When Self-Driving Car Meets Neural Network System
2019-04-08 17:33 Monday
Before the technology enters a safer level, self-driving cars have to always run at limited speeds, and most autonomous vehicles currently in development are usually tested in public roads.
But can you imagine testing the self-driving car on a race course against a real race car driver? A team of researchers from Stanford University just did that to find out if self-driving cars can do as well as human under extreme driving environment.
A mechanical engineering graduate student named Nathan Spielberg at Stanford and his team created a neural network that is patterned on the same networks found in human brains. This neural network, equipped with 200,000 motion samples, can control self-driving cars at high-speeds and low-friction maneuvers.
To test the real-world driving capability of autonomous cars, the team then brought two test vehicles from Stanford to Thunderhill Raceway in Sacramento Valley. One is a Volkswagen GTI called Niki, and the other is an Audi TTS called Shelley.
Shelley is controlled by a physics-based autonomous system that already contains information about the race track, including the entire course and conditions. When compared to the performance of a skilled amateur driver who took the same 10 consecutive trials as Shelley, both showed similar lap times.
Niki is loaded with the team's neural network system. "Niki performed similarly running both the learned and physics-based systems, even though the neural network lacked explicit information about road friction. In simulated tests, the neural network system outperformed the physics-based system in both high-friction and low-friction scenarios. It did particularly well in scenarios that mixed those two conditions." said a researcher of the study.
The researchers said that the results of the tests were encouraging, but they stressed that the new neural network still needs further study, as it "does not perform well in conditions outside the ones it has experienced."