passed the PhD proposal and advanced to PhD candidacy, with committee members Zsolt Kira, Danfei Xu, Yunzhu Li, and Dinesh Jayaraman.
  4. Selected as a Qualcomm Innovation Fellowship Finalist with Kelin Yu.

Robots operating in the real world

Real-world clips of Koopman-inspired visuo-dexterity, tactile policies, and autonomous robot learing from human video.

Koopman-inspired model

Visuo-dexterity through behavioral dynamics

A Koopman-inspired visuo-dexterity model rolls out structured visual-action dynamics for temporally coherent manipulation.

For unanticipated disturbances, the behavioral dynamics model enables event-triggered replanning. We call it behavioral dynamics because it jointly predicts the coupled evolution of robot actions and object motions, with object motion parameterized by the object flow points. At runtime, it compares predicted and observed visual object flow; when their discrepancy exceeds a threshold, it generates a new, coherent action trajectory—balancing smooth execution with immediate reactivity, without tuning action chunks or collecting failure-recovery demonstrations.

Tactile policy

Contact-aware tactile adaptation

A tactile residual policy refines a visual base policy through real-world RL, using additional tactile feedback for contact-rich tasks.

Autonomous learning from human video

One autonomous pipeline converts human manipulation videos (left) into deployable robot policies (right) across daily manipulation tasks.

Apple serving
Spicing
Box passing task
Toy rearrangement

Selected publications

A curated set of projects that best represent my current research direction in dexterous robot learning and tactile sensing.

Video2Sim2Real teaser
2026 Under review

Video2Sim2Real: Full-Stack Autonomous Dexterous Skill Acquisition from a Single Human Video

Autonomously reconstructs a digital twin from one human video, refines dexterous behavior in simulation, and transfers the skill to real robots.

arXiv Website
Koopman behavioral model overview
2026 Under review

Going with the Flow: Koopman Behavioral Models as Pseudo Planners for Visuo-Motor Dexterity

Learns dexterous behavior as coupled visual and action flows, using a structured Koopman model for temporally coherent visuo-motor planning.

arXiv Website
OmniTacTune teaser
2026 Under review

OmniTacTune: Policy-Agnostic Real-World RL for Tactile Residual Adaptation of Visual Policies

Adapts tactile feedback to pretrained visual policies through real-world residual RL for contact-rich manipulation.

arXiv Website
ImMimic method overview
2025 CoRL Oral RSS Dex Workshop Spotlight

ImMimic: Cross-Domain Imitation from Human Videos via Mapping and Interpolation

Bridges human-to-robot imitation with retargeted human videos, robot demonstrations, and interpolation across embodiments.

arXiv Website Code
CIMER motion refinement overview
2024 RA-L

Learning Prehensile Dexterity by Imitating and Emulating State-only Observations

Combines imitation and emulation to learn dexterous prehensile manipulation from state-only observations.

arXiv Website Code
MimicTouch tactile demonstration setup
2024 CoRL NeurIPS Touch Workshop Best Paper

MimicTouch: Leveraging Multi-modal Human Tactile Demonstrations for Contact-rich Manipulation

Transfers tactile-guided human manipulation strategies to robot grippers with imitation and online residual reinforcement learning.

arXiv Website OpenReview
Dexterous manipulation demonstration
2023 CoRL Oral

On the Utility of Koopman Operator Theory in Learning Dexterous Manipulation Skills

Shows that Koopman operator-based imitation learning can train dexterous manipulation skills efficiently, quickly, and with interpretable structure.

arXiv Website Code OpenReview

All publications

Search and filter the full publication list by title, topic, venue, author, or year.

