Self-driving cars were supposed to be everywhere by now.

They are not.

And the reason is not what most people think.

In this episode of Automated, Brian Heater speaks with Martial Hebert, Dean of Carnegie Mellon University’s School of Computer Science, about the reality behind decades of robotics and AI development.

Martial has spent more than 40 years at the Robotics Institute and worked on some of the earliest autonomous vehicle systems. From that perspective, the story is not about technology failing.

It is about expectations being wrong.

The core technology for self-driving cars has existed for years. What slowed everything down is something far less visible: validation, safety, and the challenge of proving these systems can operate reliably in the real world.

That gap between “it works” and “it can be trusted” is where most timelines break.

The conversation also explores why physical AI is fundamentally different from the AI most people are familiar with. Unlike software, robots have to operate in unpredictable environments, interact with people, and handle edge cases that cannot be fully simulated.

Martial explains why simulation alone is not enough, and why real-world experimentation is still essential, even when it is slow, expensive, and difficult to scale.

They also discuss the robotics data problem. While large language models benefit from massive amounts of internet data, robotics systems struggle to collect the kind of real-world data they actually need.

Brian and Martial also dig into a deeper idea that often gets overlooked: progress in robotics is not just about better algorithms. It is about building long-term ecosystems of talent, culture, and expertise.

That is part of what turned places like Carnegie Mellon into leaders in autonomy, and why many of today’s breakthroughs are the result of decades of accumulated work.

They also explore the role of DARPA and long-term research funding, not as a way to build products quickly, but as a way to push the limits of what is possible and force entirely new breakthroughs.

This conversation offers a grounded perspective on why progress in AI takes longer than expected and what it actually takes to move from impressive demos to systems that work in the real world.

Connect with Martial Hebert

https://www.linkedin.com/in/martial-hebert-76448756/

Learn more about Carnegie Mellon Robotics

https://www.ri.cmu.edu/

We’d love to hear from you.

Have thoughts or guest suggestions?

Reach us at podcast@automate.org.

You can find the transcript and more episodes of Automated at automated.fm.

Unlock full access to Automated and explore everything automation.

Subscribe today and leave a review on YouTube, Apple Podcasts, and Spotify.

Subscribe to the Automated Newsletter:

https://www.automate.org/automation/newsletter-automation-roundup

You can also find us on:

LinkedIn https://www.linkedin.com/showcase/automated-podcast-by-a3/

Instagram https://www.instagram.com/automatedpod/

Hosted on Acast. See acast.com/privacy for more information.

Martial Hebert on Why Self-Driving Cars Took So Long and What Everyone Got Wrong About AI

Automated with Brian Heater

Martial Hebert on Why Self-Driving Cars Took So Long and What Everyone Got Wrong About AI