Advertise on podcast: The Driverless Digest Podcast

Listen to this episode on Apple Podcasts, YouTube, Spotify, and Substack. Transcripts are also available by clicking on the “transcripts” button in the top right corner of this post on the app/web version. You can also access them from the email version by clicking here. In today’s episode, I’m speaking with Raquel Urtasun, Founder and CEO of Waabi. Raquel shares how she got into the self-driving field, why she left Uber to build Waabi, and what she believes sets the company apart. We also discuss Waabi’s current operations and footprint, its philosophy, and the three pillars Raquel sees as essential to commercial scale. Raquel explains how much human supervision Waabi’s trucks require today and the final milestone before the company can operate without a driver. We dig into the metrics Waabi uses to measure progress, its hardware approach, and its partnership with Volvo Autonomous Solutions. She also discusses Waabi’s other truck manufacturer partnerships and how quickly the Waabi Driver can transfer between vehicle platforms. The conversation then turns to how Waabi tests its claims about zero-shot transfer across truck platforms and why Raquel chose trucking as the company’s starting point. We compare trucking with other autonomous vehicle markets and discuss Waabi’s fundraising and its partnership with Uber to deploy robotaxis. Finally, Raquel shares her perspective on what it will take to bring autonomy to more vehicles at scale. Chapters * (00:00) Introduction to Raquel Urtasun * (01:50) Raquel’s background and how she got into the self-driving field * (04:35) Why Raquel Urtasun left Uber to build Waabi * (07:20) How Waabi stands out from its competitors * (09:20) Waabi’s current operations, footprint, and philosophy * (11:30) Waabi’s three pillars for commercial scalability * (16:07) What level of human supervision is involved in Waabi’s current product? * (16:30) Waabi’s final milestone before full driverless operations * (20:30) What drives Waabi’s scalability, and which KPIs does it track? * (22:40) Waabi’s hardware and partnership with Volvo Autonomous Solutions * (24:45) Waabi’s other OEM partnerships * (25:35) How quickly the Waabi Driver transfers between vehicle platforms * (28:30) How Waabi scientifically tests zero-shot transfer across OEM truck platforms * (30:45) How Raquel ranks different autonomy verticals and why Waabi started with trucking * (36:50) Waabi’s fundraising and their partnership with Uber to deploy robotaxis * (40:45) Conclusion and final thoughts Notes/Links: * You can find Raquel Urtasun on LinkedIn/X. * Waabi’s partnership with Volvo Autonomous Solutions, mentioned at the 22:40 timestamp (link). * Waabi’s announcement of the Waabi Driver’s zero-shot transfer between truck platforms, mentioned at the 25:18 timestamp (link). * Waabi’s latest fundraising and partnership with Uber, mentioned at the 36:48 timestamp (link). * Waabi’s website (link). -Harry This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.thedriverlessdigest.com

Thanks to Jonah Bliss for originally covering this on The Curbivore - Let Them Linger? The Surprising Case for Robotaxis at the Curb In a new study, Associate Professor Michael Hyland at UC Irvine explains why giving robotaxis somewhere to wait between rides could be crucial to avoiding unnecessary miles on city streets. Where should a robotaxi go after dropping off a passenger? It could wait at the curb, head back to a depot or it could simply keep moving. A new study from researchers at UC Irvine and UC Berkeley examines what happens when shared autonomous vehicles are prevented from resting (otherwise known as staging) at the curb in San Francisco. The researchers simulated a fleet of 1,700 robotaxis serving 68,000 daily trips. In the no-staging scenario, the fleet traveled 564,650 kilometers per day. Allowing the vehicles to stage at the curb reduced daily vehicle miles traveled (VMT) by nearly 60%. Michael Hyland, Associate Professor of Civil and Environmental Engineering at UC Irvine and one of the researchers behind the study, spoke to The Driverless Digest Editor Ben Hubbard about why curb access matters for robotaxis, how cities should manage valuable curb space, and what the rise of personally owned driverless vehicles could mean for congestion. The Driverless Digest: Tell us about your role? Michael Hyland: My research is broadly on modeling and analyzing transportation systems. I tend to focus on innovations in the transportation space, such as driverless vehicles, both in terms of shared fleets and personally owned, but also technologies like e-scooters, e-bikes, ride-hailing and micro-transit. My work involves how to operate these systems efficiently, how to design them effectively, and then I also try to understand their impact on people living in cities. You’ve recently conducted a pretty comprehensive study on managing curb usage. Can you explain the experiment and what