Wenda Zhao
Postdoctoral Fellow at University of Toronto Autonomous Drone Racing (ADR) Team
Old Toronto, Ontario, Canada
Summary
👤
Senior🎓
Top SchoolWenda Zhao is a postdoctoral researcher specializing in AI and robotics, holding a Ph.D. from UTIAS and currently working on LiDAR-based continuous-time state estimation at the University of Toronto. With eight years of experience spanning academic research and hands-on systems work, she blends learning-based methods with robust state estimation for real-world robotics, particularly UWB and visual-inertial localization for agile drones. Her contributions include firmware-level improvements to the Crazyflie platform—implementing an M-estimation Kalman filter for TDOA localization—demonstrating fluency from embedded systems to high-level learning. She collaborates across the Vector Institute, UofT Robotics Institute, and autonomous drone racing teams, benchmarking RL and optimal control for decision-making in degraded environments. Wenda is drawn to hardware-software co-design and rigorous experimental validation, often tackling non-Gaussian noise and optimal sensor placement problems that are overlooked in simulation-only studies. Based in Toronto with international training in Shanghai and Germany, she combines theoretical rigor with practical, field-validated solutions.
8 years of coding experience
Master of Science - MS, Control Science and Engineering, Master of Science - MS, Control Science and Engineering at Tongji UniversityResearch Assistant, Robotics, Research Assistant, Robotics at Technical University of MunichDoctor of Philosophy - PhD, Aerospace and Autonomous Robotics, Doctor of Philosophy - PhD, Aerospace and Autonomous Robotics at University of TorontoExchange program, Robotics Technology/Technician, Exchange program, Robotics Technology/Technician at RWTH Aachen University
Github Skills (14)
c1710
embedded10
c1110
sys10
kalman-filter10
decomposition9
numerical9
numerical-methods9
numeric9
stability9
decompose9
deco9
numerics9
matrix-decomposition9
Programming languages (4)
Github contributions (5)
bitcraze/crazyflie-firmware
Feb 2021 - May 2021
The main firmware for the Crazyflie Nano Quadcopter, Crazyflie Bolt Quadcopter and Roadrunner Positioning Tag.
Role in this project:
Embedded Systems Engineer / IoT Developer
Embedded Systems Engineer / IoT DeveloperContributions:12 commits, 8 PRs, 11 comments in 3 months
Contributions summary:Wenda contributed significantly to the firmware of the Crazyflie Nano Quadcopter, with a focus on implementing and refining the Kalman filter for Time Difference of Arrival (TDOA) localization. Their work included developing a robust M-estimation-based Kalman filter, incorporating features for hyperparameter tuning, and providing numerical stability for matrix operations. Further contributions involved addressing copy-paste errors and ensuring overall code organization and efficiency.
boltfirmwarecrazyfliezeroquadcopter
utiasDSL/crazyflie-firmware
Mar 2019 - Nov 2020
The main firmware for the Crazyflie Nano Quadcopter.
Contributions:6 PRs, 100 pushes, 23 branches in 1 year 8 months
jtagcrazyfliefirmwareiioquadcopter
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.