FRESH

Hacker News

GEN-0 / Embodied Foundation Models That Scale with Physical Interaction

65 points by jackdoe

by blueblisters

1 subcomments

Kinda genius to scale exoskeleton data collection with UMI grippers when most labs are chasing "general" VLMs / VLAs by training on human demonstration videos.
Imo the latter will be very useful for semantic planning and reasoning, but only after manipulation is solved.
A ballpark cost estimate -
- $10 to $20 hourly wages for the data collectors
- $100,000 to $200,000 per day for 10,000 hours of data
- ~1,500 to 2,500 data collectors doing 4 to 6 hours daily
- $750K to $1.25M on hardware costs at $500 per gripper
Fully loaded cost between $4M to $8M for 270,000 hours of data.
Not bad considering the alternatives.
For example, teleoperation is way less efficient - it's 5x-6x slower than human demos, and 2x-3x more expensive per hour of operator time. But could become feasible after low-level and mid-level manipulation and task planning is solved.

by amluto

0 subcomment

I’m curious how they prompt the model or otherwise tell it what its goal is. They seem to suggest some language processing — perhaps they’re starting with a multimodal text + vision LLM?

by tyushk

1 subcomments

If it really is fully autonomous, that first video is insane. I struggle to put those little tags into the slot in the box sometimes, and I'm pretty sure I'm human, but the bot gets it on the first attempt.