you set out to understand? The idea was to test the impact of banning shared automated vehicles from using the curb. So this is not when they pick up and drop off passengers, but for what we call staging or parking between one drop-off and the next pickup. Essentially, the time when the vehicle doesn’t have anything to do. The main result, of course, is that it has pretty big implications on what these vehicles do with their time. When they can’t stage, they just circle around the transportation network. In this case, they dramatically increased vehicle miles traveled on the roadway network in San Francisco. We don’t model congestion in our study, but the implications for congestion, I think, are somewhat obvious directionally. It would make congestion worse, most likely in some of the most congested parts in San Francisco. We ran some other scenarios related to weekends versus weekdays, preventing vehicles from staging at night versus only during the day. Most of the results were pretty similar. If you’re strategic with where you ban the robotaxis from using the curb, the size of the VMT impact is much smaller, but there still is an adverse impact. Plenty of people have probably wondered where an AV goes after it has dropped off a passenger. Do they just drive around in circles? Do they wait? Could you explain how this study came about because I can imagine this is going to become a really important topic when AVs take off. Yeah, that’s right. As there are more fleets, the impact will be much larger. The study actually came from Waymo reaching out to us here at UC Irvine via Susan Shaheen’s group at UC Berkeley. They knew we did modeling and they asked us to interview stakeholders in cities to understand how they’re thinking about regulating the curb and using the curb for not just robotaxis but also Uber and Lyft-type vehicles, and micromobility too. They came to us and said, “Hey, we think it’s mutually beneficial for us at Waymo and for cities for our vehicles to be able to use the curb when we’re not serving passengers,” as opposed to just driving around or even going a long distance back to an off-street parking lot. We co-designed the experiments. We made the final choices, of course. That’s the backstory of how the study came to be. So is it entirely independent? When a company like Waymo approaches a university to produce a study, there’s always a feeling that the results might be tailored in their favor. I can see that’s the impression. The main thing Waymo was pushing back on when we were writing up the report was that they said: “Well, we didn’t give you any data, so don’t make it seem like we did give you any data.” All this data is synthetic. We got the parking data from INRIX. We got the ride-hailing trip data from a company called Replica. Waymo really didn’t give us any data, which was fine with us. They gave us order-of-magnitude information about their fleet size, which is publicly available. As far as the results, I mean I hate to undercut our study, but the directional impact was kind of obvious going into the study. We knew that by banning these vehicles from using the curb, it was going to increase VMT. It was really the magnitude that was the interesting part. Was it going to be a 10% increase? 30%? We found a pretty large number, which was a 60% increase in total vehicle miles traveled with this policy. And that came directly from the results. We didn’t rerun any scenarios or rerun the experiments with Waymo’s input. Where do all those extra miles come from? There are all these peaks and valleys throughout the day in terms of the demand for robotaxis. Everyone knows when the big peaks are for regular travel, right? So the morning peak, and then you have the afternoon peak. But for a service like Uber, Lyft or Waymo, there’s even little peaks and valleys that occur throughout the day, and spatially these occur throughout different parts of the region. But when you have these vehicles out on the road and you get a little bit of a dip in demand, there’s nowhere for them to go. They’re not serving passengers, so they need to find somewhere to go. And if you don’t allow them to use the curb, what the software we use does is just gives them short “fake” trips to take throughout the network, circling around where they expect the future demand to be. And that, as the results suggest, leads to a lot of cumulative extra miles traveled in the network. Some observers might believe these vehicles would just go back to a depot. Did you measure that? Unfortunately, we didn’t create scenarios around the vehicles going back to the depot. I wish we could have but we ran out of budget. Given that there are relatively few Waymo depots across the entire 49-square-mile San Francisco area, I suspect this would reduce VMT somewhat, but probably not by much. I’m not sure exactly how many depots Waymo has, but let’s say somewhere between two and five. Whenever a vehicle became empty, it would likely have