Robotics is advancing quickly, but real-world deployment is still far more difficult than most people expect.

In this episode of Automated, Brian Heater speaks with Ranjay Krishna about the fundamental challenges preventing robots from working reliably outside controlled environments, and why solving the data problem is key to unlocking the next wave of robotics.

Ranjay explains why today’s robots struggle with tasks that humans find intuitive, from learning by observation to understanding perspective and adapting to new environments. While AI models have made massive progress in language and vision, robotics introduces a new layer of complexity where actions change the world in real time and small errors compound over time.

The conversation explores the limitations of current approaches, including why training robots in simulation often fails to translate to the real world, and how the lack of diverse environments creates major gaps in performance. Ranjay shares how his team at the Allen Institute is addressing this by building large-scale simulated environments designed to better reflect the variability of real-world spaces.

They also discuss the concept of an ImageNet moment for robotics, and what it would take to create the kind of large, diverse datasets that transformed AI. By generating hundreds of thousands of simulated environments and scaling data collection, his team is exploring whether robots can learn more effectively in simulation and generalize those skills into the physical world.

The conversation also covers why robotics requires more than just better models, including challenges in hardware, sensing, and real-world interaction. From embodiment and perception to reasoning and adaptation, it is a grounded look at why robotics remains one of the hardest problems in AI and what needs to happen next for the industry to move forward.

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.

Also, join us at MassRobotics for a happy hour with Brian Heater from A3. Wednesday, April 8 - 4:30 PM - 6:00 PM EDT

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.

Billions are flowing into humanoid robots. But on the factory floor, nobody cares what the robot looks like.

In this episode of Automated, Brian Heater speaks with Erik Nieves, CEO and co-founder of Plus One Robotics, about the gap between robotics investment and real-world deployment. Recorded live at the A3 Business Forum in Miami, Nieves explains why enterprise customers have one question and one question only: does it hit 2,200 picks per hour with three nines of uptime?

From the Cambrian explosion happening across warehouse automation to why dexterity remains the biggest unsolved problem in robotics, Nieves gives one of the most grounded, honest assessments of where the industry actually stands. He also explains why human-in-the-loop systems are not a limitation but a competitive advantage, and why robots are about to end the era of labor arbitrage entirely.

Key Moments:

(00:00) Why Enterprise Customers Don't Care What the Robot Looks Like

(00:38) From Astronomy to Robotics: Erik Nieves' Origin Story

(04:44) CES Humanoid Demos vs Real-World Deployment

(06:52) Has the Capital Outpaced the Technology

(09:32) Plus One Robotics at Year Ten

(11:15) What Has Changed and What Has Stayed the Same

(12:25) KPIs Matter More Than Form Factor

(13:28) Why Humanoids Cannot Meet Industrial Rates Yet

(15:59) Dexterity Is the Real Problem Nobody Is Solving

(19:33) Legs vs Wheels: The Debate That Won't Die

(21:43) Why Robots Are Still Behind a Fence

(23:06) The Fence Is Not There to Keep the Robot In

(24:59) The Cambrian Explosion in Robotics

(26:57) How Plus One Robotics Was Founded

(29:42) Why Human in the Loop Was the Right Bet

(34:27) Robots Will End the Era of Labor Arbitrage

(36:01) Nearshoring vs Reshoring

(37:53) Why San Antonio Is a Hidden Advantage

(39:08) Talent, Universities, and the AI Pipeline

(41:04) Why Hardware Companies Cannot Go Fully Remote

(42:17) Mentorship Only Works in Person

(46:34) The One KPI That Runs the Entire Company

Sponsored by SANYO DENKI America: SANMOTION delivers precise, reliable multi-axis control for advanced robotics systems.

Learn more at https://www.sanyodenki.com/america/

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.

Robot vacuums have been on the market for over 20 years and are still in fewer than 20 percent of US homes. In this episode of Automated, Brian Heater speaks with Gary Cohen, CEO of iRobot and the brand behind Roomba, about what it actually takes to rebuild one of the most iconic names in consumer robotics.

Gary breaks down the shift from feature-led to consumer-led product development, explaining why iRobot missed key market opportunities and how competitors used that window to take significant market share. He shares the full story behind the failed Amazon acquisition, the Chapter 11 restructuring, and how he rebuilt the company's entire product line in under 12 months to win Prime Day 2025.

They also discuss why the robot vacuum market is far from saturated, why simplifying the setup and onboarding experience matters more than any new feature, and what the Gillette razor wars teach us about the robot vacuum arms race happening right now. Gary also addresses data privacy under the new ownership structure and previews what iRobot's roadmap looks like over the next two to three years, including a Japan-first product launch and the long-awaited iRobot lawnmower.

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.