About Me

I am a robotics engineer specializing in simulation development, building high-fidelity virtual environments to accelerate robotic testing and deployment. My work contributes to bridging the sim-to-real gap by creating more accurate and efficient simulation frameworks. I am particularly interested in reinforcement learning and imitation learning, exploring novel control policies that unlock new robotic capabilities and enable safer, more human-like interactions.

I received my bachelor's degree in Mechatronics Engineering and AI option with distinction at the University of Waterloo. I was a part of WATonomous, the Waterloo's self driving car team where I gained insights in autonomous vehicles and experiences with ROS. I also competed in hackathons and have built 10 unique projects which won numerous awards.

NVIDIA Robotics

- Developed sim to sim transfer pipeline for Isaac Lab and Isaac Sim for reinforcement learning based locomotion inference workflow for humanoid and quadruped such as H1, Spot, and Anymal

- Created a digital twin’s library of over 30 humanoids, quadrupeds, manipulators, claws, and mobile robots for training and deployment in Isaac Sim and Isaac Lab

- Optimized physical sensors such as contact sensor and IMU with tensor backend to improve performance, unified raw data source, and parallelized data processing with CUDA

- Improved URDF and MJCF robot file importers to Isaac Sim to accurately represent robot dynamics and organize robot visual, physics, and sensor properties in different assets

- Mentored an intern by teaching essential skills though projects steering (Ackermann) controller and giving feedback between projects, saw significant improvement on the intern’s capabilities

- Set up sample stereo vision SLAM and ROS pipelines to demonstrate digital robot workflow in simulated warehouse environments

Internships

I worked on the body firmware controls team, and developed lighting applications that run on the new palladium Model S, X, and Tesla Semi such as the Tesla Light Test, which was featured on the Tesla Semi Delivery Event

I joined NVIDIA Isaac Sim team, a scalable robotics simulation that powers photorealistic, and physically accurate metaverse for training advance robots. I worked on creating force sensors and simulating quadruped robots in the Omniverse

Ecobee is a Canadian Smart Thermostat Company, I joined Ecobee as an embedded developer, worked on fixtures that supports thermostats productions and developed computer vision and machine learning algorithms for testing displays

I joined the Teaching Team for an introductory C++ programming course as a TA, hosted tutorials, graded assessments, created exam questions, and supported the automated testing server using Python.

Khazanah is a National Wealth Fund that primarily invest in Silicon Valley startups, and as an innovation intern, I worked on different projects in the fields of drone, computer vision, AR/VR to better understand and explain the technologies to the investors

At Ford Motor Company, I worked on supporting the various chipsets used in the F150 Lightning as a member of the manufacturing software team, using tools such as Jenkins, NI Teststand, C#, and Python.

Skills

C, C++, C#, CUDA

Python, MATLAB, R

Arduino, Raspberry Pi, ESP8266

OpenCV and learning Tensorflow

Solidworks, AutoCAD, Blender

ROS, ROS2, Gazebo, and Isaac Sim

Projects and Hobbies

Airplane Project (2020)

The sky is calling!

In this project, I built a remote controlled airplane from scratch using raspberry pi and esp8266 modules, and designed software and mechanical architectures from scratch in a team of two.

Watonomous

Bolty!

Watonomous is a University of Waterloo design team that turns a chevy bolt to a level 4 autonomous vehicle. At Watonomous, I worked on local planning for the vehicle, particularly with the MPC controller and gained valuable experience with ROS.

Webapp Hackathon Projects

Best Use of Google Cloud Award (Purrtector, NWHacks 2021)

Intelibatch (left) is a webapp for displaying and predicting COVID19 cases across North America using React (front end), Flask (back end), and Tensorflow (prediction) to compute the optimal batch size for repeated testing

Purrtector (right) is a chrome extension for encouraging planet positive behaviors by rewarding users with digital pets using React and Flask.

Wearable Hackathon Projects

1st Place (VisionSense, MakeUofT 2019)

VisionSense (left) is an IoT outfit to haptically guide users with visual impairments/obstructions while monitoring their environment

Nightlight (right) is a wearable that allows bike users to signal turns at night via motion-sensing technologies which will activate turn lights

BOFA, the Line Follower Robot

2nd highest competition mark

Lead the mechanical design for a line following robot using SolidWorks, drafted Bill of Material, and oversee software, mechanical, and electrical developments as project manager

HiSecurity!

Hack the north, 2019

This camera system which utilizes machine vision (OpenCV and Sktlearn) to physically track and identify faces using the stepper motors onboard. The handy ui also enables users to track the system remotely and in real time.

VEX Robotics

Finalists, Alberta Provincial Championship 2017 and 2018

Over the three years, we explored various robotics systems such as holonomic drives, reverse double four bar lifts, and even learned C programming and programed PID controllers from scratch in a team of three.
Furthermore, we qualified and competed at VEX World Robotics Championship representing Canada twice, and this experience ultimately propelled me towards a career in robotics engineering.

Pilot

"Oh! I slipped the surly bonds of earth and danced the skies on bright yellow wings."

I finally touched the sky when I earned my glider pilot license in grade 10 and private pilot license in grade 11. This was an breathtaking experiences that inspires me to build robotics airplanes to this date.

Hi, I am Ji Yuan Feng

I am a _