University of California, Berkeley researchers are using deep learning and NVIDIA GPUs to create a new generation of robots that adapt to changing environments and new situations without a human reprogramming them.
Their robot “Darwin” learned how to keep his balance on an uneven surface – and GPUs were essential for learning of this complexity.
“If we did the training on CPU, it would have required a week. With a GPU, it ended up taking three hours,” said Igor Mordatch, who is now using GPUs hosted in the Amazon Web Services cloud.
This type of humanoid robots could one day tackle dangerous tasks like handling rescue efforts or cleaning up disaster areas.