Yoel Fink on Education, Invention, and Asking Better Questions

Yoel Fink on Education, Invention, and Asking Better Questions

The best ideas are not always hidden in the future. Sometimes they are sitting right in front of us, waiting for someone to ask a better question. In this episode of Automated, Brian Heater speaks with Yoel Fink, Professor of Materials Science and Engineering at MIT, about education, invention, advanced fibers, and why so much of technology follows the same obvious tracks. This is not a typical conversation about robotics or automation. It is a wider look at how people learn, how researchers discover, and why stepping off a prescribed path can sometimes lead to better outcomes than following the one everyone else expects. Yoel reflects on his own unconventional path, from military service and years of backpacking to studying chemical engineering, physics, and eventually materials science at MIT. He explains why he encourages students to take time, see the world, and collect the kinds of experiences no classroom can fully provide. Brian and Yoel also discuss the pressure students face when they are pushed too quickly from one life milestone to the next. Yoel argues that people are not trains, and that education often works better when students have more room to mature, explore, and understand what they actually want to build. The conversation then moves into research and invention. Yoel shares the story of asking a simple question in a room full of leading optics researchers, a question that helped lead to a new kind of mirror and shaped the direction of his career. For Yoel, that moment reveals something essential about innovation: sometimes the breakthrough is not the answer. It is the courage to ask the question no one else is asking. They also explore Yoel’s work with advanced fibers and functional fabrics. He explains why fibers are one of the oldest and most universal forms of human technology, and why the future of computing and sensing may not look like another screen, headset, watch, or metal device. It may be woven into the clothes we already wear. Finally, Yoel challenges the way major technology companies often move in the same direction, from glasses to headsets to devices that look increasingly similar. His question is simple: are we really out of ideas, or are we just too busy following everyone else? Connect with Yoel Fink https://dmse.mit.edu/people/faculty/yoel-fink/ [https://dmse.mit.edu/people/faculty/yoel-fink/] Learn more about fibers@mit https://pbg-rle.mit.edu/ [https://pbg-rle.mit.edu/] We’d love to hear from you. Have thoughts or guest suggestions? Reach us at podcast@automate.org [podcast@automate.org] You can find the transcript and more episodes of Automated at automated.fm [http://automated.fm] Unlock full access to Automated and explore everything automation. Subscribe today and leave a review on YouTube, Apple Podcasts, and Spotify. Also subscribe to the Automated Newsletter. https://www.youtube.com/@automatedpodcast [https://www.youtube.com/@automatedpodcast] https://podcasts.apple.com/us/podcast/automated-with-brian-heater/id1837762221 [https://podcasts.apple.com/us/podcast/automated-with-brian-heater/id1837762221] https://open.spotify.com/show/60olq6brlBEIJWggx2fMR6 [https://open.spotify.com/show/60olq6brlBEIJWggx2fMR6] https://www.automate.org/automation/automated-newsletter [https://www.automate.org/automation/automated-newsletter] You can also find us on: LinkedIn https://www.linkedin.com/showcase/automated-podcast-by-a3/ [https://www.linkedin.com/showcase/automated-podcast-by-a3/] Instagram https://www.instagram.com/automatedpod/ [https://www.instagram.com/automatedpod/] ---------------------------------------- Hosted on Acast. See acast.com/privacy [https://acast.com/privacy] for more information.