2026

Video2Sim2Real teaser

Video2Sim2Real: Full-Stack Autonomous Dexterous Acquisition from a Single Human Video

Yunhai Han*, Jianuo Qiu*, Linhao Bai, Ziyu Xiao, Zihang Zeng, Yangcen Liu, Zhaodong Yang, Shalin Jain, Wenrui Ma, Jiaqi Fu, Yuqian Zheng, Manisha Natarajan, Muhammad Zubair Irshad, Kenneth Shaw, Matthew Gombolay, Zsolt Kira, Harish Ravichandar

Under review

Introduces a full-stack framework that reconstructs simulator-ready digital twins from a single human video, extracts priors for robot and object motion, refines behavior in simulation, and transfers dexterous skills to real robots.

arXiv Website
OmniTacTune teaser

OmniTacTune: Policy-Agnostic Real-World RL for Tactile Residual Adaptation of Visual Policies

Kelin Yu*, Haode Zhang*, Harish Ravichandar, Yunhai Han, Ruohan Gao

Under review

Adapts tactile feedback to pretrained visual policies through a policy-agnostic residual RL pipeline, improving real-world contact-rich manipulation across tasks, policies, and tactile representations.

arXiv Website
Bipedal navigation with Koopman MPC

Safe Navigation of Bipedal Robots via Koopman Operator-Based Model Predictive Control

Jeonghwan Kim, Yunhai Han, Harish Ravichandar, Sehoon Ha

Accepted by IROS 2026

Builds a safe navigation framework for bipedal robots by learning linearized base-level dynamics in a lifted Koopman space and using the model inside MPC.

arXiv Website

2025

ImMimic method overview

ImMimic: Cross-Domain Imitation from Human Videos via Mapping and Interpolation

Yangcen Liu*, Woochul Shin*, Yunhai Han, Zhenyang Chen, Harish Ravichandar, Danfei Xu

Accepted by CoRL 2025 (Oral); Spotlight at RSS Dex Workshop

Bridges human-to-robot imitation by combining retargeted human hand trajectories, robot demonstrations, and MixUp interpolation for embodiment-agnostic co-training.

arXiv Website Code
Spectral clipping geometric intuition

On the Surprising Effectiveness of Spectral Clipping in Learning Stable Linear and Latent-Linear Dynamical Systems

Hanyao Guo*, Yunhai Han*, Harish Ravichandar

Under review

Studies a simple post-hoc spectral clipping procedure that can produce accurate, verifiably stable, and computationally efficient learned linear and Koopman dynamical systems.

arXiv Code
AsymDex bimanual dexterity overview

AsymDex: Leveraging Asymmetry and Relative Motion in Learning Bimanual Dexterity

Zhaodong Yang, Yunhai Han, Harish Ravichandar

Spotlight at RSS Whole-body Control and Bimanual Manipulation Workshop 2025; Poster at CoRL Workshop 2024

Learns asymmetric bimanual dexterity by assigning complementary hand roles and operating over relative observation and action spaces for coordinated manipulation.

Website OpenReview

2024

CIMER motion refinement overview

Learning Prehensile Dexterity by Imitating and Emulating State-only Observations

Yunhai Han, Zhenyang Chen, Kyle A. Williams, Harish Ravichandar

Accepted by RA-L

Combines imitation and emulation to learn dexterous prehensile manipulation from state-only observations, then refines the learned motion prior through reinforcement learning.

arXiv Website Code
MimicTouch tactile demonstration setup

MimicTouch: Leveraging Multi-modal Human Tactile Demonstrations for Contact-rich Manipulation

Kelin Yu*, Yunhai Han*, Qixian Wang, Vaibhav Saxena, Danfei Xu, Ye Zhao

Accepted by CoRL 2024; Best Paper at NeurIPS Touch Processing Workshop

Collects multimodal human tactile demonstrations and uses imitation plus online residual RL to transfer tactile-guided strategies to robot grippers.

arXiv Website OpenReview

2023

Dexterous manipulation demonstration

On the Utility of Koopman Operator Theory in Learning Dexterous Manipulation Skills

Yunhai Han, Mandy Xie, Ye Zhao, Harish Ravichandar

Accepted by CoRL 2023 (Oral)

Shows that Koopman operator-based imitation learning can train dexterous manipulation skills efficiently, quickly, and with interpretable structure.

arXiv Website Code OpenReview

2022

Multi-agent conflict resolution simulation

Leveraging Heterogeneous Capabilities in Multi-Agent Systems for Environmental Conflict Resolution

