正在加载视频...
视频加载失败
Teamwork makes the dream work. To test multi-robot collaboration with Gemini Robotics 2, we challenged our Apollo and Duo robots to tidy up a messy garage. The high-level reasoning model breaks down what to do, where to go, and identifies the exact moment to hand over control ↓
23,312 次观看 • 3 个月前 •via X (Twitter)
12 条评论
To be truly useful, a robot needs the dexterity that humans take for granted. But asking AI models to coordinate these motions is incredibly complicated. In this demo, we pushed Apollo 2 to master fine motor skills and complete tricky kitchen chores ↓
This is how Gemini Robotics 2 helps @Apptronik’s Apollo 2 use whole body intelligence to pack for a sports game ↓
The exact handoff moment is where these demos usually wobble
The handoff point is where multi-robot systems get interesting. Is that decision based only on task semantics, or does the model also use live confidence, reachability, and robot health signals before transferring control?
The handoff moment is where the coordination gets interesting.
whole body coordination for packing is a good stress test, most manipulation work quietly assumes a static base
apollo and duo hand off garage tasks without a human mid loop
the model's playing foreman here - deciding which robot does what and when to swap, not a person directing traffic. one robot running a script is normal now, two working out who goes next isn't.
Which robot gets blamed when they both decide the other one was supposed to pick it up?
The handoff logic is the interesting part here. I’d love to see how it handles a blocked path or a missing tool without breaking the whole plan.
The handoff moment is the real test here—not just two robots following scripts, but a model deciding when control should move between bodies. I’d score coordination failures and recovery time, too.
the handoff moment is the hard part, most demos skip straight to the pretty grab
![John: "Over in China, they’re doing robot Olympics. They’re doing marathons and all sorts of stuff." Figure founder Brett Adcock: “We look at the distribution of what humans do that is useful, and we [designed our humanoid] to do as much of that as possible.” “These things where we run marathons, or we do backflips, or we do karate moves—they’re not in the main part of the distribution. They don’t matter. And if you really want to size for those, you’re going to build a really expensive and unsafe robot that’s hard to manufacture.” “People want the $10,000 humanoid that can do general-purpose work. We want it to do laundry and dishes and be a companion. I want to ship robots at scale into the workforce to do logistics and healthcare, and build buildings and data centers.” "I don't need [our humanoid] to do backflips to do any of that work. I want robots building other robots."](https://image.24vids.com/tw-2022786577924325714/amplify_video_thumb/2022786433782812673/img/_TrIWe2vwjWaIIhJ.jpg)
