SLAM: The purpose-built chip at 80 frames per second while consuming only 240mW. The chip was made up of three key parts. One was a convolutional neural network that picked out features to use as landmarks from images as they streamed in. Another was an accelerator that matched the landmarks from frame to frame. The third refined the robot’s trajectory over multiple frames. Tested on a standard automotive 1-kilometer drive recording, it was 97.9% accurate.
from Tumblr http://doronelinav.tumblr.com/post/183352240254