About me

I’m a Ph.D. candidate in Mechanical Engineering at the University of Washington, advised by Prof. Xu Chen. My research focuses on Robotics, Motion Planning & Control, Tactile Sensing, and Vision-Language Models for Robot Reasoning. I received my B.Eng. from Zhejiang University in 2021, where I was part of the Chu Kochen Honors College.

Education & Experience

University of Washington, Seattle, WA
Ph.D. in Mechanical Engineering (Sep 2021 - June 2026)
M.S. in Mechanical Engineering & Minor in Data Science (2023) | GPA: 3.91/4.0

Zhejiang University, Hangzhou, China
B.Eng. in Biosystems Engineering (Sep 2017 - July 2021)
Chu Kochen Honors College | Advanced Honor Class of Engineering Education (ACEE)

Technical University of Munich, Munich, Germany
Exchange Student, Mechanical Engineering (Oct 2019 - Mar 2020)

Google - Student Researcher (Robotics & Embodied AI)
Mountain View, CA | Sep 2025 - Dec 2025
Sim-to-Real RL for humanoid robot and object interaction, VLM reasoning with Gemini, XR Perception

Western Digital - Electrical & Firmware Engineering Intern
San Jose, CA | June 2024 - Sep 2024, June 2025 - Sep 2025
System identification for HDD servo, Youla-Kucera loop-shaping controller design

Futronics (UBTECH Robotics North America) - Robotics & Control Engineer Intern
Los Angeles, CA | Jan 2025 - March 2025
Learning Based Trajectory optimization for rehabilitation upper limb exoskeleton

Selected Publications

Google Scholar

Robotics & AI

Learning to Detect Slip through Tactile Estimation of the Contact Force Field and Its Entropy Properties

Xiaohai Hu, Aparajit Venkatesh, Yusen Wan, Guiliang Zheng, Neel Jawale, Navneet Kaur, Xu Chen, Paul Birkmeyer

Mechatronics, 2024  🏆 Best Paper Award in 2024 ASME Robotics Certificate

A physics-informed, data-driven approach for real-time slip detection using GelSight tactile sensor, achieving 95.61% classification accuracy.

Paper

[Enabling Egocentric Cognitive Reasoning in Humanoids via Geometric-Aware Motion Imitation and AR Integration]

Xiaohai Hu, [Co-authors]

Under Review, 2025

Sim-to-Real RL for humanoid robot and object interaction.

Paper

Learned Slip-Detection-Severity Framework Using Tactile Deformation Field Feedback for Robotic Manipulation

Neel Jawale*, Navneet Kaur*, Amy Santoso, Xiaohai Hu, Xu Chen

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024

A learned framework for slip detection and severity estimation, achieving 92% detection accuracy and 0.6 cm/s MAE for slip velocity.

Paper Project

Context and Geometry Aware Voxel Transformer for Semantic Scene Completion

Zhu Yu, Runmin Zhang, Jiacheng Ying, Junchen Yu, Xiaohai Hu, Lun Luo, Si-Yuan Cao, Hui-Liang Shen

NeurIPS, 2024

A novel context and geometry aware voxel transformer that initializes context-dependent queries and extends deformable cross-attention to 3D pixel space for semantic scene completion.

Paper Code

GraphLLM: Boosting Graph Reasoning Ability of Large Language Model

Ziwei Chai, Tianjie Zhang, Liang Wu, Kaiqiao Han, Xiaohai Hu, Xuanwen Huang, Yang Yang

IEEE Transactions on Big Data, 2025

Paper Code

Multi-view Consistent Latent Action Learning for World Modeling and Control

Shenghua Wan, Xiaohai Hu, Xunlan Zhou, Lei Yuan, Le Gan, De-Chuan Zhan

Preprint, 2024

MuCoLA learns robust, view-invariant action representations by enforcing semantic consistency across synchronized video streams via DINO-style self-distillation.

Paper Code

MARVL: Multi-Stage Guidance for Robotics Manipulation via Vision Language Models

Xunlan Zhou, Xuanlin Chen, Shaowei Zhang, Xiangkun Li, Shenghua Wan, Xiaohai Hu, Lei Yuan, Le Gan, De-Chuan Zhan

Preprint, 2024

MARVL fine-tunes a VLM for spatial and semantic consistency and decomposes tasks into multi-stage subtasks with task direction projection.

Paper Code

Control

State-Space System Identification Beyond the Nyquist Frequency with Collaborative Non-Uniform Sensing Data

Xiaohai Hu, Thomas Chu, Xu Chen

American Control Conference (ACC), 2024

A method for system identification using non-uniform sensing data to recover dynamics beyond the Nyquist frequency limit.

Paper

Optimal Loop Shaping and Disturbance Rejection Beyond the Nyquist Frequency using Forward Model Disturbance Observer

Thomas Chu, Xiaohai Hu, Xu Chen

American Control Conference (ACC), 2024

Paper

Iterative Youla-Kucera Loop Shaping For Precision Motion Control

Xiaohai Hu, Jason Laks, Guoxiao Guo, Xu Chen

IFAC-PapersOnLine, 2025

Paper

PyHDD Benchmark: A Python-Based Framework for Magnetic-Head Positioning Control Systems in Hard Disk Drives

Zidong Liu, Yusen Wan, Richard Lu, Amy Santoso, Xiaohai Hu, Thomas Chu, Tianyu Jiang, Guoxiao Guo, Takenori Atsumi, Xu Chen

IFAC World Congress, 2026 (Under Review)

The first Python-based open-source framework for simulating dual-stage actuator control in HDD servo systems with high-fidelity dynamics and multi-rate digital control.

Code

News & Awards

• 2025: Students win ASME Best Paper Awards - “Learning to Detect Slip through Tactile Estimation of the Contact Force Field and Its Entropy Properties” [Certificate]
• 2023: Featured in UW ME News: Robotics for Manufacturing
• 2022: Featured in IEEE Spectrum - Chess Playing Robot

Fun Projects

Humanoid VGGT Scene Reconstruction
Real-time 3D scene reconstruction with humanoid robot wearing AR glasses for navigation

Chess-Playing Robot
Chess Piece detection and manipulation

2018 Chinese Agricultural Robot Competition
Apple harvesting robot demo

Mobile Manipulator
Robot arm mounted on mobile base for manipulation tasks

Real-Time Whole-Body Teleoperation
Humanoid robot control using general motion tracker

Misc: I hail from Jiangxi, China, with my formative years spent in Jingdezhen, a city globally acclaimed for its centuries-old tradition of crafting the finest porcelain.