给"梦一"(Dream-1)一个有并列抓取器的新双人机器人，将其连接到我们的API上，它可以开始从盒子外执行任务。 没有微调，没有演示从那个机器人，和不需要机器学习的专门知识。
这是向通用机器人智能迈出的重要一步。
今天，"梦想实验室"也以90000M的种子资金从"隐形"中走出，并通过一个公开的API让"梦想一"为全世界人民提供。
01
解决鸡蛋问题
数十年来，机器人一直被困在鸡蛋问题中：机器人在人们想要购买之前需要有用，但使其有用需要来自精确的机器人的数据，只有足够多的人开始使用数据，数据才存在。 梦一号是我们打破这个循环的第一步
自驾车找到了解决这个冷起问题的方法。 汽车从第一天起就变得无自主性，所以数以百万计的人每天驾驶汽车，并生成培训能力越来越强的模型所需的数据。 多数其他机器人从未有过这种优势。
有两件事正在改变
首先，机器人硬件越来越便宜，可以接触到更多的人。 有能力的双人臂搭配现在成本可达2克1.
第二，机器人可能不再需要自己的大数据集才能有用。 如果一个模型能够将零镜头概括到看不见的环境，任务，甚至机器人，那么一个新的机器人就可以从有用的能力开始。
把这些放在一起，飞轮就可以开始了。 便宜的硬件让更多的机器人进入世界。 通用模型使得这些机器人更早有用。 有用的机器人产生更多的数据，这些数据使得模型更适合下一个机器人。
02
廉价廉价机器人的 Cambrian爆炸
机器人硬件比预期的要快参见上面的机器人，其中7个半人造机器人的价格还不到15克，这一价格水平在一年前就已经勉强存在了。 在价格曲线最远的一端，Hugging Face的399Microduck在8月2日下旬发布的4天内售出一万多台。 我们相信机器人会从这些机器人开始起飞
$2,000
双臂相接
从今天起，一个有能力的双臂装置
7
15克以下的半人体
轮子，两只手臂，平行的钳子一年前才存在
$399
Hugging Face 微多克语Name
发布 8月下旬开通。
这是因为他们的买家是消费者、投机者、小团队，而不是企业。 企业买方正在作出电子表格决定。 如果机器人不以成本，速度，或可靠性击败一个人，它就得不到买入；那是需要清除的高杠。 消费者不同。 超过一万人在4天之内支付了399美元，在那和完全有能力的家用机器人之间的某个地方是一个甜点，一个能够承受得起的机器人，一个容易是和有用的机器人，足以在家中获得自己的位置。 一旦机器人到达这个点，我们认为收养开始复合，家里的每个机器人都成为了新的训练数据的来源。 想象一下，两个微小的小孩把你的衣服叠起来，用他们的喙当抓手。
03
开始梦幻实验室的结果
2026年2月，我们的球队发布 DreamZero出道，论文为"推出世界行动模式"3. 此后，社区将WAMs作为机器人学习中最有前途的范式之一。 那时，我们最令人惊讶的结果是，在经过30分钟的YAM机器人数据训练后，我们看到它将零镜头概括为从未见过的任务。 这种概括曾经需要数百甚至数千小时具体化的数据。 如果某个机器人的30分钟数据足以将通用任务知识转移给该机器人，打破"鸡蛋圈"就不再看起来不可能了。 加上上面的硬件波，时间感觉是正确的。 那时我们决定开始梦幻实验室。
经过半年的建设，我们兴奋地分享了一个新的研究突破，这个突破只是通过世界行动模式才得以实现的：零弹孔平面化的早期迹象。
04
介绍梦想1
Dream-1是通过一个公众API提供的第一个世界行动模式，可以在世界各地使用。 从盒子里，它可以控制看不见的机器人在看不见的环境中进行看不见的任务。
04.1
几分钟后开始
我们希望所有拥有机器人的人都能使用通用机器人，而不仅仅是大型实验室。 所以我们设计了"梦一"，尽可能接近插座和游戏。 连接你的机器人，对准API，然后运行。 启动不需要机器学习背景。 每周我们都会运行内部黑客尽可能缩短部署时间开始学习
导入梦
客户端=梦想。 DreamClient( 梦境) (
api key QAPI KEY> (英语).
