Why Do Humanoid Robots Still Struggle With the Small Stuff?

About this episode

This episode explores the challenges humanoid robots face in performing everyday tasks despite their advanced capabilities.

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: https://youtu.be/I44_zbEwz_w?si=KuKC34o_PiKs8zJP

People in this episode

Host: Samir Patel

Guest: John Pavlus

Topics covered

• humanoid robots
• robotics
• physics
• AI
• technology

Keywords

• climbing stairs
• opening doors
• messy physics
• reinforcement learning
• Boston Dynamics

Mentioned in this episode

Products: Atlas

More episodes of The Quanta Podcast

• Ecotypes Make the Idea of a Species Even Fuzzier · June 9, 2026 · 27 min
• What Actually Causes Lightning? · June 2, 2026 · 22 min
• Audio Edition: Astrophysicists Find No ‘Hair’ on Black Holes · May 28, 2026 · 13 min
• The AI Revolution in Math Has Arrived · May 26, 2026 · 30 min
• Ice Is Way More Complex Than It Seems · May 19, 2026 · 25 min
• Audio Edition: How Distillation Makes AI Models Smaller and Cheaper · May 14, 2026 · 8 min