to travel a fairly long distance to reach a depot, perhaps a mile and a half on average. It would then have to travel another mile and a half or so to pick up customers once a new request came in. So I think there’d be a pretty negative impact if the vehicles were always returning to the depot as well. Maybe you could bring that 60% number down to like 40-45%. To reduce the VMT, you’d need to have depots all over the city then? Yeah, I don’t think they [Waymo] are really into real estate development. They could partner with other companies, though. One thing we learned throughout the study is that the price of off-street parking is clearly time-dependent. In some parts of the city, such as commercial districts, parking might be very cheap to access at night but very expensive during the day. In residential areas, it’s usually expensive no matter what, and there are rarely large enough areas for a depot to be set up. Acquiring land is also expensive. I imagine they’re trying to minimize the amount of land they need to acquire and be strategic about where they park their vehicles. They’d have to consider both the location and whether they’d have to pay for parking there. Were there any other major findings? The other major finding, which Waymo liked a lot, was related to a metric we used called curb productivity. We measure curb productivity as the number of passengers who move between the transportation system and their destination per unit of time a robotaxi occupies the curb, including time spent staging and picking up or dropping off travelers. We found that robotaxis were about eight to ten times more productive than personal vehicles in terms of how they use the curb. A personal vehicle spends about one-and-a-half hours at the curb on average, whereas a robotaxi spends eight to ten times less time there, around eight minutes per ride served on average. If you’re concerned about one of a city’s most valuable assets, the curb, it seems that robotaxis use that asset much more productively than personal vehicles do. Personal vehicles can simply park at the curb and stay there for a very long time. Obviously, people can get out and walk around and do many things while their vehicle is parked, but you still have a very valuable piece of land being occupied by a vehicle that isn’t actively serving passengers. And I should say that buses are much more productive than robotaxis, which in turn are much more productive than personal vehicles. A bus is only at the curb for a very short period of time, but it can have many people getting on and off during that time. What can cities do in terms of regulating the curb? I’m not sure how many cities were considering banning robotaxis from using the curb, but if they were, I would say don’t do that. They might be increasing congestion a bit, but I think they’re providing valuable mobility to a large number of people in urban environments. Moving beyond our study, I am generally in favor of having desig

Listen to this episode on Apple Podcasts, YouTube, Spotify, and Substack. Transcripts are also available by clicking on the “transcripts” button in the top right corner of this post on the app/web version. You can also access them from the email version by clicking here. In today’s episode, I’m speaking with Dave Ferguson, Co-Founder and Co-CEO of Nuro. Dave reflects on Nuro’s first decade, what has kept him motivated through the AV industry’s ups and downs, and how Nuro’s co-CEO structure works in practice. We also discuss the differences between leading the technical and business sides of an AV company and how Dave’s role has evolved over time. Dave explains what makes Nuro’s approach to autonomy unique and takes us inside the company’s partnership with Lucid and Uber. We explore the vehicle’s hardware stack, how Nuro plans to differentiate as AV hardware becomes cheaper, and the latest milestones on the path toward fully driverless testing/deployment. Dave also shares how the Nuro Driver can generalize across different vehicle platforms and draws on Nuro’s previous driverless deployments to explain Nuro’s driverless capabilities. The conversation also examines whether the AV industry is moving toward full vertical integration or greater specialization, how building the software and hardware stacks compares, and how Nuro’s partnership with Uber could expand over time. Finally, Dave shares Nuro’s broader goals and what comes next for the company. Chapters * (00:00) Introduction to Dave Ferguson * (01:30) Nuro’s past decade, and the experiences thus far * (03:05) What keeps AV company execs motivated in the long run? * (05:28) How Nuro’s Co-CEO setup works, including the advantages, disadvantages, and roles * (10:10) Comparing the technical vs. business sides of running an AV company * (12:30) What makes Nuro’s approach to autonomy unique, and the Nuro–Lucid–Uber partnership * (14:45) The most compelling aspect of the Nuro–Lucid–Uber partnership * (15:35) Is the AV