Google DeepMind recently announced Robotics Transformer 2 (RT-2), a vision-language-action (VLA) AI model for controlling robots. RT-2 uses a fine-tuned LLM to output motion control commands. It can perform tasks not explicitly included in its training data and improves on baseline models by up to 3x on emergent skill evaluations.
This is a companion discussion for the article “Google DeepMind Announces LLM-Based Robot Controller RT-2 - https://www.infoq.com/news/2023/10/deepmind-robot-transformer/” submitted on the community's news feed.
Reply to this topic to share your thoughts on this article.