)
客户端。 policy({"检查点":"梦想拉布斯/梦想-1")}
客户端。 set 观察(观察)
动作=客户端.get action ()
客户端。 close ()
压缩客户端代码
04.2
对机器人零镜头，它从未见过
Dream-1可以将零发一般化为许多双人，并发并发的机器人。 这里有一些我们已经测试。 它甚至可以控制18年前的原始PR2，即通用双人研究机器人发布。 请注意，没有使用具体体现的数据来进行这些推广。
这是首次报道的零射通缩图，用于完全不为人所见的机器人化身。 如果你有一个双手平行的机器人，尝试提示"梦一"，让我们知道它是如何进行的。 零镜头的性能部分取决于你的机器人反动能(IK)解析器，所以我们写了指南来帮助你从中取出最多。 IK向导。 机器人的性能也各不相同。 下面，我们在模拟和真正的机器人上破解零发性能。
下面，我们解释零弹出化的通俗化是如何运作的，它在哪里不足。 然后，我们展示一发一发的学习如何弥合这一差距。
04.3
零射入相的通则如何工作
控制机器人的两种方法：关节或终端效应。 机器人政策通常输出关节角度，它们与一个特定的机器人的身体联系在一起。 梦一可以同样地为它原生地支持的活化而做活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活化活每个拥有两只手臂和平行抓取器的机器人都共享EEF动作空间，而它自己的IK解析器将外形转化为联合指令。 这个共享接口让"梦一"有一个共同的方法来指挥它从未见过的机器人，但是单靠自己还不足以使"零发"的传输工作。
为什么这样有效？梦一透过三相相机来观察世界：头相机和手腕相机每臂相机。 此前关于通用操纵界面(UMI)的研究表明，当每只手臂都使用同一种抓取器时，政策可以将零相机传输到机器人手臂上，而政策只依靠腕相机5. 从手腕的角度来看，机器人看起来完全一样。 但捷径有困难的极限。 只有在抓取器的硬件完全匹配时才有效，并放弃了头相机对整个场景的取景。
世界行动模式取消了这一限制。 一个WAM学会了一起预测视频和行动，所以控制一个机器人，想象那个机器人会做什么，也是同样的问题。 而每个机器人显示的上升方式与像素相同。 头相机看到一个UMI抓取器，一双指抓取器或一臂"梦一"从未遇到过，只是形状在一幕中移动，这使得视频成为了每个机器人类型共享的一款。 如果"梦一"可以预测一个机器人在完成一个任务时会是什么样子，那么它就能产生得到它的行动。 因此它可以控制机器人和UMI一样
04.4
梦一号可以也不能做
领先于发布，Robocurve6，一家测量并向公众报告前沿机器人能力的公益公司，独立评价"梦一". 他们的报告，上面，显示 Dream-1更好，更快，更便宜：一个新的用于机器人控制的Pareto前沿。 它的得分高于次等最佳模型"Opus 5.5"和"Gemini 4 Argon"，每任务尝试以16x更低的成本进行，比"Gemini 4 Argon"和"1.7x"快于最快的"LLM","GPT-6 Astra". 虽然目前LLMs在规划上表现优异，但机器人仍然需要一个快而通用的System 1来行动，这就是"梦一"所构建的。
运行"梦一"要多少钱？. 我们想让你知道在你尝试之前该期待什么运行模型的成本只有梦一号每小时3美元，或者梦一号-快克时2美元。 每一次给模型的呼叫都返回了1.6秒的动作，所以一个小时是2,250个呼叫：约0.0013美元是"梦一"的动作，而0.0009美元是"梦一-一-一-一"的动作。
3美元/小时
梦想 1个
超过小时成本的一切都归你了
2美元/小时
梦一闪起
更快，更轻的模型。
穿越任务我们把Dream-1的表现分成八个任务类别
微调，你的任务与法阿斯。 如果梦一没有完成你关心的任务，收集一些关于你自己机器人的数据，通过FaaS运行，并获得一个为这个任务而设计的自定义模型。
我们希望任何拥有机器人的人都能像前方部署的工程师一样工作：找到一个人需要完成的任务，收集一些数据，使"梦一"适应，并部署。 如果人们会为你机器人的工作付出代价，你将一切维持在小时成本之上。
04.5
一发一发的表演学习
当零发不够时，我们微调 Dream-1为你的机器人。 我们称之为微调-as-a-Service(FaaS).