industry moving toward full vertical integration or greater specialization and partnerships? * (18:06) The software vs. hardware aspects of AV development * (20:45) The hardware stack on the Nuro–Lucid–Uber robotaxi * (22:50) How to stand out in the era of cheaper AV hardware * (24:48) The latest milestones in the Nuro–Lucid–Uber partnership * (27:32) What it’ll take to remove the safety driver, achieve fully driverless testing, and Nuro’s past driverless deployments * (30:05) How the Nuro Driver generalizes and transfers between different vehicle platforms * (33:50) Nuro’s relationship with Uber, how their partnership could evolve, and Nuro’s goals * (37:30) Conclusion and final thoughts Notes/Links: * You can find Dave Ferguson on LinkedIn/X. * My previous interview with Nuro’s COO Andrew Chapin, mentioned at the 12:32 timestamp (link). * Nuro, Lucid, and Uber announced plans to launch their robotaxi service in Houston in mid-2027 (link, no paywall). * Nuro’s website (link). -Harry This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.thedriverlessdigest.com

Listen to this episode on Apple Podcasts, YouTube, Spotify, and Substack. Transcripts are also available by clicking on the “transcripts” button in the top right corner of this post on the app/web version. You can also access them from the email version by clicking here. In today’s episode, I’m speaking with Peter Ludwig, co-founder and CTO of Applied Intuition. Peter shares how the company has evolved since its founding, the idea behind it, and its mission to accelerate the adoption of safe and intelligent machines worldwide. We also explore physical AI, how it differs from digital AI, and Applied Intuition’s partnership with HUMAIN. Peter breaks down Applied Intuition’s work in autonomous trucking, including its partnerships, current deployments, plans for global scale, and what it will take to remove the safety driver and achieve fully driverless operations. He also explains the most common causes of failure in autonomous vehicle deployments, the role simulation plays in safely validating AV systems, and how much technology can transfer between different autonomous driving applications, such as trucks and robotaxis. The conversation also covers end-to-end AI, Applied Intuition’s approach to commercializing and deploying the technology, and how the company works with partners to bring consumer products to market. Finally, Peter explains closed-loop simulation with reinforcement learning, reflects on lessons from nearly a decade in the industry, and shares his outlook on the future of autonomous vehicles. Chapters * (00:00) Introduction to Peter Ludwig * (01:19) How the vision and operations at Applied Intuition have evolved from inception to today * (03:54) Applied Intuition’s global footprint * (04:16) Peter’s past work experience and the idea behind Applied Intuition * (06:17) Applied Intuition’s mission * (07:32) What is physical AI, and how does it compare to digital AI? * (09:20) Applied Intuition’s partnership with HUMAIN * (10:41) Details of Applied Intuition’s trucking vertical and how it will scale globally * (14:00) Applied Intuition’s trucking partnerships and deployments * (16:20) What it’ll take to remove the safety driver and achieve fully driverless operations * (18:37) The most common causes of failure in AV deployments * (20:25) The role of simulation in safely deploying AV systems * (23:20) How much technology can transfer between different autonomous modalities, like trucking and robotaxis * (26:50) Lessons learned from nearly 10 years of operations * (29:12) End-to-end AI and Applied Intuition’s approach to commercializing and deploying it * (31:09) Applied Intuition’s B2C approach and how it collaborates with partners to launch consumer products * (33:15) Applied Intuition’s future plans and Peter’s outlook on the future of AVs * (35:40) What is closed-loop simulation with reinforcement learning? * (37:23) Conclusion and final thoughts Notes/Links: * You can find Peter Ludwig on LinkedIn. * Applied Intuition’s website (link). * Applied Intuition’s partnerships mentioned in the episode: * HUMAIN, mentioned at the 9:20 timestamp (link, no paywall). * Isuzu Motors, mentioned at the 14:14 timestamp (link). * Stellantis, mentioned at the 31:17 timestamp (link). * This partnership was extended in May 2026 (link). * Applied Intuition’s SDS for Automotive, mentioned at the 29:51 timestamp (link). -Harry This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.thedriverlessdigest.com

