For helper robots, the smallest things can be the hardest to grasp

Today, robots by and large exist in industrial environments, and are painstakingly coded for specific tasks. What if there was a better way to communicate with learning robots so they can help us? Researchers and engineers at Google Research and Everyday Robots are working together to combine the best of machine learning language models with helper robots that can complete complex and abstract tasks like ‘cleaning up a spilled drink.’

Resources:

Watch episodes of Meet A Google Researcher → https://goo.gle/MeetAGoogleResearcher

Watch episodes of ResearchBytes → https://goo.gle/ResearchBytes

Learn more → https://g.co/research/palm-saycan

Subscribe to the Google Research channel → https://goo.gle/GoogleResearch

What is PaLM what is SayCan how robotics is grounded in language models getting started with language models for robotics what are robotics language models what is Everyday Robots the power of language model research for robotics language models robotics research large language models Google Research PaLM SayCan robotics