实际情况是这样的：我们两个伙伴的机器人的数据收集时滞，每人5分钟。
在仅仅这5分钟后，显示与零射出跑的相差相去甚远。 梦一现在更了解机器人的承受力和运动力。
一些浮雕与梦一号已经知道的相距甚远，Dexmate与夏帕的德克塞特手用手来取而代之，取而代之的是取而代之的握手，并取取了它的数据77分。 在YAM上，我们交换了不同的终端效应器来完成这个任务，一个符合要求的抓取器和一个被修改了的刀子抓取器，这需要98分钟的数据。
微调从我们的FaaS Beta合作伙伴的12个机器人中
一发即发的适应性仍然超过零发，所以差距依然存在。 关闭它是我们的主要目标之一：零射得越好，任何新的机器人都越接近工作。
05
展望未来
今天的"梦一"(Dream-1)是双人机器人和平行抓取器的操纵政策。 这是起点。 我们相信一个强大的，一般的机器人基础模型可以扩展到移动操纵者，狡猾的手，和我们尚未想象到的躯体，打开更多人们真正想要机器人做的事情。 机器人不会在第一天被解决，和"梦一"有真正的限制，我们已经尝试透明地显示上面。
机器人仍然被困在一个困难的循环中：每个新机器人或任务都需要新的数据和自定义政策，往往一般化程度有限。 随着"梦一"作为机器人API，我们希望打破这个循环，将机器人智能投入到更多的人手中，因此日常用户，不仅是研究人员，都可以发现通用机器人智能的新应用。
梦一。 公共API
把"梦"1放在机器人上
如果你正在建造机器人，或者让他们去执行真正的任务，我们希望梦一号成为最快的方法，使其有用。 告诉我们你在做什么。
指出和参考文献
- 1MakerMods, Maker Arm：由约2克的双臂相接而成。
- 2Yahoo Tech,Hugging Face的399Microduck机器人已售出一万多台，2026年9月1日：自8月28日预购开通后一万多台。
- 3DreamZero：推出世界行动模型的论文，2026年2月。
- 4LAP还显示浮雕的生命迹象
本文由 AI宝库自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
Give Dream-1 a new bimanual robot with parallel grippers, connect it to our API, and it can start performing tasks out of the box. No fine-tuning, no demonstrations from that robot, and no machine learning expertise required.
This is an important step toward general-purpose robot intelligence.
Today, Dream Labs is also coming out of stealth with $90M in seed funding and making Dream-1 available to people all around the world through a public API.
01
Breaking the chicken-and-egg problem
For decades, robotics has been stuck in a chicken-and-egg problem: a robot needs to be useful before people want to buy it, but making it useful requires data from that exact robot, and that data only exists once enough people start using it. Dream-1 is our first step toward breaking that loop.
Self-driving found a way around this cold-start problem. Cars were useful from day one with zero autonomy, so millions of people drove them every day and generated the data needed to train increasingly capable models. Most other robots never had that advantage.
Two things are changing that.
First, robot hardware is getting cheap enough to reach far more people. A capable bimanual arm setup can now cost as little as $2k1.
Second, a robot may no longer need a large dataset of its own before it can be useful. If a model can generalize zero-shot to unseen environments, tasks, and even robots, a new robot can start with useful capabilities.
Put those together and the flywheel can finally start. Cheaper hardware puts more robots into the world. Generalizable models make those robots useful earlier. Useful robots generate more data, and that data makes the models better for the next robot.
02
The Cambrian explosion of cheap, affordable robots
Robot hardware is getting cheap faster than anyone expected. See the robots above, where 7 semi-humanoid robots cost less than $15k, a price tier that barely existed a year ago. At the far end of the price curve, Hugging Face's $399 Microduck sold more than 10,000 units within 4 days of its launch in late August2. We believe the robotics take-off will start with robots like these.
$2,000
a bimanual arm setup
A capable two-arm setup, as of today.
7
semi-humanoids under $15k
Wheels, two arms, parallel grippers; a tier that barely existed a year ago.
