Wenzhe Tong

wenzhet [at] umich.edu


I'm a 2nd year robotics PhD student at UMich advised by Prof. Xiaonan Huang and Prof. Maani Ghaffari. I earned my M.S.E in ECE at UMich advised by Prof. Maani Ghaffari. Previously I exchanged at UC Berkeley advised by Prof. Koushil Sreenath. I worked on path planning algorithms for leash-leaded Human Robot Interaction system in Hybrid Robotics Lab.

I love snowboarding 🏂 and film photography 📷 in my free time.

CV  |   GitHub  |   Google Scholar  |   LinkedIn

profile photo

News

  • Jan. 2025: Tensegrity robot state estimation has been accepted by IEEE RA-L
  • May. 2024: I advanced to Robotics Ph.D. candidate.
  • Sept. 2023: I've joined HDR Lab at UMich.
  • Apr. 2023: I earned ECE M.S.E. degree at UMich.


Research


* denotes equal contribution

Tensegrity Robot Proprioceptive State Estimation with Geometric Constraints.


Wenzhe Tong, Tzu-Yuan Lin, Jonathan Mi, Yicheng Jiang, Maani Ghaffari, Xiaonan Huang
RA-L 2025

[Paper]  [Video

Design of a Variable Stiffness Quasi-Direct Drive Cable-Actuated Tensegrity Robot.


Jonathan Mi, Wenzhe Tong, Yilin Ma, Xiaonan Huang
ArXiv 2024

[Paper

Proprioceptive Invariant Robot State Estimation.


Tzu-Yuan Lin, Tingjun Li, Wenzhe Tong, Maani Ghaffari
ArXiv 2023

[Project page]  [Paper]  [Video

Fully Proprioceptive Slip-Velocity-Aware State Estimation for Mobile Robots via Invariant Kalman Filtering and Disturbance Observer.


Xihang Yu, Sangli Teng, Theodor Chakhachiro, Wenzhe Tong, Tingjun Li, Tzu-Yuan Lin, Sarah Koehler, Manuel Ahumada, Jeffrey M. Walls, Maani Ghaffari
IROS 2024

[Paper]  [Video

Robotic Guide Dog: Leading a Human with Leash-Guided Hybrid Physical Interaction.


Anxing Xiao*, Wenzhe Tong*, Lizhi Yang*, Jun Zeng, Zhongyu Li, Koushil Sreenath
ICRA 2021 | ICRA Best Paper Award Finalist for Service Robotics

[Paper]  [Video

We propose a hybrid physical Human-Robot Interaction model that involves leash tension to describe the dynamical relationship in the robot-guiding human system. This hybrid model is utilized in a mixed-integer nonlinear programming problem to develop a reactive planner that is able to utilize slack-taut switching to guide a blind-folded person to safely travel in a confined space.




Course Projects


RRT path planning for PR2 robot


EECS498-Introduction to Algorithmic Robotics(Fall 2021)

Using RRT-connect algorithm to search feasiable path, then shorten and smoothen the path to the target point.

Control, RL, Grasp planning for 7-DOF Baxter robot


EECS106B-Robotic manipulator and interaction(Spring 2020)

[Project page]  [Video

Based on 7-DOF robot Baxter, we designed workspace position, joint angle and joint torque controller for the robot; then using reinforcement learning to get parameters for our controller. Also designed grasping algorithms for bi-finger gripper.

Camera rig offline extrinsic self-calibration


CS294-Geometry and Learning for 3D Vision(Spring 2020)

We proposed an extrinsic calibration framework for camera rig(binocular camera). Utilizing the hard constraints of cameras' relative pose to design the optimization problem for extrinsic parameter calibration.

Automatic book scanner


ME102B-Mechatronics Design(Fall 2019)

[Video

Compelete 3D model design in SolidWorks; manufactured parts of the scanner by 3D printing and laser cutting. Integrated electronics components with proper specifications in the scanner; implemented controller in ROS with camera image processing.

Auto-aiming pellet launcher quadcopter


Robomaster National Robotics Competetion, University Championship

Designed and analyzed the light-weight quadcopter structures. Integrated electronical control systems for the payload gimbal. Developed target aiming algorithm framework, including detection and tracking with OpenCV.






Last update: Apr. 1st, 2025

source code       credits