Stanford autonomous car learns to handle unknown conditions

Shelley, Stanford’s autonomous Audi TTS, performs at Thunderhill Raceway Park

Researchers from Chris Gerdes' Dynamic Design Lab have developed a neural network that integrates past driving experiences from driving trials from dry roads and under snowy conditions. The neural network system outperformed the physics-based system in both high-friction and low-friction scenarios and did particularly well in situations that mixed these two conditions.