$399
Hugging Face Microduck
Launched late August.
That's because their buyers are consumers, prosumers, and small teams, not enterprises. An enterprise buyer is making a spreadsheet decision. If the robot doesn't beat a person on cost, speed, or reliability, it doesn't get bought; that's a high bar to clear. Consumers are different. 10,000+ people just paid $399 within 4 days for a robot whose main job is to be delightful and cute: it walks, waddles, and roller-skates. Somewhere between that and a fully capable home robot is a sweet spot, a robot affordable enough to be an easy yes and useful enough to earn its place in the home. Once robots hit that point, we think adoption starts to compound, and every robot in a home becomes a source of new training data. Imagine two Microducks folding your laundry, using their beaks as grippers.
03
The result that started Dream Labs
In February 2026, our team released DreamZero, the paper that introduced World Action Models3. Since then, the community has adopted WAMs as one of the most promising paradigms in robot learning. At that time, the most surprising result for us was when after post-training DreamZero on just 30 minutes of YAM robot data, we saw it generalize zero-shot to tasks it had never seen. That kind of generalization used to take hundreds or even thousands of hours of embodiment-specific data. If 30 minutes of data from a given robot was enough to transfer general-purpose task knowledge to that robot, breaking the chicken-and-egg loop no longer looked impossible. Combined with the hardware wave above, the timing felt right. That's when we decided to start Dream Labs.
After six months of building, we're excited to share a new research breakthrough that was only made possible through world action models: early signs of zero-shot embodiment generalization.
04
Introducing Dream-1
Dream-1 is our first World Action Model available through a public API that can be used all around the world. Out of the box, it can control unseen robots for unseen tasks in unseen environments.
04.1
Get started in minutes
We want generalizable robotics to be accessible to anyone with a robot, not just large labs. So we designed Dream-1 to be as close to plug-and-play as possible. Connect your robot, point it at the API, and run. No machine learning background is needed to get started. Every week, we run internal hackathons to keep time-to-deploy as short as possible. Getting started tutorial
import dream
client = dream.DreamClient(
api_key=<API_KEY>,
)
client.policy({"checkpoint": "dreamlabs/dream-1"})
client.set_observation(observation)
action = client.get_action()
client.close()
Condensed client side code
04.2
Zero-shot on robots it has never seen
Dream-1 can zero-shot generalize to many bimanual, parallel-gripper robots. Here are some we've tested. It can even control the original PR2, a general-purpose bimanual research robot released 18 years ago. Note that no embodiment-specific data was used to get these rollouts.
This is one of the first reported zero-shot generalizations to completely unseen robot embodiments.4 If you have a bimanual parallel-gripper robot, try prompting Dream-1 and let us know how it goes. Zero-shot performance depends partly on your robot's inverse kinematics (IK) solver, so we've written a guide to help you get the most out of it. IK guide. Performance also varies across robots. Below, we break down zero-shot performance in simulation and on real robots.
Below, we explain how zero-shot embodiment generalization works and where it falls short. We then show how one-shot embodiment learning closes that gap.
04.3
How zero-shot embodiment generalization works
Two ways to control a robot: joints or end-effectors. Robot policies commonly output joint angles, which ties them to one specific robot's body. Dream-1 can do the same for the embodiments it supports natively, but it can also predict end-effector (EEF) poses: where each gripper should be and whether it should be open or closed. Every robot with two arms and parallel grippers shares that EEF action space, and its own IK solver turns the poses into joint commands. That shared interface gives Dream-1 a common way to command robots it has never seen, but on its own it isn't enough to make zero-shot transfer work.
Why does this work? Dream-1 sees the world through three cameras: a head view and a wrist view on each arm. Prior work on the Universal Manipulation Interface (UMI) showed that policies can transfer zero-shot across robot arms when every arm uses the same gripper and the policy relies only on wrist cameras5. From the wrist's point of view, the robots look identical. But that shortcut has a hard limit. It only works when the gripper hardware matches exactly, and it gives up the head camera's view of the whole scene.
