Education

New York University

Sep 2019 - May 2024

Ph.D, Electrical Engineering

Carnegie Mellon University

Aug 2017 - May 2019

Master of Science, Mechanical Engineering

Huazhong University of Science and Technology

Sep 2013 - Jun 2017

Bachelor of Engineering, Mechanical Engineering

Research & Work Experience

Point Cloud Based Control Barrier Function for Safe Navigation

Oct 2023 -- May 2024

New York University, Tandon School of Engineering, Brooklyn, NY

  • Proposed a new methodology for synthesizing control barrier functions from raw point cloud measurements.
  • Utilized GPU acceleration to make the control barrier function synthesis computationally efficient.
  • Performed experimental validation of the proposed approach on Unitree Go2 and Unitree B1 quadrupedal robots.
Differentiable Optimzation Based Control Barrier Function Synthesis

Oct 2022 -- Sep 2023

New York University, Tandon School of Engineering, Brooklyn, NY

  • Proposed a new methodology for control barrier function synthesis using differentiable optimization.
  • Performed experimental validation of the proposed methodology on Franka Research 3 robot.
  • Extended the methodology to handle problem with time-varying safe set which considering measurement noise and acutation limits.
Learning Based Control Barrier Function Synthesis

Oct 2021 -- Sep 2022

New York University, Tandon School of Engineering, Brooklyn, NY

  • Proposed a new methodology for learning based control barrier function synthesis starting from handcrafted control barrier functions.
  • Proposed a prioritized sampling method to make the learning based control barrier function synthesis more data efficient.
State Constrained Stochasitic Optimal Control Using LSTMs

May 2020 -- Sep 2022

New York University, Tandon School of Engineering, Brooklyn, NY

  • Proposed a new methodology for state constrained nonlinear stochastic optimal control using forward-backward stochastic differential equations and LSTMs.
  • Created custom simulation environments to test the performance and scalability of nonlinear systems with both continuous and hybird dynamics.
Reinforcement Learning in Mining

Jun 2019 -- Aug 2019

SafeAI Inc, San Jose, CA

  • Created a reinforcement learning simulation environment for the load-haul-dump cycle.
  • Designed the reward function, state space and action space to be both realistic while also speeds up training.
  • Constructed a behavior tree that orchestrates between reinforcement learning based and traditional controllers.
Adaptive Identification of Robotic Kinematic Structure

Jan 2018 -- May 2019

Carnegie Mellon University, Robotic Institute, Pittsburgh, PA

  • Proposed a 6 degrees-of-freedom (DOF) joint based kinematic model for a multi-link bipedal robot system
  • Developed a 6 DOF joint based kinematic identification algorithm using linear regression and achieved 92.3\% accuracy in simulation with white noise polluted data.
  • Implemented the kinematic identification algorithm on a real bipedal robot ATRIAS using mocap data.
Human Knee Sensory System for Exoskeletons

Jan 2017 -- May 2017

Huazhong University of Science and Technology, Mechanical Engineering Department, Wuhan, Hubei, China

  • Used a three-dimension curvature-based model to represent the whole femur-knee-tibia system, which overcomes the difficulty for modelling non-uniform shaped contact parts in bio-joints.
  • Implemented a modal-superpostion method to reduce the number of sensors required to only three.

Skills

  • Programming Skills: Python, C++, C, Matlab, Java, HTML, CSS, JavaScript
  • Deep Learning Frameworks: Tensorflow, PyTorch, Keras
  • Languages: English (fluent) and Mandarin (native)