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.
Read more on the NVIDIA blog >>
AI-Generated Summary
- University of California, Berkeley researchers are using deep learning and NVIDIA GPUs to create robots that adapt to changing environments without human reprogramming.
- Their robot Darwin learned to keep balance on uneven surfaces and rise from the floor to a standing position without being taught.
- GPU acceleration reduced training time from a week on CPU to three hours, with Igor Mordatch now using GPUs hosted in the Amazon Web Services cloud.
- This type of humanoid robot could one day tackle dangerous tasks like handling rescue efforts or cleaning up disaster areas.
Next Steps
- Read the NVIDIA blog post for more details on the deep learning robot research.
Powered by NVIDIA Nemotron. AI-generated content may summarize information incompletely. Verify important information. Learn more
About the Authors
