RT-2, short for Robotics Transformer 2, is a cutting-edge model that harnesses the power of a Vision-Language Models VLMs 55B to enhance robotic control. This model represents a significant leap in the field of robotics, demonstrating how web-scale pre-training can be used to improve the generalization performance of robotic systems.
Vision Language Models further fine-tuned with a robotics data set to a VLA model. A Vision-Language-Action model for advanced robotics.
#ai
#robotics
#explained
8 Comments