At a press event held Tuesday in San Francisco, Talla gave four main reasons: bandwidth, latency, privacy, and availability. Bandwidth is becoming an issue for cloud processing, he indicated, particularly for video, because cameras in video applications such as public safety are moving to 4K resolution and increasing in numbers. "By 2020, there will be 1 billion cameras in the world doing public safety and streaming data," he said. And availability of the cloud, Talla pointed out, is an issue in many parts of the world where communications are limited.
When the original developer's kit was released a year ago, Michael Houston, the technical lead for the project, told IEEE Spectrum that the system could accommodate knowledge gleaned from deep learning, a method that uses reiterative analysis to discover patterns in masses of data. "Deep learning has different applications," he said. However, in a test drive he conducted last year, Spectrum's Lawrence Ulrich was able to beat Audi's robotic RS7 racecar on a racetrack near Barcelona, in southern Spain. Heaven smiled on him: Ulrich beat the robot car by 4 seconds.