Reward AI

Frontier Intelligence for Any Robot

[Reward AI @RewardAI_]

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

[Reward AI @RewardAI_]

We stress test OM-1 on last-mile delivery for packages from Amazon, Walmart, DHL, etc in different positions and orientations. Our model can reactively adjust, and let humanoids climb, navigate together with whole-body approaching, and hold packages firmly while climbing down.

[Reward AI @RewardAI_]

We deploy OM-1 on more humanoid tasks in both indoor and outdoor environments. OM-1 can power humanoids to do useful things robustly that other models or form factors cannot.
- last-mile delivery from a Cybertruck
- manipulation on stairs

[CyberRobo @CyberRobooo]

Beating Amazon to the punch on last-mile delivery,haha

Humanoid delivery workers will soon be on the job.

a humanoid robot hops onto a Cybertruck, grabs a package, and places it at the doorstep.

good demo

---
This also explains why humanoid robots are needed.

[Rohan Paul @rohanpaul_ai]

imo, the the impressive part here is grip stability during locomotion, since every step down jolts the load in the hands.

also stairs are turning into one of the most useful test benches in humanoid robotics.

Their OM-1 model here learns from people wearing a sensorized glove that records hand pose, touch and images, with no teleoperation or on-robot demonstrations.

[Yanjie Ze @ZeYanjie]

This video exactly shows why we need bipedal humanoid robots (physical labor in very unstructured envs)

[Chen Wang @chenwang_j]

Excited to show OM-1 taking on last-mile delivery! From picking up packages to carrying them down, it coordinates the whole body and adapts on the fly. We’re pushing into more tasks and environments behind the scenes. More to come!

[Wenlong Huang @ CoRL 2026 @wenlong_huang]

Very impressive! The reactiveness in package handling shows the importance of pushing tracking to the limit in data collection to capture the subconscious human behaviors!

[Zipeng Fu @zipengfu]

We deployed OM-1 across an expanding range of humanoid tasks, both indoors and outdoors.

From last-mile delivery out of a Cybertruck to manipulation on stairs, OM-1 enables humanoids to reliably tackle useful real-world tasks that other models or form factors struggle with.

[Reward AI @RewardAI_]

Our website: https://t.co/RqiF20DBwd
More details about OM-1 can be found in the following post: https://t.co/C4th6NI22F

[Reward AI @RewardAI_]

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

[Reward AI @RewardAI_]

We deploy OM-1 on more humanoid tasks in both indoor and outdoor environments. OM-1 can power humanoids to do useful things robustly that other models or form factors cannot.
- last-mile delivery from a Cybertruck
- manipulation on stairs

[Reward AI @RewardAI_]

OM-1 can power humanoids to grasp different objects on stairs from different positions and orientations with feet standing on the same or different stair treads.

[Mengyue Yang @Mengyue_Yang_]

Efficiency will be the next trending?

[Ilir Aliu @IlirAliu_]

.@RewardAI_ came out of stealth yesterday with OM-1, a robot foundation model trained entirely from human demonstrations.

The part I find interesting is how they collect the data.

Instead of teleoperating a robot, a person wears a device called the Omnibody Hand and simply does the task themselves.

Pick something up, fold laundry, mix a drink, package a phone, or plug and unplug cables.

The system records the human hand motion, tactile information, proximity, vision and position. That data can then be used to train OM-1 to control different robot bodies.

Reward calls the idea:

“One Model, One Data Interface, Any Body.”

According to the company, a new task can be learned from less than 30 minutes of human demonstration data, without collecting additional robot data.

The videos are worth watching.

They show four robot arms packaging a phone, robots folding laundry and mixing cocktails, an arm unplugging an Ethernet cable, and early experiments with humanoids.

Some of the longer tasks finish in under 30 seconds, in real time.

There is also some history behind this.

Reward AI builds on DexCap, work that came out of Stanford in 2024 around capturing human dexterous manipulation and transferring it to robots. @chenwang_j , C. Karen Liu and Li Fei-Fei were among the researchers involved.

I think the bigger bet here is about the data layer.

Robot hardware is changing quickly. If collecting training data means teleoperating every new robot body for thousands of hours, scaling gets expensive fast.

Reward is betting that you can collect much of that knowledge from humans instead, then transfer it across different embodiments.

That could become quite valuable if it works.

For now, we only have the launch material. There is no paper or open model yet, and Reward has not published the kind of large-scale success-rate data needed to judge robustness.

Still, this is one of the more interesting approaches I’ve seen to the robotics data problem recently.

Source: https://t.co/tYyhp90zGn

——

Weekly robotics and AI insights.
Subscribe free: https://t.co/9Nm01QUcw3

[CyberRobo @CyberRobooo]

Honestly, watching robot bartenders, robot installers, and humanoid assistants actually get work done autonomously is way more interesting than sitting around worrying about the dangers of AI.

They’re already moving fast and smoothly. Desktop manipulation tasks seem almost effortless, and they look pretty close to being ready for fast customer order fulfillment.

[Raphael cohen @cohenrap]

Why isn't laundry folding the first frame? 😍😍

[Afiz ⚡️ @itsafiz]

Turning a nut calls for a different kind of control than shaking a cocktail. The range from quick arm movements to careful finger work is pretty compelling here.

[Peter Stone @PeterStone_TX]

Congrats @yifengzhu_ut and colleagues on impressive progress!

[Minghuan Liu @ericliuof97]

The speed is seriously impressive — I can only imagine how much hard work went on behind the scenes. Huge congrats to the team on the release!

[Shaoxiong (Shawn) Wang @ShaoxiongW]

Super impressive! The co-design of mechanics, sensing, and data are fantastic, and the policy is incredibly dynamic and smooth! Living the dream toward human-level dexterity! Big congrats to @chenwang_j, @zipengfu and the team!