116 episodes
Ep 116 | Robot Hardware Is Worse Than You Think (w/ Prof. Robert Katzschmann, ETH Zurich)
19/11/2026 | 1h 8 mins.Robot hardware, not AI, is the real bottleneck for physical AI, says Prof. Robert Katzschmann, head of the Soft Robotics Lab at ETH Zurich and co-founder of Mimic Robotics.
Robert Katzschmann is Assistant Professor of Robotics at ETH Zurich, where he founded and has led the Soft Robotics Lab since 2020. His lab builds robots made for contact rather than avoiding it: tendon-driven robotic hands, 3D-printed hands with bones, ligaments and tendons (Nature, 2023), electrohydraulic artificial muscles and biohybrid robots powered by living muscle tissue. In 2026 he received the IEEE RAS Early Academic Career Award. Before ETH he did his PhD at MIT CSAIL with Daniela Rus, where he built SoFi, the soft robotic fish that swam on Fiji's reefs (Science Robotics, 2018), and his TED talk on machines that move like animals has more than 1.4 million views.
In 2024 he co-founded Mimic Robotics with four of his former students. Mimic puts dexterous, human-like robot hands on standard industrial arms and trains them on human demonstrations. The ETH spin-off raised a $16M seed round, works with Audi and BMW, and built the FLUX-mimic video-action model with Black Forest Labs.
His path was anything but straight: he left high school in Germany at 16 to work in the US, then went via KIT, ABB Shanghai, Stanford, a surgical robotics startup, MIT, Amazon Robotics and a food robotics startup to ETH Zurich in 2020.
In this episode, Robert and Ilir talk about:
• Why startups should pick tasks today's robot hardware can already do reliably, not the generalist vision
• Why you should not get fooled by robot videos, and how to stress-test a robotics company
• How ETH Zurich built a robotics hub, with core faculty, donor-funded professorships and a steady flow of spin-offs (ANYbotics, Duatic, Flexion, RIVR, Mimic)
• How ETH bachelor students start product development in year three and spin out with VC money
• Artificial muscles from living cells, electrohydraulics and motors
• His mother, an electrical engineer who ran an engineering office for 30 years, and what taking a scary opportunity really costs
• Whether physical agentic AI will help or hurt society
SPONSOR
This podcast is brought to you by CoreWeave, providing the specialized cloud infrastructure that powers physical AI and large-scale model training.
ETH Zurich Soft Robotics Lab: https://srl.ethz.ch
Mimic Robotics: https://www.mimicrobotics.com
Robert Katzschmann on LinkedIn: https://www.linkedin.com/in/robertkatzschmann
Robert Katzschmann on X: https://x.com/katzschmann
Ilir on X: https://x.com/IlirAliu_
Ilir on LinkedIn: https://www.linkedin.com/in/ilir-aliu
Ilir on Instagram: https://www.instagram.com/_iliraliu_
22Astronauts: https://www.22astronauts.com/
TIMESTAMPS
0:00 Who is Robert Katzschmann (ETH Zurich)
1:19 A bionics book and an engineer mother
7:59 Teaching electricians with disabilities
11:12 The scary opportunity: running an engineering office for 30 years
14:35 Leaving high school at 16 to work in the US
19:01 No money, no degree: the flight back to Germany
27:30 Medicine in Heidelberg or mechanical engineering?
30:52 Karlsruhe, ABB Shanghai and a master's thesis at Stanford
33:01 Becoming a father during the Stanford thesis
35:16 First job: a surgical robotics startup
39:11 MIT PhD: betting on soft robotics in 2013
43:40 Amazon Robotics and the Thanksgiving dinner that led to ETH
45:45 CTO in food robotics during COVID
48:36 Why ETH Zurich became a robotics hub
53:10 How ETH students turn capstone projects into startups
54:40 Soft Robotics Lab: robots built for contact
56:47 Artificial muscles from living cells, electrohydraulics and motors
57:10 Mimic Robotics: dexterous robot hands for industry
60:00 Robotics hype waves: what can robots deliver in 3 to 5 years?
61:50 Hardware readiness decides which problems to pick
63:42 Don't get fooled by robot videos
66:00 Is physical agentic AI good for humanity?
Watch on YouTube: https://youtu.be/Kq5WYQVKhNkEp 115 | Your Factory Is Holding Back Your Design (w/ Edward Mehr, CEO Machina Labs)
12/11/2026 | 49 mins.Edward Mehr, Co-founder & CEO of Machina Labs .
Ed's interest in manufacturing started as a kid, walking through the appliance and automotive plants his father ran. Years later, a shop floor visit at SpaceX pulled him out of pure software and into hardware. He worked at SpaceX, joined Relativity Space as the fourth person on the team to lead 3D printing, and co-founded Machina Labs in 2019.
"If your interface is only digital, the computer will learn to do it at some point."
Machina Labs builds factories around its RoboCraftsman platform, robotic cells that use AI to form and finish metal parts without dedicated tooling. The same floor can make aircraft components in the morning and missile components in the afternoon.
