PBMin is a Pole Balancing Mini-robot. It utilizes a 36 node neural network that learns to balance a pole. The pole is attached to a variable resistor to sense pole angle and two infrared sensors to measure cart position.
Dean Hougen, John Fischer, and Deva Johnam, "A neural network pole-balancer that learns and operates on a real robot in real time," Proceedings of the MLC-COLT Workshop on Robot Learning, 73-80, 1994. Abstract and full paper available.
Look at our other Mini-Robots.