
"Atlas, the humanoid robot famous for its parkour and dance routines, has recently begun demonstrating something altogether more subtle but also a lot more significant: It has learned to both walk and grab things using a single artificial intelligence model. What is more, the robot's single learning model is showing some tantalizingly emergent skills, like the ability to instinctively recover when it drops an item without having been trained to do so."
"The single model used to control Atlas is fed images from the robot's visual sensors, proprioception data from bodily sensors (which give it a continuous sense of its position and movement), and language prompts related to different actions. The model is shown examples of Atlas performing a range of tasks using a mix of teleoperation, simulation, and demonstration videos. The resulting large behavior model (LBM) controls the humanoid robot in a more natural-seeming way."
"This is different from the norm: robots equipped with the ability to learn would usually rely on one model to walk and jump and another to grasp items. The feet are just like additional hands, in some sense, to the model, says Russ Tedrake, a roboticist at the Toyota Research Institute and the Massachusetts Institute of Technology, who led the current work. And it works, which is just awesome."
A single large behavior model (LBM) learns to control both arms and legs of the humanoid Atlas using multimodal inputs including camera images, proprioception, and language prompts. Training combines teleoperation, simulation, and demonstration videos to teach a range of tasks. The unified policy treats feet like additional manipulators, enabling coordinated whole-body actions rather than separate locomotion and manipulation controllers. The LBM produces more natural movement, such as repositioning legs to rebalance when reaching low. The model exhibits emergent abilities, for example bending to recover a dropped object without explicit training. Boston Dynamics and the Toyota Research Institute collaborated on the system.
Read at www.wired.com
Unable to calculate read time
Collection
[
|
...
]