In this episode, Ed and Ilir talk about why he left university several times for internships at Sony, Microsoft and Google, what SpaceX taught him about picking up new disciplines in months, why he handed Machina's first experiments to former interns instead of specialists, and why he sees convincing smart people to bet on something unfinished as the core of a founder's job.
𝐒𝐏𝐎𝐍𝐒𝐎𝐑
This podcast is brought to you by CoreWeave providing the specialized cloud infrastructure that powers physical AI and large-scale model training.
Machina Labs: https://machinalabs.ai
Edward Mehr on LinkedIn: https://www.linkedin.com/in/edward-mehr
Edward Mehr on X: https://x.com/EdwardMehr
Ilir on X: https://x.com/IlirAliu_
Ilir on LinkedIn: https://www.linkedin.com/in/ilir-aliu
22Astronauts: https://22astronauts.vc/
Hosted by Ilir Aliu
𝐓𝐈𝐌𝐄𝐒𝐓𝐀𝐌𝐏𝐒
0:00 Machina is the factory
2:47 Growing up in his dad's factories ("it looks like a casino")
6:47 The SpaceX visitor badge that pulled him out of software
9:04 Teal collar: why AI pushes work back into the physical world
10:59 A school built around shop class, then QBasic and IRC
16:31 Choosing computer engineering
17:26 Leaving school for Sony, Microsoft and Google
21:01 He never planned to start a company
23:07 Hard problems attract smart people
27:01 What SpaceX changed about learning new disciplines
29:43 Spotting manufacturing as the bottleneck
33:04 Generalists vs. specialists
36:00 Why interns proved robotic sheet forming could work
38:32 Engineers look for flaws, and that can stop new ideas
39:38 Joining Relativity Space as employee #4
41:09 Why Falcon 9 got taller but never wider
43:04 The founder's real job: making believers
47:04 Machina today: high-mix factories and the RoboCraftsman
48:57 A future where things look different againEp 114 | Why We Build the Whole Robot Stack Ourselves (w/ Neil Nie, CEO Verne Robotics)
05/11/2026 | 47 mins.With Neil Nie, Co-founder & CEO of Verne Robotics.
Neil came to the US as a kid and grew up in a small town in rural Massachusetts, writing software mostly on his own. As a high school runner he built a workout tracking app for his coach when the first Apple Watch came out, and with a friend he built a self-driving golf cart.
He went on to do robot learning research with Shuran Song at Columbia and with Jiajun Wu in Stanford's SVL, spent about a year on Apple's fitness tracking team, and left his PhD at Berkeley to start Verne in summer 2025 with a friend from high school.
"If you have an arm that can only carry three or four kilograms, certain applications, especially in industrial settings, are simply not going to make sense."
Verne builds dual-arm mobile robots for manufacturing and logistics and owns the whole stack, from pre-training and post-training to the controllers on the robot. Customers today range from semiconductor supply chains to packing operations for contractors serving the US defense industry.
In this episode, Neil and Ilir talk about his mother's advice to turn down an Apple salary after college, why research still matters when AI can answer most questions, how Verne got into YC without a single customer, why he thinks industrial robots don't need legs, and why he wants customers to build on Verne's robots the way developers built on the App Store.
𝐒𝐏𝐎𝐍𝐒𝐎𝐑
This podcast is brought to you by CoreWeave providing the specialized cloud infrastructure that powers physical AI and large-scale model training.
Verne Robotics: https://vernerobotics.com
Neil Nie on X: https://x.com/neil_nie_
Neil Nie on LinkedIn: https://www.linkedin.com/in/neilnie
Ilir on X: https://x.com/IlirAliu_
Ilir on LinkedIn: https://www.linkedin.com/in/ilir-aliu
22Astronauts: https://22astronauts.vc/
Hosted by Ilir Aliu
𝐓𝐈𝐌𝐄𝐒𝐓𝐀𝐌𝐏𝐒
0:00 What Verne Robotics builds
2:54 First-generation immigrant with entrepreneurial parents
3:43 Building a self-driving golf cart in high school
4:06 Columbia with Shuran Song, Stanford with Jiajun Wu
6:57 A workout app for his track coach
8:29 A year on Apple's fitness team
10:04 Alone in rural New England, then the robotics club
13:00 Should you still do a PhD when AI does research?
14:50 "Back then robotics just didn't work at all"
15:45 His mom's advice: skip the Cupertino salary
18:42 There are no shortcuts
23:03 Starting Verne and dropping out of the PhD
23:47 Why the company is named after Jules Verne
26:01 Robots that help businesses make and ship more
28:21 Selling into manufacturing as a first-time founder
30:58 Getting into YC with zero customers
33:20 The Pareto frontier of what robots should do
34:16 Windows XP vs. the App Store: customers as robot developers
38:14 The questions critics ask: vertical integration, deployment, form factor
41:54 Why legs are optional and payload is not
43:17 Design and public perception
45:00 What's coming nextEp 113 | Why Robotics Needs Physical Benchmarks, Not Simulation (w/ Ali Ansari, CEO Micro1)
02/11/2026 | 40 mins.In Ep #113 of 22Astronauts, Ilir Aliu sits down with Ali Ansari, Founder & CEO of Micro1.
