This project centers on developing a low-power analog spiking neural network (SNN) to control an autonomous, line-following electric vehicle. The team first verified the behavior of a digital FPGA-based SNN, then replicated its function using a breadboard-based analog circuit. An Arduino was used to interpret spike frequency data from the SNN somas and convert it into motor control signals. The system responds in real time, directing the vehicle based on left and right neural activity.


This project addressed the challenge of validating and replicating the behavior of a line-following electric vehicle (EV) originally controlled by an FPGA-based Spiking Neural Network (SNN), using a newly developed analog SNN system. The problem centered