Inside Waymo’s strategy to grow the best brains for self-driving cars
Waymo, the self-driving unit of Alphabet, is the only company in the world to have fully driverless vehicles on public roads today.
The company asserts that its cars have the most advanced brains on the road today thanks to a head start in AI investment, strategic acquisitions by sister company Google, and a close working relationship with the tech giant's in-house team of AI researchers
Waymo's engineers are modeling how cars recognize objects in the road, how human behavior affects how cars should behave, and they're using deep learning to interpret, predict, and respond to data accumulated from 6 million miles driven on public and 5 billion driven in simulation.
In March, a 49-year-old woman was struck and killed by a self-driving Uber vehicle while crossing the street in Tempe, Arizona.
A few weeks later, the owner of a Tesla Model X died in a gruesome crash while using Autopilot, the automaker’s semi-autonomous driver assist system
Meanwhile, the public is growing increasingly skeptical of the safety of driverless vehicles
In the midst of all this uncertainty, Waymo invited me out to its headquarters in Mountain View, California, for a series of in-depth interviews with the company's top humans in artificial minds.
ImageNet started as a poster from Princeton University researchers, displayed at a 2009 conference on computer vision and pattern recognition in Florida
It grew into an image dataset, then a competition to see who could identify the most images with lowest error rate
Around 2011, the error rate was about 25 percent, meaning one in four images were being identified incorrectly by the teams' algorithms
A big shift was going from neural nets that were quite shallow (two or three layers) to the deep nets (double-digit layers)
The biggest breakthrough was in 2012, when AI researcher Geoffrey Hinton and his two graduate students, Ilya Sutskever and Alex Krizhevsky, showed a new way to attack the problem: a deep convolutional neural network to the ImageNet Challenge that could detect pictures of everyday objects
This led to Google acquiring Hinton’s company DNNresearch
Problems emerged almost immediately: the new system was making too many errors, mislabeling cars, traffic signals, and pedestrians
Google began applying the technique to other parts of the project including prediction and planning
Other car and tech companies have already caught on to the importance of machine learning, and Waymo's data may be too specific to extrapolate to a global scale.
AI and machine learning are essential to self-driving cars, but how long can they last?
A natural consequence of improvements in AI is that big head-starts like Waymo’s are less significant as they have been
Each additional mile that Waymo accrues needs to be interesting for it to be relevant to the process of training the neural networks
Dolgov is sitting in one of X's conference rooms, whiteboard marker in hand, MacBook Pro splayed before him, asking me to describe to him the difference between Garfield and Odie.
Before I can stammer out a reply, Dolgov keeps going: "If I give you a picture, and I ask you "is it a cat or a dog," you will know very quickly."
This type of question is well-suited for deep learning algorithms
It's one thing to come up with a bunch of basic rules and parameters, but teaching a computer to distinguish between different types of traffic signs is much easier
Waymo uses an automated process and human labelers to train its neural nets
After they've been trained, these giant datasets also need to be pruned and shrunk so they can be deployed in the real world in Waymo's vehicles
This process, akin to compressing a digital image, is key building the infrastructure to scale to a global system.
The future of AI at Waymo isn't sentient vehicles. It's in cutting-edge research like automated machine learning, in which the process of building machine learning models is automated.
Waymo uses Google's data centers to train its neural nets, using a high-powered cloud computing hardware system called "tensor processing units."
Information Source: The Verge
