Pac-Man Pete: An extensible framework for building AI in VEX Robotics
Jacob Zietek, Nicholas Wade, Cole Roberts, Aref Malek, Manish Pylla,, Will Xu, Sagar Patil

TL;DR
This paper presents Pac-Man Pete, an extensible framework for developing AI in VEX Robotics, including simulation, vision, and data transfer components, aimed at advancing autonomous robotics education.
Contribution
It introduces a modular, reusable AI development framework for VEX Robotics, combining simulation, vision, and data transfer pipelines to facilitate autonomous robot development.
Findings
Developed a Unity simulation environment for VEX Robotics AI.
Created a flexible computer vision pipeline for autonomous tasks.
Implemented a data transfer system to offload computations from the robot.
Abstract
This technical report details VEX Robotics team BLRSAI's development of a fully autonomous robot for VEX Robotics' Tipping Point AI Competition. We identify and develop three separate critical components. This includes a Unity simulation and reinforcement learning model training pipeline, a malleable computer vision pipeline, and a data transfer pipeline to offload large computations from the VEX V5 Brain/micro-controller to an external computer. We give the community access to all of these components in hopes they can reuse and improve upon them in the future, and that it'll spark new ideas for autonomy as well as the necessary infrastructure and programs for AI in educational robotics.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsReinforcement Learning in Robotics