Listen to this episode on Apple Podcasts, YouTube, Spotify, and Substack. Transcripts are also available by clicking on the “transcripts” button in the top right corner of this post on the app/web version. You can also access them from the email version by clicking here. In today’s episode, I’m speaking with Frank Reig, CEO of Voltera. Frank explains how the merger between Voltera and Revel came together and how the combined company is building the infrastructure needed to support autonomous vehicle fleets at scale. We discuss where the industry currently stands in the AV deployment timeline, what has surprised Frank since entering the fleet-charging space, and why AV infrastructure development often takes much longer than vehicle deployment. Frank also breaks down what goes into developing a full-stack AV depot, from finding suitable real estate and securing power to providing charging, maintenance, and operational support. He explains how Voltera evaluates potential locations, works with customers to plan their infrastructure needs, and differentiates itself from other charging and depot providers. We also explore the operational challenges these facilities will face, how depots can adjust to shifting ride-hail demand, and what AV fleets could look like as they reach greater scale. Finally, Frank shares the trends he expects to shape AV infrastructure and what’s next for Voltera. Chapters * (00:00) Introduction to Frank Reig * (01:45) The Voltera-Revel merger and how it came together * (04:26) Voltera’s footprint, operating domain, and current focus * (05:13) What phase are we in the AV deployment timeline? * (06:38) What has surprised you since entering the AV fleet charging space? * (07:30) What actually goes into setting up an AV depot? * (10:04) How AV vehicle and infrastructure deployment timelines differ * (10:43) How Voltera supports its AV fleet partners with full-stack AV depots, including charging, maintenance, and operations * (12:04) The unexpected challenges of building out AV depots * (13:21) What factors do you consider before developing an AV depot at a location? * (16:01) How customers typically approach AV depot development with Voltera * (17:30) The strategy behind selecting the best sites for AV depots * (20:42) How Voltera stands out among its competitors * (22:30) Potential challenges in AV depot operations * (24:19) What Voltera does and what it doesn’t do * (25:50) What will AV fleets of the future look like, and what are the benefits of scale? * (28:02) Future trends in AV depot development * (29:30) How AV fleet infrastructure adjusts for shifting ridehail demand * (31:03) Voltera’s roadmap and future plans * (32:10) Conclusion and final thoughts Notes/Links: * You can find Frank Reig on LinkedIn. * Voltera’s website (link). -Harry This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.thedriverlessdigest.com

Listen to this episode on Apple Podcasts, YouTube, Spotify, and Substack. Transcripts are also available by clicking on the “transcripts” button in the top right corner of this post on the app/web version. You can also access them from the email version by clicking here. In today’s episode, The Driverless Digest Editor Ben Hubbard speaks with Gautam Narang, CEO & co-founder of Gatik. Gautam explains what fuels his passion for autonomous trucking and introduces Gatik’s approach to driverless freight, including its current fleet, commercial deployments, and areas of focus. He also discusses Gatik’s contracted revenue and what differentiates the company from other autonomous trucking developers. They take a closer look at why Gatik chose to focus on middle-mile, dock-to-dock routes and how its fleet management platform, Gatik Omni, allows customers to interact with and manage their autonomous freight operations. Gautam also breaks down the edge cases Gatik’s trucks encounter, some of the most complex scenarios they have successfully navigated, and the four core pillars underpinning the Gatik Driver. Finally, they discuss how Gatik measures autonomous vehicle safety, the company’s safety record, and the current state of autonomous vehicle safety standards in the United States. Gautam also explains how autonomous trucks could help address the freight industry’s labor shortage, why Gatik has attracted significant investor interest, and how the company is approaching capitalization, customer partnerships, and contracted revenue. He closes by sharing what’s next for Gatik as it works to expand its fleet and scale driverless freight operations. Chapters * (00:00) Introduction to Gautam Narang and what fuels his passion * (02:20) Introduction to Gatik, fleet size, driverless deployments, and focus areas * (05:25) Gatik’s contracted revenue * (06:30) How Gatik stands out from competition * (07:45) How Gatik came to focus on middle-mile dock-to-dock operations * (11:16) How Gatik’s fleet management platform, Gatik Omni, facilitates customer interaction * (13:41) What kind of edge cases Gatik experiences, and how it handles them * (18:35) What are the most complex scenarios Gatik’s trucks have dealt with well? * (20:22) Gatik’s vehicles specifications * (21:10) The four pillars of the Gatik Driver * (24:07) How Gatik measures AV safety, and the current state of AV safety standards in the US * (28:04) Gatik’s safety record and how the company assesses incidents * (30:13) Filling the labor shortage in the freight industry with autonomous trucking * (34:20) Investor interest in Gatik’s business, its capitalization, contracted revenue, and partners * (36:25) Gatik’s future plans * (37:30) Conclusion and final thoughts Notes/Links: * You can find Gautam Narang on LinkedIn and X. * Gatik’s website (link). This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.thedriverlessdigest.com

