Skip to main content
NVIDIA AI Podcast

The Future of Humanoid Robots With 1X's Bernt Bornich - Ep. 259

31 min episode · 2 min read
·
Bernd Bornick

Episode

31 min

Read time

2 min

Topics

Productivity, Leadership, Design & UX

AI-Generated Summary

Key Takeaways

  • Safety Through Low-Energy Design: 1X's tendon-driven robots weigh only 30 kilos but lift 150 pounds by using low gear ratios (0.7-1.2:1 versus 100:1 in industrial robots), reducing internal energy by 10x and enabling safe human interaction and learning through failure.
  • Learning From Failure Strategy: Robots achieve initial task success through teleoperation demonstrations and internet data, then autonomously improve by attempting tasks repeatedly, distinguishing successful attempts from failures, creating a self-improving data flywheel that scales beyond human teleoperation limits.
  • World Models Enable Prediction: World models allow robots to simulate future outcomes based on current state and planned actions, creating probability trees that enable backward search from goals and dramatically improve data efficiency for learning physics and complex manipulation tasks.
  • Consumer Launch Timeline: 1X ships Neo humanoid robots to consumer homes in 2025, capable of vacuuming, tidying, doing laundry, and folding clothes, positioning the product as a developmental journey where customers participate in teaching robots through daily interaction, not a finished solution.

What It Covers

Bernt Bornich, CEO of 1X Technologies, explains how his company builds safe, affordable humanoid robots using tendon-driven systems that learn through reinforcement learning, teleoperation data, and real-world failure to enable autonomous home assistance.

Key Questions Answered

  • Safety Through Low-Energy Design: 1X's tendon-driven robots weigh only 30 kilos but lift 150 pounds by using low gear ratios (0.7-1.2:1 versus 100:1 in industrial robots), reducing internal energy by 10x and enabling safe human interaction and learning through failure.
  • Learning From Failure Strategy: Robots achieve initial task success through teleoperation demonstrations and internet data, then autonomously improve by attempting tasks repeatedly, distinguishing successful attempts from failures, creating a self-improving data flywheel that scales beyond human teleoperation limits.
  • World Models Enable Prediction: World models allow robots to simulate future outcomes based on current state and planned actions, creating probability trees that enable backward search from goals and dramatically improve data efficiency for learning physics and complex manipulation tasks.
  • Consumer Launch Timeline: 1X ships Neo humanoid robots to consumer homes in 2025, capable of vacuuming, tidying, doing laundry, and folding clothes, positioning the product as a developmental journey where customers participate in teaching robots through daily interaction, not a finished solution.

Notable Moment

Bornich describes his robot autonomously answering the door to retrieve a food delivery while he interviewed a job candidate, demonstrating how small automated tasks compound to reclaim the 2.3 hours daily people spend on household chores without interrupting human connection.

Know someone who'd find this useful?

Episode Transcript

Hello, and welcome to the NVIDIA AI podcast. I'm your host, Noah Kravitz. As we move deeper into the age of physical AI, advanced humanoid robots are reshaping industries and enhancing daily life. Advancements in AI models and simulation tools are enabling robots to perform complex tasks with greater dexterity and efficiency, and foundation models are playing a key role in generalizing robot tasks. Here with us to pull the curtain back a little more on the rapidly developing world of humanoid robotics is Bernd Bornick. Bernd is founder and CEO of One X Technologies, a Silicon Valley company that's dedicated to building fully autonomous humanoid robots. Bernd, welcome, and thank you so much for joining the AI podcast. Oh, thank you, Noah. So can we start with a little bit about your journey, how you got into the field? Sure. So to me, this is kind of been a lifelong journey. Right. So as as a kid, I was the kind of kid who picked everything apart to figure out what's inside. I think nothing with motors in it of our kitchen appliances survived in the early days. And, I also just I was very lucky. I grew up with a dad that loved building things. We built soapbox cars in the garage. We went all in, like, welded aluminum frames and chassis. Nice. Nice. And then I discovered computers. Right? And we're back in, like, Commodore '64 and then, like, early, I think it was until February Okay. Like, the first one. But, like, the first kinda, like, computer I had my had my only for me, right, in my room was, like, a April. Okay. And I really got into programming. Right. Mainly due to games and just being part of the mod community, making mods for games Mhmm. Is a big thing. One of my childhood heroes is John Carmack. Right. And, I learned writing code by reading his, Quake code. Mhmm. And then, you know, at some point it clicks and you're just like, wait a minute. I can type code and this thing moves. Right. I like connecting these two realities. Right? Yeah. Yeah. The digital and the physical is, like, it's just magical. It's magic. Yeah. And, yeah, one thing led to another. And very early, I think I was, like, 11, I decided I wanna make humanoid robots. And then I followed the field Okay. Followed the field ever since. Right. Right. So I'm like, I'm the luckiest scholar. Right? I get to do my childhood dream. Every day in the morning, I get up and, like, even now I get up and there's a robot walking around in my house. Right. And it's absolutely magical. That's amazing. So tell us a little bit about one x then. What inspire I mean, you've been talking about your journey inspired by everything you've been doing since you were a kid. But how did the company get started? And maybe you can talk a …

Get the full transcript (6,607 words) + summary by email — free

One-time email with the complete transcript and AI summary of this episode. No account needed.

One email, no spam. We’ll also show you what SignalCast does.

Browse all NVIDIA AI Podcast transcripts →

You just read a 3-minute summary of a 28-minute episode.

Get NVIDIA AI Podcast summarized like this every Monday — plus up to 2 more podcasts, free.

Pick Your Podcasts — Free

Keep Reading

More from NVIDIA AI Podcast

We summarize every new episode. Want them in your inbox?

Similar Episodes

Related episodes from other podcasts

Explore Related Topics

This podcast is featured in Best AI Podcasts (2026) — ranked and reviewed with AI summaries.

You're clearly into NVIDIA AI Podcast.

Every Monday, we deliver AI summaries of the latest episodes from NVIDIA AI Podcast and 192+ other podcasts. Free for one show.

Start My Monday Digest

No credit card · Unsubscribe anytime