Human sensory neurons work as a team through a mutual regulation mechanism, amplifying weak signals so people can perceive relevant information in their field of vision, making humans much better than self-driving cars at driving in difficult conditions such as fog, storms and at night; self-driving vehicles, without this regulation mechanism, can become blind to obstacles. A group of scientists from the University of Valencia taught neural networks of AI models to imitate the way human neurons regulate, then subjected them to driving tests in reduced visibility scenarios in virtual simulators. The models trained to imitate humans achieved, even in conditions of thick fog and total darkness, performance that was more than 20% higher than the standard versions.