Listen to this episode on Apple Podcasts, YouTube, Spotify, and Substack. Transcripts are also available by clicking on the “transcripts” button in the top right corner of this post on the app/web version. You can also access them from the email version by clicking here. In today’s episode, I’m speaking with Emily Warren, Deputy Secretary for Innovative Mobility Solutions at the California State Transportation Agency (CalSTA). Emily explains CalSTA’s role overseeing California’s transportation agencies, how the state balances innovation with regulation, and what she has learned since transitioning from the private sector into public service. We also take a closer look at California’s newly updated autonomous vehicle regulatory framework, including how the DMV’s rulemaking process unfolded, what has changed, and how public feedback shaped the final regulations. Emily breaks down the respective roles of CalSTA, the DMV, and the California Public Utilities Commission in overseeing AV deployment, as well as how California approaches safety, data sharing, and coordination among local, state, and federal regulators. Finally, we discuss what the new rules mean for robotaxis and autonomous trucks, how driverless trucking could scale in California, and where the state’s AV regulations may still need to evolve, including the possibility of personally owned autonomous vehicles. Chapters * (00:00) Introduction to Emily Warren * (02:20) Background on CalSTA, the agencies they oversee, and Emily’s role * (05:00) How CalSTA balances transportation innovation and regulation * (07:05) What Emily has learned from transitioning from the private sector to public service at CalSTA * (09:20) The roles of CalSTA, the DMV, and the CPUC in California’s AV permitting process * (10:33) California’s new AV regulatory framework, how long it took, and what’s new * (13:40) Public feedback on the new AV regulatory framework * (16:46) Behind the scenes of the California DMV rulemaking process * (21:01) The right cadence for reviewing California’s AV regulations * (21:42) Areas for improvement in California’s AV regulations, including personal AV ownership * (23:01) How AV trucking could scale in California * (25:23) How CalSTA thinks about AV safety * (29:25) The differences between AV trucks and robotaxis in the new AV regulations * (32:56) AV regulation and coordination between the local, state, and federal regulators * (37:30) Data sharing between cities and state regulators * (40:04) Conclusion and final thoughts Notes/Links: * You can find Emily Warren on LinkedIn. * CalSTA’s website (link). * My podcast episode with CPUC Deputy Executive Director Pat Tsen, mentioned at the 09:24 timestamp (link). * California’s new AV regulatory framework, mentioned at the 10:42 timestamp (link). -Harry This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.thedriverlessdigest.com

Listen to this episode on Apple Podcasts, YouTube, Spotify, and Substack. Transcripts are also available by clicking on the “transcripts” button in the top right corner of this post on the app/web version. You can also access them from the email version by clicking here. In today’s episode, I’m speaking with Don Burnette, founder and CEO of Kodiak AI. Don shares what has kept him motivated after more than a decade in the autonomous vehicle industry, why he remains confident in the future of AVs, and how the space has evolved from years of R&D into real-world commercialization. We also dive into what Kodiak AI is building and its vehicle-agnostic physical AI approach, which spans long-haul trucking, industrial applications, defense, and more. Don explains why long-haul trucking remains such a large opportunity, what it will take to reach fully driverless operations at scale, and why highway-only autonomy isn’t enough to make the product viable. Finally, we discuss the differences between highway and city-street autonomy, how Kodiak approaches proving safety, and what it has learned from earlier deployments. Don also shares his perspective on scaling KPIs, the competitive landscape, Kodiak’s experience as a public company, and whether autonomous trucking could ultimately be a larger market than robotaxis. Chapters * (00:00) Introduction to Don Burnette * (01:30) What’s kept Don going in the AV space for over a decade * (02:15) Why Don is confident in the future of AVs, and some of the challenges the industry faces today * (04:09) How AVs have moved from R&D to commercialization * (06:30) What Kodiak AI does * (07:55) Kodiak AI’s generalized physical AI and how it’s vehicle agnostic * (10:07) Kodiak AI’s verticals: