Cofounder and CEO @RewardAI_ | Past: Stanford PhD, Google DeepMind, CMU
Palo Alto, CA
- Tweets 442
- Following 1,321
- Followers 14,265
- Likes 1,872
Pinned Tweet
Mobile ALOHA's hardware is very capable. We brought it home yesterday and tried more tasks! It can:
- do laundry👔👖
- self-charge⚡️
- use a vacuum
- water plants🌳
- load and unload a dishwasher
- use a coffee machine☕️
- obtain drinks from the fridge and open a beer🍺
- open doors🚪
- play with pets🐱
- throw away trash
- turn on/off a lamp💡
Project website: mobile-aloha.github.io/
Co-lead @tonyzzhao, advised by @chelseabfinn
(amazing photographing from @qingqing_zhao_ )
313
1,625
6,804
2,983,882
it's always fun to see robots playing soccer. still remember i accidentally tackled someone pretty hard in my last soccer match at cmu iykyk😜
The only AGI on Earth emerged after billions of years of "physical self-play". Robots won't be any different.
This method scales, and we will scale it.
1
2
19
4,896
Zipeng Fu retweeted
this reminds me of classic cascaded control: the outer loop outputs setpoints or trajectories, while the inner loop runs much faster and handles the low-level dynamics. For fast actions, waypoints alone aren’t enough—velocities and contact feedback matter too. Impedance control is a useful analogy: instead of rigidly following a path, the robot responds to contact like a spring and damper. IMO, getting this interaction right is one of the keys to fast, smooth motion.
a big challenge in building a generalist robot is the outer loop: mapping language& images into possible trajectories. A lot of the attention in robot AI goes there and stops there. RewardAI says that picking a good trajectory is only part of the problem; executing it smoothly when contact and loads change is just as important. The team is very serious about robotics, impressive and congrats.
Introducing OM-1, our first robot foundation model, zero-shot generalizing to any robot: table-top arms, industrial arms and humanoids.
- learned directly from human manipulation data
- no teleop/robot data
- close to human-level dexterity and efficiency
- multi-robot collab
1
12
107
10,588
Zipeng Fu retweeted
Amazing!!!
Introducing OM-1, our first robot foundation model, zero-shot generalizing to any robot: table-top arms, industrial arms and humanoids.
- learned directly from human manipulation data
- no teleop/robot data
- close to human-level dexterity and efficiency
- multi-robot collab
3
14
1,747
Zipeng Fu retweeted
daaamn, just realised this is on 1x speed
smoooth
Introducing OM-1, our first robot foundation model, zero-shot generalizing to any robot: table-top arms, industrial arms and humanoids.
- learned directly from human manipulation data
- no teleop/robot data
- close to human-level dexterity and efficiency
- multi-robot collab
9
47
627
70,453
Zipeng Fu retweeted
Achieving human-level speed execution is something that Astra can never achieve. Congrats to @zipengfu and the team!
Introducing OM-1, our first robot foundation model, zero-shot generalizing to any robot: table-top arms, industrial arms and humanoids.
- learned directly from human manipulation data
- no teleop/robot data
- close to human-level dexterity and efficiency
- multi-robot collab
4
6
26
3,270
Zipeng Fu retweeted
Wow
Introducing OM-1, our first robot foundation model, zero-shot generalizing to any robot: table-top arms, industrial arms and humanoids.
- learned directly from human manipulation data
- no teleop/robot data
- close to human-level dexterity and efficiency
- multi-robot collab
6
11
218
43,325
Zipeng Fu retweeted
Don't miss this. The ChatGPT moment of robotics is near.
We built Omnibody Hand around function: useful contact points, in-hand reorientation, and smooth transitions between precision and power grasps. Its compact 7-DoF design combines thumb-index dexterity with coordinated finger motion for power grasps.
7
26
5,309
This is huge! 🤯
Reliance on real robot data and cross embodiment are big issues of robotics action models! Super excited to see OM1 solving both of them!
The motion is also fast and looks smart!
Great work @zipengfu @chenwang_j!
Introducing OM-1, our first robot foundation model, zero-shot generalizing to any robot: table-top arms, industrial arms and humanoids.
