DeepMind is helping Waymo evolve better self-driving AI algorithms
Waymo’s self-driving cars now have something in common with the brains that guide regular vehicles: their intelligence comes partly from the power of evolution.
Engineers at Waymo, owned by Alphabet, teamed up with researchers at DeepMind, another Alphabet division dedicated to AI, to find a more efficient process to train and fine-tune the company’s self-driving algorithms.
They used a technique called population-based training (PBT) previously developed by DeepMind for honing video-game algorithms. PBT takes inspiration from biological evolution, by speeding up the selection of machine learning algorithms and parameters for a particular task by having candidate code draw from the “fittest” specimens (the ones that perform a given task most efficiently) in an algorithmic population.
Refining AI algorithms in this way may also help give Waymo an edge. The algorithms that guide self-driving cars need to be retrained and recalibrated as the vehicles collect more data and are deployed in new locations. Dozens of companies are racing to demonstrate the best self-driving technology on real roads. Waymo is exploring various other ways of automating and accelerating the development of its machine learning algorithms.
Indeed, more efficient methods for retraining machine-learning code should allow AI to be flexible and useful in different contexts.
“One of the key challenges for anyone doing machine learning in an industrial system is to be able to rebuild the system to take advantage of new code,” says Matthieu Devin, a scientist at Waymo. “We need to constantly retrain the net and rewrite our code. And when you retrain, you may need to tweak your parameters.”
Modern self-driving cars are controlled by an almost Rube Goldberg combination of algorithms and techniques. Numerous machine learning algorithms are used to spot road lines, signs, other vehicles and pedestrians in sensor data. These work in concert with conventional, or hand-written, code to control the vehicle and respond to different eventualities. Each new iteration of a self-driving system has to be tested rigorously in simulation.