including long-haul trucking, industrial trucking and defense * (18:03) The role of robotaxis in propagating autonomy to the general public * (19:50) Why long-haul trucking has a bigger total addressable market than industrial trucking * (21:30) Steps to reaching full driverless operations in long-haul trucking, and how Kodiak AI is approaching it * (23:44) Why highway-only autonomy isn’t enough * (25:10) Highway vs. city-street autonomous driving * (26:59) Public perception of accidents and proving the safety case in AV trucking vs. robotaxis * (30:20) Learning from the experiences of earlier, broader AV deployments * (33:10) Experience operating as a publicly listed company * (34:50) KPIs for autonomous truck deployments and which ones Kodiak AI focuses on * (37:42) Competition in the AV trucking space and Kodiak AI’s position * (39:25) How individual incidents affect the general perception of autonomy * (41:50) Is autonomous trucking’s total addressable market bigger than robotaxi’s? * (43:41) Conclusion and final thoughts Notes/Links: * You can find Don Burnette on LinkedIn and X. * Kodiak AI’s website (link). -Harry This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.thedriverlessdigest.com

Listen to this episode on Apple Podcasts, YouTube, Spotify, and Substack. Transcripts are also available by clicking on the “transcripts” button in the top right corner of this post on the app/web version. You can also access them from the email version by clicking here. In today’s episode, The Driverless Digest Editor Ben Hubbard speaks with Brandon Basso, VP of Engineering at Wayve. Brandon breaks down the role of world models in autonomous driving and how Wayve is using them to train, test, and validate its AI Driver. He explains what problems world models can solve, where their limitations still lie when it comes to rare edge cases, and how Wayve’s latest model, GAIA-4, advances the company’s approach to simulation. The conversation dives into GAIA-4’s closed-loop capabilities, how it can simulate multiple sensor modalities, and why closed-loop testing could give Wayve an edge in virtual testing and validation. Brandon also explains the distinction between “AV 1.0” and “AV 2.0,” including how an AI-first approach changes the role of data, development, and validation. Ben and Brandon also discuss the challenge of optimizing autonomous vehicles for passenger comfort, what it takes to validate a more generalizable AI driving system, and how Wayve sees GAIA-4 playing a central role in the future of AV development and validation. Chapters * (00:00) Introduction to Brandon Basso * (02:20) Brandon’s day-to-day role at Wayve * (03:00) What is the Wayve AI Driver? * (04:05) What is a world model, and why is it used to teach an AI how to drive? * (05:11) What problem does the world model solve? * (08:04) How some edge cases constrain what can be tested using world models * (09:21) How far off are we from capturing all edge cases using world models? * (11:35) GAIA-4, Wayve’s latest world model and its new features * (12:06) Closed-loop vs. open-loop testing with GAIA-4 * (14:30) Multimodality and how GAIA-4 simulates different sensors * (15:27) How closed-loop simulation gives an edge in virtual testing * (17:38) The difference between AV 1.0 and AV 2.0 * (26:13) How difficult is it to optimize for comfort in the AV industry? * (27:02) How important data is to the AI Driver * (27:38) The challenges of developing and validating an AV 2.0 system * (30:55) The future of validation and GAIA-4’s central role * (32:18) Conclusion and final thoughts Notes/Links: * You can find Brandon Basso on LinkedIn. * Wayve’s article about GAIA-4 (link). * The diagram explaining the difference between closed-loop and open-loop, mentioned in the 12:08 timestamp (link). * Check out Harry’s earlier interview with Wayve CEO Alex Kendall (link). This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.thedriverlessdigest.com

Listen to this episode on Apple Podcasts, YouTube, Spotify, and Substack. Transcripts are also available by clicking on the “transcripts” button in the top right corner of this post on the app/web version. You can also access them from the email version by clicking here. In today’s episode, I’m speaking with Alex Pischalnikov, Senior Director of Strategy at MN8 Energy. Alex explains how MN8 has grown into one of the country’s largest renewable energy infrastructure companies and why its experience building and operating energy assets positions it to play a critical role in the AV ecosystem. We discuss the company’s business across renewable generation, battery storage, EV charging, and energy management, along with what differentiates MN8 in an increasingly competitive market. We also dive into the growing intersection between energy infrastructure and autonomous vehicles. Alex explains why charging is becoming one of the most important considerations for commercial AV deployments, how the needs of robotaxi and