- Vehicle agents trained within simulation for vision-based lane centering.
- Using reinforcement learning.
- Using Unity ML Agents platform.
- Uses a 50x50 px greyscale image of rendered lanes, forward speed, lateral speed, and yaw rate, as input to the neural network.
- Neural network output is steering and accel / braking actions.
- Arrow keys when manual torque, and steer override checkboxes are toggled.
