Educational Robotics
Balancio
Balancio An educational project involving an ultra-low-cost self-balancing robot 🤖 capable of running a neural network to maintain balance and being wirelessly controlled 🖲️.
Developed for didactic purposes to teach concepts of Reinforcement Learning (RL), Machine Learning (ML), Artificial Intelligence (AI), and control.

Three models were developed: V0.7, V0.6 (Wall-e), and V0.5. Each comes with assembly instructions and 3D blueprints available at https://github.com/udesa-ai/balancio-kit. These documents outline the required components, program installation procedures, and calibration steps.

Air Hockey
The project's goal is to create an open-source platform that serves both educational and research purposes, particularly in the fields of optimal control, Reinforcement Learning, and imitation learning.

The algorithms are developed within a simulator featuring a custom physics engine designed for high-fidelity simulations.
We have a robotic air hockey table that allows us to test algorithms and assess their performance in real-world scenarios. The robotic platform used is an enhanced version of an open-source project by JJRobots.