Robotics teams still struggle to say which policy model is better, because almost nobody evaluates them on the same real hardware. Ali’s view is that measurement comes first and improvement follows. micro1 builds expert-generated training data and evaluations for most frontier AI labs, and by Ali’s account robotics is already above $100M of its run rate.
Ali was born in Iran, moved to the US at ten after his family won the green card lottery, and studied CS and math at Berkeley before a short stint at Stanford. micro1 began as an AI interviewer he built to screen engineers for his own software agency and is now valued at $4B.
“If you can precisely measure intelligence, you by definition have a reward model to train on.”
In this episode, Ali and Ilir cover why robot models will learn from human actions the way LLMs learned from human text, how micro1 collected 100,000+ hours of egocentric household video, and why cheap hardware with heavy annotation scales better than expensive sensors.
They also get into the new Malibu lab for safety evals on real arms and humanoids, how micro1 serves competing labs at the same time, and what Ali learned from the sacrifices his parents made.
𝐒𝐏𝐎𝐍𝐒𝐎𝐑
This podcast is brought to you by @CoreWeaveYT providing the specialized cloud infrastructure that powers physical AI and large-scale model training.
micro1: https://www.micro1.ai
Ali Ansari on X: https://x.com/aliansarinik
Ilir on X: https://x.com/IlirAliu_
Ilir on LinkedIn: https://www.linkedin.com/in/ilir-aliu
22Astronauts: https://22astronauts.vc/
Hosted by Ilir Aliu
TIMESTAMPS
0:00 What micro1 does and who Ali is
2:00 Born in Iran and winning the green card lottery
5:00 What the move cost his parents
9:40 Raising $100M+ at 25 and staying capital efficient
13:35 Why experts outside San Francisco change how people see AI
16:50 The two theses behind micro1’s move into robotics
21:40 From AI recruiter to training data for frontier labs
25:40 Synthetic vs. human data: simple hardware, heavy annotation
27:50 Why robotics needs physical benchmarks, not simulation
30:15 Inside the Malibu lab: safety evals and post-training
31:35 Serving competing labs without leaking information
34:00 Hiring, risk appetite and a role that changes every month
37:00 Mentors: Sean Rad and Joshua Browder
38:50 The Sunday reflection hourEp 112 | Why 99% Reliability Means Your Robotics Fleet Fails (w/ Joe Harris, CEO Alloy Robotics)
15/10/2026 | 52 mins.In Ep #112 of 22Astronauts, Ilir Aliu sits down with Joe Harris, Founder & CEO of Alloy Robotics.
Before starting Alloy, Joe helped scale a consumer telehealth platform to a $1B+ acquisition. Now, he is bringing those high-growth scaling principles to physical AI.
"Reliability is measured at the action level. If every action is 99% accurate and you multiply that across 10,000 actions a day, your robot's actual uptime degrades incredibly fast."
Alloy Robotics builds the "AI Robotics Engineer", a specialized data and agent platform that ingests robot logs, telemetry, and sensor streams to automatically detect, diagnose, and resolve field failures.
In this episode, Joe and Ilir break down why general-purpose robotics hype collides with real-world fleet engineering, why hardware teams need SRE and agentic tooling, and how software remains the highest-leverage layer in robotics.
𝐒𝐏𝐎𝐍𝐒𝐎𝐑
This podcast is brought to you by @CoreWeaveYT providing the specialized cloud infrastructure that powers physical AI and large-scale model training.
Follow Joe Harris on X: https://x.com/_joe_harris_
Alloy Robotics: https://www.usealloy.ai/
22Astronauts: https://22astronauts.vc/
Hosted by Ilir Aliu
TIMESTAMPS
(00:00) Building the First AI Robotics Engineer
(04:05) Don't Sell a Platform, Sell a Solution
(09:38) Lessons from Scaling a $1B+ Business
(14:38) Scar Tissue vs. Intellectual Learning
(20:40) Why Hardware Needs SRE & Agentic Tooling
(27:58) How Platform Shifts Expand Total Market Cap
(34:25) The Hidden Cost of Robotics Log Data
(41:10) Global Supply Chains & Re-Industrialization
(51:12) The Compound Math of 99.999% Fleet Reliability
More Technology podcasts
Trending Technology podcasts
About 22Astronauts
The most interesting AI & robotics stories. Ilir Aliu sits down with the founders and engineers who build robots, showing the people behind the technology.
Podcast websiteListen to 22Astronauts, Acquired and many other podcasts from around the world with the radio.net app

Get the free radio.net app
- Stations and podcasts to bookmark
- Stream via Wi-Fi or Bluetooth
- Supports Carplay & Android Auto
- Many other app features







































