Apr 3, 2017

Spam detection in the physical world

Posted by in categories: cybercrime/malcode, food, policy, robotics/AI

We’ve created the world’s first Spam-detecting AI trained entirely in simulation and deployed on a physical robot.

Our vision system successfully flagging a can of Spam for removal. The vision system is trained entirely in simulation, while the movement policy for grasping and removing the Spam is hard-coded. Our detector is able to avoid other objects, including healthy ones such as fruit and vegetables, which it never saw during training.

Deep learning-driven robotic systems are bottlenecked by data collection: it’s extremely costly to obtain the hundreds of thousands of images needed to train the perception system alone. It’s cheap to generate simulated data, but simulations diverge enough from reality that people typically retrain models from scratch when moving to the physical world.

Read more

Comments are closed.