An update from our robot G1PO

,

Over the past few weeks, our Innovation Hacking Team has successfully trained our Unitree G1 Robot 'G1PO' to walk using Reinforcement Learning techniques. We achieved this solely through the utilization of a self-trained neural network developed by TNG, bypassing the need for the pre-installed locomotion program provided by Unitree. Furthermore, we have integrated the Apple Vision Pro into our operations, enabling us to control 'G1P0' via immersive commands. Our team is now testing the limits of the robot's mobility and agility.