Robots Learn to Move: How Xiaomi Is Teaching Machines to Think
Hey everyone! Welcome back to "Learn English with Podcasts." I'm Mike.
And I'm Sarah! Today we're talking about something really cool — robots that can learn to move and do things in the real world.
That sounds like science fiction, but it's actually happening right now. Xiaomi just released a project called Xiaomi-Robotics-1. It's a foundation model for robots.
Foundation model 是一种大型预训练模型，可以应用于多种任务。类似 GPT 在语言领域的角色，机器人基础模型也能处理各种操控任务。
A foundation model for robots? What does that mean exactly?
Think of it like this. In language AI, we have models like ChatGPT that can do many things — answer questions, write stories, translate languages. A robot foundation model is similar, but for physical actions.
So instead of learning to write text, the robot learns to move objects, open doors, fold clothes?
Exactly. And what makes this special is the data. Xiaomi trained this model on over 100,000 hours of real-world robot data. That's a huge amount.
Pre-training 指模型在大量数据上进行初步训练，学习通用能力，之后再针对具体任务做微调。
100,000 hours? That's like working 24 hours a day for over 11 years!
Right. And it covers more than 1,700 different scenarios — homes, offices, factories, even outdoor spaces.
How did they collect so much data? Did they have thousands of robots working all day?
Sort of. They used something called embodiment-free data. It's captured with a special device called UMI — a handheld robot controller. A human operator moves the controller, and the robot records the motion.
Embodiment-free 意味着数据不绑定特定机器人形态，可以用于训练不同类型的机器人。
Oh interesting. So the data isn't from one specific robot, it's more general. That makes sense for a foundation model.
Exactly. Then in a second stage, they use real robot data to teach the model how to actually control physical robots. This is called post-training.
What kind of tasks can the robot do after training?
All sorts of things. Tidying a sofa, sorting shoes in a cabinet, putting kitchen items away, packing suitcases. It can even do things like refill a printer or load laundry into a washing machine.
That's impressive. And how well does it work?
Really well. When they gave it less than 10 hours of training per new task, it already achieved a 75% success rate. With 40 hours of training, it reached 85%.
Success rate 是成功率，表示任务完成的百分比。75% 意味着每 100 次尝试有 75 次成功。
And compared to other robot models?
It beats the competition. On simulation benchmarks — that's like virtual tests — Xiaomi-Robotics-1 scored the highest on all four major tests. One test showed a 58% improvement over the second-best model.
Why does having more data and a bigger model help so much? Is there something special about how they trained it?
Yes. They found something called scaling behavior. As the model gets bigger and sees more data, it gets consistently better. The improvement doesn't slow down — it keeps going up.
Scaling behavior 指模型性能随数据和参数规模增长而稳定提升的现象，是大模型的关键特性。
That's encouraging. It means there's still a lot of room to improve.
And here's what's really practical about this. The model can learn new tasks with very little data. If you want it to learn a brand new task, you only need a few hours of demonstrations.
Demonstrations meaning someone shows the robot how to do the task?
Right. The human performs the task while the robot watches and records. Then the model learns from those examples. It's like teaching a child by showing them how to do something.
So what does this mean for the future? Will we all have robot helpers at home?
We're getting closer. This kind of foundation model is a big step. Instead of programming each robot task separately, you train one general model that can adapt to many situations.
It's like the difference between learning one recipe and learning how to cook in general. A general cooking skill lets you handle any recipe.
Great analogy. And because the model scales well, as more data becomes available and computers get more powerful, these robots will keep getting better.
I'm excited about this. It feels like we're entering a new era where robots can actually be useful in everyday life.
Me too. Well, before we wrap up, let's review today's vocabulary.
First, "foundation model." A foundation model is a large AI model trained on lots of data that can be adapted to many different tasks.
"Pre-training" is the first stage of training a model on a huge dataset to learn general skills.
"Post-training" comes after pre-training. It fine-tunes the model for specific tasks or environments.
"Scaling behavior" means that as a model gets bigger and uses more data, its performance keeps improving.
"Embodiment-free" describes data that isn't tied to one specific robot. It can be used to train different types of robots.
"Demonstration" means showing someone how to do something by doing it yourself.
Great job today, everyone! Thanks for listening to "Learn English with Podcasts." See you next time!
Bye-bye!