A self-driving go kart was made with a machine learning method called behavioral cloning. The kart, also called the Teskart, has 3 Logitech C920 webcams. All three cameras are used during data collection and only the middle one is used when self-driving. That camera supplies the visual input the model uses to analyze the scene and choose steering. The steering motor is from a power wheelchair. That motor acts as a giant servo, driven by an Arduino and a Cytron DC motor driver. Position feedback comes from a potentiometer that turns with the motor shaft. The Arduino reads the potentiometer value and PWM signal and uses a PID controller to compute the output. A second Arduino receives the predicted steering angle from Python over serial communication and converts it into a PWM signal for the first Arduino. An onboard laptop records data, trains the model, and evaluates performance.