In ep 61 of Automate It, Stefan and Ilia dive headfirst into robot subversion hoodies, self-cleaning backyards, and the philosophical sinkholes of the Three Laws of Robotics. They explore why "don't hurt humans" is harder to code than it sounds, the limits of common sense in machine learning, and how old sci-fi still haunts today’s AI safety debates.

Then, things get weird. From fiber optic controlled drones in Ukraine to perimeter defense bots equipped with buzzsaws, the duo brainstorm real (and, our lawyer wants to say, inadvisable) autonomous battlefield tech.

But first, they play the robot invention game and accidentally invent a $2,000 robotic hand-on-a-stick startup.

If you're into philosophy, robotics, defense tech, and backyard wood chip problems(?), this one’s for you.

On this episode of Automate It, Stefan and Ilia dive into Aurora’s recent announcement about running driver-out trucks on public highways—an undeniably huge technical feat, but one that curiously failed to make a media splash. But first, they play the Robot Invention Game, drawing a wild scenario: applying deep learning to railroads.

This week on Automate It, we're excited to have a special guest!

Carnegie Robotics co-founder David LaRose joins the podcast to share his perspective on the evolution of robotics from academic research to rugged real-world systems.

He reflects on what’s changed - and what hasn’t - over the last 15 years, from safety systems that still rely on spreadsheets to why so many autonomous vehicle projects have stalled.

David also unpacks the real challenges of selling to the DoD, the importance of enabling the next generation of robotics companies with hardened components, and what it’s like crawling through Florida cornfields in the name of agtech R&D.

(00:00) Introduction and welcome to the episode
(00:32) Robot Invention Game: Foundational Models for Space Exploration
(18:30) David’s journey from liberal arts to robotics via IBM and CMU
(20:41) Founding Carnegie Robotics
(23:55) Why the robotics industry hasn’t scaled as fast as expected
(29:18) Safety systems: still slow, manual, and deeply fragmented
(35:17) Why big companies (Amazon, Apple) still struggle with robotics
(40:05) Demos gone wrong: off-by-one bugs, e-stop failures, and bedbugs
(45:38) Working with the DoD: myths, structure, and real challenges
(01:08:30) Launching ruggedized autonomy kits and components online
(01:16:33) Environmental challenges and thermal testing tales
(01:20:42) Advice for roboticists: Embrace collaboration, not just competition
(01:23:00) What’s next for Carnegie Robotics: Supporting the enablers

In the 58th episode of Automate It, Polymath Robotics co-founders Stefan Seltz-Axmacher and Ilia Baranov discuss why hardware for robots is so dang expensive.

But first, they play the robot invention game and come up with a humanoid axe murderer.

On Ep 57 of Automate It, Stefan and Ilia get into Polymath Robotics' latest progress—scaling the team, launching new customer projects, and pushing forward despite the usual challenges.

Then they play the robot game, brainstorming how machine learning could help identify high-value recyclables -- devolving into "spot the $10 treasure," complete with GPU budgets, conveyor belt chaos, and the eternal battle between processing speed and precision.

Then, they tackle the vertical vs. horizontal integration debate—when to build, when to buy, and how to avoid the costly mistakes of legacy autonomy. Plus, a deep dive into Polymath’s approach to testing and development, from cost-effective sensor trials to the surprising impact of RF interference in agricultural automation.

On this episode of Automate It, Stefan and Ilia break down the surprisingly flawed state of collision avoidance systems in mining—where billion-dollar companies still rely on network-dependent GPS safety systems that can fail with network outages, jamming, or spoofing.

They get into why legacy mining autonomy is stuck in the past, how vendor lock-in prevents progress, and what a modern, sensor-driven approach to safety should actually look like.

But first, they play the robot invention game, brainstorming thermal-camera-guided healthcare robots before escalating into a zombie apocalypse fever-detection system—complete with flamethrowers, saw blades, and a ruthless AI security gate. You're welcome.

On Ep 55 of Automate It, we invite Adrian Macneil, CEO of Foxglove, to play the robot game -- which takes a turn into pest control, debating whether humanoid robots should stomp or grab mice. Then, Adrian gives us a deep dive on the state of robotics developer tools, why debugging robots is still a mess, and what it takes to build a software company in a hardware-heavy industry. Plus: why robotics is where SaaS was in the early 2000s—and what that means for the future.

In Ep 54 of Automate It, Polymath's co-founders tackle the tough topic of safety -- and what it means for a big heavy robot to be "safe enough."

But first, they play the robot invention game, which creates industrial grey goop. Try the grey stuff it's delicious, indeed.

On Ep 53 of Automate It, the guys discuss their takeaways from CES 2025 - including Jensen Huang's big announcement on autonomous vehicles, how the Chinese auto industry is leapfrogging everyone, evolution of the Lidar industry, a big OEM stepping back from autonomy, and more.

But first, they play the robot invention game, which they basically use to make fun of a VTOL "company" that exhibited at CES this year.

On Ep 52 of Automate It, Stefan and Ilia discuss the demise of Cruise Automation and why it's representative of the hidden dangers in autonomy programs. But first, they play the robot game and invent a ground-penetrating radar application for fast food.