Researchers at South Korea’s KAIST have demonstrated a humanoid robot that can push objects weighing up to 35 kg and lift loads of up to 20 kg.
The robot uses learning-based control and visual feedback to improve how it interacts with objects.
They have also showcased its
@TheHumanoidLabs Nice to see someone talking faster robot design, not just arms powered by general software
AMRS + robot arms cover 80% of automation for most orgs, but the boring stuff (conveyors, pick/place, spool holding, inventory binning, etc) need to get designed faster and smarter too
How do we reward the best engineers for the value they create in their designs?
My order:
1) Equity (distributions)
2) Rev share (dicey for CF, need enough margin)
3) profit share (define clearly)
4) Quarter/EOY bonuses (define good metrics)
106K Followers 397 FollowingAsst Prof of CS & EE @Stanford
Co-founder of Physical Intelligence @physical_int
PhD from @Berkeley_EECS, EECS BS from @MIT
602K Followers 3K FollowingNVIDIA Director of Robotics & Distinguished Scientist. Co-Lead of GEAR lab. Solving Physical AGI, one motor at a time. Stanford Ph.D. OpenAI's 1st intern.