Michael E. Cao*, Jonas Warnke*, Yunhai Han, Xinpei Ni, Ye Zhao, Samuel Coogan

Accepted by SSRR 2022

Introduces a temporal-logic-based controller synthesis framework for heterogeneous agents that resolve runtime environmental conflicts while preserving safety and task completion.

arXiv Video

2021

Differential privacy framework

A Numerical Verification Framework for Differential Privacy in Estimation

Yunhai Han, Sonia Martinez

Accepted by L-CSS and ACC 2022

Develops a numerical method for verifying differential privacy in estimation problems with performance guarantees.

arXiv Slides

2020

2D surgical simulation

A 2D Surgical Simulation Framework for Tool-Tissue Interaction

Yunhai Han, Fei Liu, Michael C. Yip

Spotlight presentation at IROS Workshop 2020

Tracks manipulator motion and simulates tissue deformation under collision detection for control and planning in surgical robotics.

arXiv Slides Talk
Stop-sign auto-calibration pipeline

Auto-calibration Method Using Stop Signs for Urban Autonomous Driving Applications

Yunhai Han*, Yuhan Liu*, David Paz, Henrik Christensen

Accepted by ICRA 2021

Uses recognized stop signs as structures for dynamic camera calibration after vehicle motion or bumps challenge the original calibration.

arXiv Dataset
Real-to-sim registration of deformable tissue

Real-to-Sim Registration of Deformable Soft Tissue with Position-Based Dynamics for Surgical Robot Autonomy

Fei Liu*, Zihan Li*, Yunhai Han, Jingpei Lu, Florian Richter, Michael C. Yip

Accepted by ICRA 2021

Proposes an online registration method that connects 3D visual perception with position-based dynamics modeling of deformable tissue.

arXiv Video

Students and collaborators

Students I have mentored and external collaborators I have worked with across robotics, control, and robot learning.

Mentored students

  • Kelin Yu CS M.S., 2022-2024; now PhD at UMD CS
  • Zhenyang Chen Robotics M.S., 2023-2024; now PhD at GT Robotics
  • Hanyao Guo Robotics M.S., 2024-2025; now SDE at Amazon
  • Pratik Shah CS M.S., 2024-2025; now MLE at Amazon Annapurna Labs
  • Yuqian Zheng CSE M.S., 2024-2025
  • Yangcen Liu Robotics M.S. in Prof. Danfei Xu's lab, 2024-2025; now CS PhD at UChicago
  • Woochul Shin CS M.S. in Prof. Danfei Xu's lab, 2024-2025; now CS PhD at UMD
  • Linhao Bai CS M.S., 2024-present
  • Ziyu Xiao ECE M.S., 2025-present
  • Jianuo Qiu Robotics M.S., 2026-present
  • Jiaqi Fu Robotics M.S., 2026-present
  • Zihang Zeng Robotics M.S., 2026-present

External collaborators

Group projects

Hands-on robotics projects that shaped how I think about perception, control, and deployed systems.

RoboMaster robot

RoboMaster

RoboMaster is a DJI-founded platform for robotic competitions and academic exchange. I was the vision group leader of YSU Eagle, where my group worked on object tracking, range estimation, serial-port communication, and gimbal stability control for mobile robots.

Overview Our robots

Service, teaching, and interests

Academic service, teaching experience, and a few personal interests outside the lab.

Professional service

  • GT RoboGrads Research Vice President
  • Reviewer ICRA, IROS, RSS, CoRL, RA-L, IEEE T-RL, NeurIPS, ICLR, AIM, SSRR
  • Session Chair ACC

Teaching

  • MAE145, Robotic Planning & Estimation, UCSD Teaching Assistant, Winter 2021
  • MAE146, Introduction to ML Algorithms, UCSD Teaching Assistant, Spring 2021

Working experience

  • Research Assistant, Georgia Institute of Technology Summer 2021 to Spring 2022

Misc

  • Running Finished a half-marathon within 2 hours
  • Soccer and badminton
  • Photography
  • Gaming League of Legends
  • Anime, manga, and movies