Author

İsmail Özgenç

Intern Engineer

İsmail Özgenç is a 4th-year Electrical and Electronics Engineering student at Bilkent University with a interest for cognitive robotics and machine learning, particularly in reinforcement learning. İsmail has worked on projects like the BBT Maze Solver, developed at Acrome, which utilizes reinforcement learning to guide a ball through a maze using the Ball Balancing Table (BBT). Additionally, İsmail has developed the BBT Oscillation Generator, which utilizes the same table to create controlled oscillations.

Blog Posts

Automatic Control

Min

Automatic Control

Ball Balancing Table Maze Solver - Reinforcement Learning

In this project, we investigate the application of PID control and Q-learning algorithms to the Ball Balancing Table (BBT) in order to solve a maze. An open-source tool called the BBT makes it possible to experiment with control systems directly. The device can guide a ball through a maze by adjusting the tilt of the table, imparting important knowledge about reinforcement learning, control theory, and feedback systems. The table's orientation is adjusted by using a PID controller in response to real-time feedback from the ball's position. A matrix of 0s and 1s with open paths and walls, respectively, is used to depict the maze. The system associates movements with the Q-learning reinforcement learning algorithm to learn how to move the ball through the maze.

Min

Author

İsmail Özgenç

Blog Posts

Ball Balancing Table Maze Solver - Reinforcement Learning

Discover Acrome