Hi I'm Max :D

I'm a Mechatronics Engineering student at the University of Waterloo, working on quadruped locomotion, ROS2 autonomy, and learned + vision-guided manipulation.

Portfolio: https://notmax08.github.io

Projects

The Brackey Way — Bracket Bot (1st place, Battle of the Schools, UMIST / WAT.AI)

A dual-arm Bracket Bot that takes toast out of a toaster, puts it on a plate, adds lettuce, and places the top slice. A fine-tuned π₀ VLA (trained on 100+ Meta Quest teleop episodes) handles the difficult grasps, OpenCV + inverse kinematics handles the simple ones, and a state machine switches between them.

π₀ VLA, Imitation learning, OpenCV, State machine

Quadruped Locomotion with PPO — Unitree Go2 (in progress)

A walking policy for a Unitree Go2 quadruped, trained with PPO in Isaac Lab.

Isaac Lab, PPO, PyTorch

best_demo.mp4

Autonomous Maze Navigator — Nova Carter

A ROS2 navigation stack in Isaac Sim: SLAM builds a map of the maze, AMCL localizes the robot on the map, and Nav2 plans a path and drives it.

ROS2, Nav2, SLAM

nav2_demo.mp4

RICO — Robotic Arm That Fetches Tools (Eureka Hacks)

You ask for a tool, and the arm finds it on the bench and hands it to you. Uses a Groq LLM, homography, YOLOv8 object detection, and inverse kinematics.

YOLOv8, OpenCV, Inverse kinematics

FIRST Tech Challenge 18844 (1st Connect Award, Ochoa Division, 2025 FIRST World Championships)

Co-captain and lead programmer. PID point-to-point movement, odometry with IMU heading, and CNN-driven automated pickup.

PID control, Odometry, Java

ftc.mov

Toolkit

• Languages: Python, Java, C++
• Simulation and robotics: Isaac Sim, Isaac Lab, ROS2, RViz, Onshape
• Learning and vision: PyTorch, rsl_rl, OpenCV, YOLOv8, π₀ VLA
• Focus areas: Reinforcement learning, Imitation learning, PID control, Inverse kinematics, Odometry and SLAM