- learned directly from human manipulation data
- no teleop/robot data
- close to human-level dexterity and efficiency
- multi-robot collab
11
25
155
700,827
Zipeng Fu retweeted
This is really good; very difficult task for a robot
We also tested OM-1 on a deceptively hard task: unplugging an Ethernet cable. Unlike USB, Ethernet connectors lock firmly in place and release only when the latch is pressed very precisely. OM-1 reliably solves this fine-grained manipulation task.
12
10
197
25,977
Zipeng Fu retweeted
Smoothest manipulation policy at this dexterity level I ever seen, almost feel like an industrial arm!
Also the WBC is very nice and natural, really wish to see more.
Congrats @zipengfu @chenwang_j
Introducing OM-1, our first robot foundation model, zero-shot generalizing to any robot: table-top arms, industrial arms and humanoids.
- learned directly from human manipulation data
- no teleop/robot data
- close to human-level dexterity and efficiency
- multi-robot collab
1
2
22
2,079
Zipeng Fu retweeted
Really cool stuff! Huge congratulations to the team @zipengfu @chenwang_j @yifengzhu_ut behind this. It’s great to see strong academic research making such meaningful progress in robotics!
Introducing OM-1, our first robot foundation model, zero-shot generalizing to any robot: table-top arms, industrial arms and humanoids.
- learned directly from human manipulation data
- no teleop/robot data
- close to human-level dexterity and efficiency
- multi-robot collab
3
9
55
7,952
Zipeng Fu retweeted
Really cool to see the smooth motion and it's quite impressive that this is achieved without teleop data. Congrats @chenwang_j @zipengfu and team!
Introducing OM-1, our first robot foundation model, zero-shot generalizing to any robot: table-top arms, industrial arms and humanoids.
- learned directly from human manipulation data
- no teleop/robot data
- close to human-level dexterity and efficiency
- multi-robot collab
2
4
11
1,327
Zipeng Fu retweeted
The movement looks soooo smooth!! Big congrats to @chenwang_j @zipengfu @yifengzhu_ut et al. at @RewardAI_ on the release!
Introducing OM-1, our first robot foundation model, zero-shot generalizing to any robot: table-top arms, industrial arms and humanoids.
- learned directly from human manipulation data
- no teleop/robot data
- close to human-level dexterity and efficiency
- multi-robot collab
4
16
1,692
Zipeng Fu retweeted
Real-world deployment needs real-world speed! ⚡️ Love the speed and smoothness — congrats!
Introducing OM-1, our first robot foundation model, zero-shot generalizing to any robot: table-top arms, industrial arms and humanoids.
- learned directly from human manipulation data
- no teleop/robot data
- close to human-level dexterity and efficiency
- multi-robot collab
5
26
1,759
Congratulations @zipengfu and @RewardAI_ team!
Introducing OM-1, our first robot foundation model: zero-shot generalizing across table-top arms, industrial arms, and humanoids.
- Learned directly from human manipulation data
- No teleop or robot data
- Near human-level dexterity and efficiency
- Multi-robot collaboration
2
2
7
1,773
Zipeng Fu retweeted
it's 1x speed 🤯
Introducing OM-1, our first robot foundation model, zero-shot generalizing to any robot: table-top arms, industrial arms and humanoids.
- learned directly from human manipulation data
- no teleop/robot data
- close to human-level dexterity and efficiency
- multi-robot collab
2
4
15
2,831
Zipeng Fu retweeted
Congratulations! The policy looks great
Introducing OM-1, our first robot foundation model: zero-shot generalizing across table-top arms, industrial arms, and humanoids.
- Learned directly from human manipulation data
- No teleop or robot data
- Near human-level dexterity and efficiency
- Multi-robot collaboration
1
2
19
3,994
Zipeng Fu retweeted
Extremely excited about this release! I saw the system in action at @RewardAI_ and could hardly believe what it was capable of. The team really cooked. Congrats, @chenwang_j and @zipengfu!
Introducing OM-1, our first robot foundation model, zero-shot generalizing to any robot: table-top arms, industrial arms and humanoids.
- learned directly from human manipulation data
- no teleop/robot data
- close to human-level dexterity and efficiency
- multi-robot collab
2
12
100
11,684
Zipeng Fu retweeted
Very cool that it’s from human manipulation and not teleop. Robotics is making fast progress.
Introducing OM-1, our first robot foundation model, zero-shot generalizing to any robot: table-top arms, industrial arms and humanoids.
- learned directly from human manipulation data
- no teleop/robot data
- close to human-level dexterity and efficiency
- multi-robot collab
5
9
88
16,603