RT-2 is a vision language model fine tuned on the current vision input and actuator positions as the output. Google uses a bunch of TPUs to produce a full response at a cycle rate of 3 Hz and the VLM has learned the kinematics of the robot and knows how to pick up objects according to given instructions.
Given the current rate of progress, we will have robots that can learn simple manual labor from human demonstrations (e.g. Youtube as a dataset, no I do not mean bimanual teleoperation) by the end of the decade.
Given the current rate of progress, we will have robots that can learn simple manual labor from human demonstrations (e.g. Youtube as a dataset, no I do not mean bimanual teleoperation) by the end of the decade.