Russ Tedrake on Robotics, Physical AI, and the Future of Work

Physical AI is moving fast. But Russ Tedrake says the biggest shift may not just be better robots. It may be the way robotics itself is changing. In this episode of Automated, Brian Heater speaks with Russ Tedrake, Toyota Professor at MIT and founder of a stealth physical AI startup, about why this moment in robotics feels different from past hype cycles. Russ explains how machine learning has moved ahead of our theoretical understanding, and why that changes the role of robotics engineers. Instead of designing everything from first principles, teams are increasingly building systems they do not fully understand yet, then studying their behavior like scientists. Brian and Russ also discuss the long arc of robot locomotion, from passive dynamic walkers to today’s humanoid robots. Russ reflects on why bipedal walking was always the dream, why humanoid hardware has become surprisingly turnkey, and why the next exciting question is what AI can do with a powerful general-purpose body. The conversation also digs into one of the biggest debates in robotics right now: data. Russ argues that the robotics data problem is often framed the wrong way. Robots do not need to learn everything from scratch. Instead, he says the field can build on powerful video and multimodal models that already contain world knowledge, then train those models to output robot actions. Russ also explains the difference between large behavior models and vision-language-action models, why multitask pre-training may help with robustness, and why real-world deployment is the next major milestone for the field. Finally, Russ talks about launching a new physical AI company, why he believes robotics may have escape velocity this time, and why the future of work has to be central to the conversation. His goal is not just more capable robots. It is building systems that amplify people rather than replace them. Connect with Russ Tedrake https://www.linkedin.com/in/russ-tedrake-88648a4a [https://www.linkedin.com/in/russ-tedrake-88648a4a?utm_source=chatgpt.com] Learn more about Russ Tedrake at MIT https://locomotion.csail.mit.edu/russt.html [https://locomotion.csail.mit.edu/russt.html?utm_source=chatgpt.com] Learn more about Drake https://drake.mit.edu/ [https://drake.mit.edu/?utm_source=chatgpt.com] Learn more about Large Behavior Models from Toyota Research Institute https://toyotaresearchinstitute.github.io/lbm1/ [https://toyotaresearchinstitute.github.io/lbm1/?utm_source=chatgpt.com] We’d love to hear from you. Have thoughts or guest suggestions? Reach us at podcast@automate.org [podcast@automate.org] You can find the transcript and more episodes of Automated at automated.fm [http://automated.fm] Unlock full access to Automated and explore everything automation. Subscribe today and leave a review on YouTube, Apple Podcasts, and Spotify. Also subscribe to the Automated Newsletter. https://www.youtube.com/@automatedpodcast [https://www.youtube.com/@automatedpodcast] https://podcasts.apple.com/us/podcast/automated-with-brian-heater/id1837762221 [https://podcasts.apple.com/us/podcast/automated-with-brian-heater/id1837762221] https://open.spotify.com/show/60olq6brlBEIJWggx2fMR6 [https://open.spotify.com/show/60olq6brlBEIJWggx2fMR6] https://www.automate.org/automation/automated-newsletter [https://www.automate.org/automation/automated-newsletter] You can also find us on: LinkedIn https://www.linkedin.com/showcase/automated-podcast-by-a3/ [https://www.linkedin.com/showcase/automated-podcast-by-a3/] Instagram https://www.instagram.com/automatedpod/ [https://www.instagram.com/automatedpod/] ---------------------------------------- Hosted on Acast. See acast.com/privacy [https://acast.com/privacy] for more information.

