Why Do Humanoid Robots Still Struggle With the Small Stuff?
The Quanta Podcast
Quanta Magazine
4.7 • 638 Ratings
🗓️ 31 March 2026
⏱️ 31 minutes
🧾️ Download transcript
Summary
Humanoid robots can run, crawl, and sort objects in flashy demos. So why can’t they reliably climb stairs or open doors? On this episode of The Quanta Podcast, host Samir Patel speaks with contributing writer John Pavlus on why robots still struggle with the messy physics of the real world. This topic was covered in a recent story for Quanta Magazine.
Each week on The Quanta Podcast, Quanta Magazine editor in chief Samir Patel speaks with the people behind the award-winning publication to navigate through some of the most important and mind-expanding questions in science and math.
In this video, Atlas walks, runs and crawls using reinforcement learning. This work was done as part of a research partnership between Boston Dynamics and the Robots and AI (RAI) Institute:
Transcript
Click on a timestamp to play from that location
| 0:00.0 | The word robot comes from Czech, Robota, meaning forced labor, and it dates back to the 1920 play by Carol Chappec, called RUR, which stood for Rossum's Universal Robots, and it was science fiction, and it was a capitalist critique and oh look I see in my newsfeed |
| 0:25.6 | here that Tesla is cutting back on making cars to make the optimist robot to work in factories |
| 0:32.4 | and eventually do chores. Okay, now let's go back to RUR and see how it ends. |
| 0:40.6 | Hmm. The robots develop consciousness and kind of wipe out humanity. And the last living human finds that a couple of the robots have |
| 0:46.5 | fallen in love. All right. Okay, to be fair, Chappex robots were more like biological |
| 0:53.4 | replicants. And this story of the robot |
| 0:56.7 | takeover has been told in countless forms over the years. |
| 1:01.3 | Today if you watch the tech news, there are plenty of humanoid robots wandering around, |
| 1:06.6 | at least in demos, and they're doing some pretty cool things. |
| 1:09.7 | Are they coming? |
| 1:10.7 | Are they already here? |
| 1:18.5 | Welcome to the Quanta podcast where we explore the frontiers of fundamental science and math. |
| 1:23.0 | I'm Samir Patel, editor-in-chief of Quantum Magazine. In a recent essay in Quanta, science writer John Pavlis dug into the state of humanoid robots. |
| 1:33.7 | He looked into the advances of the last 10 years or so, obviously including AI, and found |
| 1:39.6 | that there are still some remaining issues with humanoid robots, and they're pretty fundamental. So |
| 1:44.9 | John's here to walk us through it. Welcome back to the show, John. Hi, thanks. Glad to be back. |
| 1:50.5 | So, John, what's the big idea? Okay, the big idea here, I'll just put it in the words that |
| 1:57.0 | one of my sources use. Robots are still bad, but the bones are good, and it's still hard. |
| 2:03.3 | So that's the take on the state of humanoid robotics. |
| 2:06.8 | Yeah, I want to get to the bottom of this because there are a lot of videos of robots out there, |
| 2:12.1 | and you really have to look at the date on when these videos were made, |
| 2:16.1 | because if you look at ones that are from 2015 or something, |
... |
Please login to see the full transcript.
Disclaimer: The podcast and artwork embedded on this page are from Quanta Magazine, and are the property of its owner and not affiliated with or endorsed by Tapesearch.
Generated transcripts are the property of Quanta Magazine and are distributed freely under the Fair Use doctrine. Transcripts generated by Tapesearch are not guaranteed to be accurate.
Copyright © Tapesearch 2026.