DeepMind robotics team has revealed three new advances to help robots make faster, better, and safer decisions in the wild. The first one includes a system for gathering training data with a “Robot Constitution” to make sure your robot office assistant can fetch you more printer paper. Secondly, Google’s data gathering system, AutoRT, can use a visual language model (VLM) and a large language model (LLM), working hand in hand to understand its environment, adapt to unfamiliar settings, and decide on appropriate tasks. Lastly, DeepMind programmed the robots to stop automatically if the force on its joints went past a certain threshold. It included a physical kill switch human operators can use to deactivate them.
Source: The Verge
Leave a Reply