Rick Faulk on Locus Robotics, Warehouse Automation, and Physical AI

Warehouse automation is not about building the flashiest robot. It is about solving the right problem at scale. In this episode of Automated, Brian Heater speaks with Rick Faulk, CEO of Locus Robotics, about what it really takes to deploy robots inside working warehouses and why the future of physical AI may look very different from the humanoid hype cycle. Rick explains how Locus grew out of a major logistics problem. Quiet Logistics had been using Kiva robots before Amazon acquired Kiva and took the product off the market. Instead of returning to a manual operation, the team started building its own robotics solution inside the warehouse. That origin story shaped the company’s entire approach. Rick says many robotics companies fail because they start with the robot instead of the customer’s problem. Locus was different because it was built inside the environment it was trying to automate. Brian and Rick also discuss why fixed automation can be limiting in warehouses with seasonal peaks, shifting demand, labor shortages, and changing order volume. Rick explains why flexible systems, Robots-as-a-Service, and scalable deployments matter when operators need to handle holiday surges, back-to-school volume, and unpredictable demand. The conversation digs into one of the biggest topics in robotics right now: humanoids. Rick says humanoids may eventually play a role, but purpose-built warehouse robots have a clearer path to ROI today. In his view, the winning systems are not trying to fold laundry, make burgers, and work in a warehouse. They are designed to do one important job extremely well. They also get into Locus’s real-world data advantage. Rick says Locus has completed more than seven billion picks and is now doing around 150 picks per second. Every pick becomes part of a data flywheel that helps robots move more safely, respond to warehouse conditions, and improve productivity. Rick also breaks down Locus Array, the company’s autonomous Robots-to-Goods system. He explains why mobile manipulation is so difficult, why picking in a warehouse is much harder than it looks, and why Array is designed as a practical physical AI system for fulfillment. Finally, Brian and Rick discuss what automation means for warehouse workers, why robotics can create higher-value roles inside facilities, and how companies can compete in a logistics world shaped by Amazon-level expectations. Connect with Rick Faulk https://www.linkedin.com/in/rickfaulk [https://www.linkedin.com/in/rickfaulk?utm_source=chatgpt.com] Learn more about Locus Robotics https://locusrobotics.com/ [https://locusrobotics.com/?utm_source=chatgpt.com] Learn more about Locus Array https://locusrobotics.com/blog/locus-array-autonomous-warehouse-era [https://locusrobotics.com/blog/locus-array-autonomous-warehouse-era?utm_source=chatgpt.com] We’d love to hear from you. Have thoughts or guest suggestions? Reach us at podcast@automate.org [podcast@automate.org] You can find the transcript and more episodes of Automated at automated.fm [http://automated.fm] Unlock full access to Automated and explore everything automation. Subscribe today and leave a review on YouTube, Apple Podcasts, and Spotify https://www.youtube.com/@automatedpodcast [https://www.youtube.com/@automatedpodcast] https://podcasts.apple.com/us/podcast/automated-with-brian-heater/id1837762221 [https://podcasts.apple.com/us/podcast/automated-with-brian-heater/id1837762221] https://open.spotify.com/show/60olq6brlBEIJWggx2fMR6 [https://open.spotify.com/show/60olq6brlBEIJWggx2fMR6] You can also find us on: LinkedIn https://www.linkedin.com/showcase/automated-podcast-by-a3/ [https://www.linkedin.com/showcase/automated-podcast-by-a3/] Instagram https://www.instagram.com/automatedpod/ [https://www.instagram.com/automatedpod/] ---------------------------------------- Hosted on Acast. See acast.com/privacy [https://acast.com/privacy] for more information.

Aya Durbin on Turning Atlas Into a Real Industrial Robot

Humanoid robots are everywhere in the headlines. But Aya Durbin says the real test is not whether a robot can impress people in a demo. It is whether that robot can deliver real value, positive ROI, and reliable performance inside industrial environments. In this episode of Automated, Brian Heater speaks with Aya Durbin, Director of Product for Atlas at Boston Dynamics, about what it will actually take to bring humanoid robots out of the lab and into the workforce. Aya explains why she considers herself both a dreamer and a pragmatist. Boston Dynamics has shown what is possible with legged robots, viral demos, and advanced mobility, but productizing Atlas means focusing on customer value, uptime, deployment, serviceability, and hard industrial work. The conversation explores why Atlas has legs, what Boston Dynamics learned from Spot and Stretch, and why the first meaningful humanoid deployments will likely happen in structured industrial environments before anything broader. Brian and Aya also dig into the reality behind Boston Dynamics’ famous robot videos. The backflips, gymnastics, and playful demos may look like fun, but Aya explains how many of those moments are tied to the same core technology used to train robots for real tasks. They also discuss why Atlas is being built around AI-based tools rather than hard-coded applications, how early customers will help shape the roadmap, and why integration, IT, security, downtime, and ROI are just as important as the robot itself. Finally, Aya outlines Boston Dynamics’ current timeline for Atlas, including customer pilots planned for 2028 and Hyundai’s commitment to building 30,000 Atlas robots a year starting in 2030. This is a grounded look at what humanoid robotics looks like beyond the hype, and what has to happen before Atlas becomes a trusted member of the industrial workforce. Connect with Aya Durbin https://www.linkedin.com/in/alexa-durbin [https://www.linkedin.com/in/alexa-durbin] Learn more about Boston Dynamics Atlas https://bostondynamics.com/products/atlas/ [https://bostondynamics.com/products/atlas/] Thanks for being an Automated fan! Enter our giveaway to win robot-building sets from some of our favorite robotics companies and exclusive Automated swag. We’d love to hear from you. Have thoughts or guest suggestions? Reach us at podcast@automate.org [podcast@automate.org] You can find the transcript and more episodes of Automated at automated.fm [http://automated.fm] Unlock full access to Automated and explore everything automation. Subscribe today and leave a review on YouTube, Apple Podcasts, and Spotify https://www.youtube.com/@automatedpodcast [https://www.youtube.com/@automatedpodcast] https://podcasts.apple.com/us/podcast/automated-with-brian-heater/id1837762221 [https://podcasts.apple.com/us/podcast/automated-with-brian-heater/id1837762221] https://open.spotify.com/show/60olq6brlBEIJWggx2fMR6 [https://open.spotify.com/show/60olq6brlBEIJWggx2fMR6] You can also find us on: LinkedIn https://www.linkedin.com/showcase/automated-podcast-by-a3/ [https://www.linkedin.com/showcase/automated-podcast-by-a3/] Instagram https://www.instagram.com/automatedpod/ [https://www.instagram.com/automatedpod/] ---------------------------------------- Hosted on Acast. See acast.com/privacy [https://acast.com/privacy] for more information.