World Action Models remove that limit. A WAM learns to predict video and actions together, so controlling a robot and imagining what that robot will do are the same problem. And every robot shows up the same way: as pixels. The head camera sees a UMI gripper, a two-finger gripper or an arm Dream-1 has never met as nothing more than shapes moving through a scene, which makes video the one representation every robot type shares. If Dream-1 can predict what a robot will look like as it completes a task, it can produce the actions that get it there. That’s why it can control robots with grippers that look nothing like UMI’s, and even entirely new bodies seen through the head camera.
04.4
What Dream-1 can and can't do
Ahead of launch, Robocurve6, a Public Benefit Corporation that measures and reports frontier robotics capabilities to the public, evaluated Dream-1 independently. Their report, above, shows Dream-1 is better, faster and cheaper: a new Pareto frontier for robot control. It scores above the next best models, Opus 5.5 and Gemini 4 Argon, at 16x lower cost per task attempt than Gemini 4 Argon and 1.7x faster than the fastest LLM, GPT-6 Astra. While current LLMs excel at planning, robots still require a fast, general System 1 to act, and that is what Dream-1 is built to be.
How much does it cost to run Dream-1? We want you to know exactly what to expect before you try it. Running the model costs just $3 per hour for Dream-1, or $2 per hour for Dream-1-flash. Each call to the model returns 1.6 seconds of actions, so an hour is 2,250 calls: about $0.0013 an action for Dream-1, and $0.0009 for Dream-1-flash.
$3 / hour
Dream-1
Everything above the hourly cost is yours to keep.
$2 / hour
Dream-1-flash
The faster, lighter model.
Across tasks. We break Dream-1’s performance down into eight task categories, from what it handles well to where it still struggles.
Fine-tune for your task with FaaS. If Dream-1 falls short on a task you care about, you don’t have to wait for our next release. Collect some data on your own robot, run it through FaaS, and get a custom model built for that task.
We want anyone with a robot to work like a forward-deployed engineer: find a task someone needs done, collect a bit of data, adapt Dream-1 to it, and deploy. If people will pay for what your robot does, you keep everything above the hourly cost.
04.5
One-shot embodiment learning
When zero-shot isn't enough, we fine-tune Dream-1 for your robot. We call this Fine-tuning-as-a-Service (FaaS).
Here's what that looks like in practice: timelapses of data collection on two of our partners' robots, 5 minutes each.
After adapting on just those 5 minutes, the difference shows side-by-side with the zero-shot run. Dream-1 now understands a bit better the affordance and kinematics of the robot.
Some embodiments sit much further from what Dream-1 already knows, and closing a gap that large takes more of the robot’s own data. Dexmate with Sharpa dexterous hands grasps with hands in place of grippers, and took 77 minutes of its data. On YAM, we swapped in different end effectors for this task, a compliant gripper and a modified knife gripper, and it took 98 minutes of data.
Across twelve robots from our FaaS beta partners, fine-tuning lifts the language-following score on ten of them:
One-shot adaptation still outperforms zero-shot, so a gap remains. Closing it is one of our main goals: the better zero-shot gets, the closer any new robot comes to working out of the box.
05
Looking forward
Dream-1 today is a manipulation policy for bimanual robots with parallel grippers. It’s a starting point. We believe a strong, general robot foundation model can extend to mobile manipulators, dexterous hands, and bodies we haven't imagined yet, opening up many more of the things people actually want robots to do. Robotics won't be solved on day one, and Dream-1 has real limits, which we've tried to show transparently above.
Robotics is still stuck in a difficult loop: every new robot or task demands new data and a custom policy, often with limited generalization. With Dream-1 as a robotics API, we want to break that loop and put robot intelligence into more people's hands, so everyday users, not only researchers, can discover new applications for general-purpose robot intelligence.
Dream-1 . public API
Put Dream‑1 on your robot
If you're building robots or putting them to work on real tasks, we want Dream-1 to be the fastest way to make them useful. Tell us what you're working on.
Notes and references
- 1MakerMods, Maker Arm: a bimanual arm setup from about $2k. ↩
- 2Yahoo Tech, Hugging Face's $399 Microduck robot has already sold more than 10,000 units, 1 September 2026: more than 10,000 units since pre-orders opened on 28 August. ↩
- 3DreamZero: the paper that introduced World Action Models, February 2026. ↩
- 4LAP also showed signs of life of embodime
Auto-fetched and translated by AI Gem Box. All rights belong to the original author.