Andrew Barry on Why Dexterity Is the Next Breakthrough in Physical AI

Physical AI is moving quickly. But Andrew Barry says one of the biggest unlocks in robotics is not just getting robots to move through the world. It is getting them to touch, grasp, adjust, and manipulate the world with real dexterity. In this episode of Automated, Brian Heater speaks with Andrew Barry, co-founder and CTO of Generalist, about how the company is building general intelligence for the physical world and why dexterous robots may be the starting point for far more capable automation. Andrew explains why Generalist is focused on the tasks that are both difficult and valuable. Robots have made major progress in mobility, but their ability to manipulate objects is still limited. If robots can solve dexterity, they can become useful in a much wider range of real-world environments. The conversation explores how Generalist is collecting massive amounts of real-world manipulation data. Andrew describes the handheld data capture devices the company built, why they chose that approach over teleoperation, and how thousands of devices have helped them scale a much richer data set for robot learning. Brian and Andrew also discuss the commercial side of physical AI. Andrew explains why the company is not just chasing impressive demos, but benchmarking against real tasks people are already paying for today. That distinction matters because a viral robot demo is not the same thing as a deployable robotic system. They also dig into one of the most surprising parts of modern robot learning: improvisation. Andrew shares the moment when a robot picked up a baggie with the opposite hand from the one it had been trained on, completed the task anyway, and left the team realizing something very different was happening inside the model. The episode also covers Generalist’s GEN-1 model, the parallels between robotics and the early GPT era, why flexible objects like cables are so difficult to automate, what data flywheels may actually look like in robotics, and why robots sometimes learn human mistakes from the data they are trained on. Finally, Andrew reflects on his path from Boston Dynamics to the Broad Institute and then to Generalist, explaining how work in molecular biology, machine learning, transformers, and robotics all shaped the way he thinks about building intelligence for the physical world. Connect with Andrew Barry https://www.linkedin.com/in/andy-barry [https://www.linkedin.com/in/andy-barry?utm_source=chatgpt.com] Learn more about Generalist https://generalistai.com/ [https://generalistai.com/?utm_source=chatgpt.com] We’d love to hear from you. Have thoughts or guest suggestions? Reach us at podcast@automate.org [podcast@automate.org] You can find the transcript and more episodes of Automated at automated.fm [http://automated.fm]. Unlock full access to Automated and explore everything automation. Subscribe today and leave a review on YouTube, Apple Podcasts, and Spotify. https://www.youtube.com/@automatedpodcast [https://www.youtube.com/@automatedpodcast] https://podcasts.apple.com/us/podcast/automated-with-brian-heater/id1837762221 [https://podcasts.apple.com/us/podcast/automated-with-brian-heater/id1837762221] https://open.spotify.com/show/60olq6brlBEIJWggx2fMR6 [https://open.spotify.com/show/60olq6brlBEIJWggx2fMR6] You can also find us on: LinkedIn https://www.linkedin.com/showcase/automated-podcast-by-a3/ [https://www.linkedin.com/showcase/automated-podcast-by-a3/] Instagram https://www.instagram.com/automatedpod/ [https://www.instagram.com/automatedpod/] Subscribe to the Automated Newsletter: https://www.automate.org/automation/automated-newsletter [https://www.automate.org/automation/automated-newsletter] ---------------------------------------- Hosted on Acast. See acast.com/privacy [https://acast.com/privacy] for more information.