autonomous trucking fleets compare to large data centers, and why the location, design, and operation of depots can have a major impact on fleet economics. We discuss deadheading, charging strategies, fleet utilization, and the operational challenges companies face as they scale from hundreds to thousands of autonomous vehicles. Finally, Alex shares lessons the AV industry can learn from years of EV charging deployment, how MN8 works with autonomous vehicle companies to accelerate commercialization, and what the next generation of AV fleet hubs could look like as autonomous transportation scales over the coming decade. Chapters * (00:00) Introduction to Alex Pischalnikov and MN8 Energy * (03:05) What verticals is MN8 Energy focused on? * (03:58) MN8 Energy’s unique differentiator in the energy sector * (06:00) Inside MN8 Energy’s renewable energy infrastructure business * (07:33) The different types of customers MN8 Energy caters for * (10:00) Similarities between powering data centers and AVs * (11:45) How early are we in the AV cycle? * (14:25) The importance of charging to AV deployments * (16:20) The major cost factor in AV deployments * (18:52) How MN8 Energy helps AV companies deploy better * (21:40) The importance of different depot layouts for effective fleet management * (23:15) How to locate depots effectively to balance costs and reduce deadheading * (25:45) The biggest fleet management challenges when scaling AV fleets from hundreds to thousands of vehicles * (29:44) Lessons the AV fleet charging industry can learn from EV customer charging * (32:27) The future of AV fleet hubs and what they might look like * (35:40) Conclusions and final thoughts Notes/Links: * You can find Alex Pischalnikov on LinkedIn. * MN8 Energy’s website (link). * MN8 Energy’s article about AV fleets: Autonomous Fleets May Be Self-Driving, But They’re Not yet Fully Self-Reliant (link). -Harry This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.thedriverlessdigest.com

Listen to this episode on Apple Podcasts, YouTube, Spotify, and Substack. Transcripts are also available by clicking on the “transcripts” button in the top right corner of this post on the app/web version. You can also access them from the email version by clicking here. In today’s episode, I’m speaking with Matt Cragun, Director of Product for Autonomous Vehicles at NVIDIA. Matt breaks down NVIDIA’s strategy for autonomous vehicle development and how the company is approaching both the hardware and software sides of the AV stack. We discuss how NVIDIA works with AV developers to accelerate development, the role of its Hyperion platform, and how NVIDIA is making its technology easier to integrate across different vehicle platforms. We also dive deep into Alpamayo, NVIDIA’s open-source family of AI models for autonomous driving. Matt explains how Alpamayo works, how it was trained, and how developers can adapt the models to their own use cases. We discuss the limitations of the technology, how it approaches edge cases, and how Alpamayo combines end-to-end AI with more classical autonomous driving approaches rather than relying entirely on one or the other. Matt also discusses how Level 4 autonomy will eventually make its way from robotaxis into consumer vehicles, where the AV industry stands today, and what still needs to happen before AV technology can scale more broadly. Finally, he shares what excites him most about the next few years of autonomous driving and where he expects the technology to make the biggest advances. Chapters * (00:00) Introduction to Matt Cragun * (02:10) What is Alpamayo? * (03:50) Is NVIDIA more focused on building the hardware (chips) or software (models) for AVs? * (05:29) NVIDIA’s strategy for AV development * (07:03) How NVIDIA helps new AV developers accelerate development * (08:44) How open-source is Alpamayo, and can it be run on non-NVIDIA chips? * (09:28) Hyperion and how NVIDIA democratizes access to AV hardware * (10:40) How Hyperion is vehicle-agnostic and easy to integrate into different vehicle platforms * (11:20) How Level 4 autonomy will make its way from robotaxis to consumer vehicles in the coming years * (15:10) Digging deep into Alpamayo: How it works and how it was trained * (17:16) The limitations of Alpamayo and how AV developers can tailor it to their use cases * (19:20) The different use cases for Alpamayo, and its approach * (22:15) How Alpamayo combines the end-to-end AI and classical AV approaches * (27:23) How their AV models handle edge cases * (30:46) The current state of AV development * (32:52) What excites Matt most about the next few years for AVs * (33:50) Conclusions and final thoughts Notes/Links: * You can find Matt Cragun on LinkedIn. * An article about Alpamayo 2 Super on Hugging face, mentioned at the 04:43 timestamp (link). * NVIDIA’s article about Alpamayo 2 Super (link). * NVIDIA Alpamayo landing page (link). -Harry This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.thedriverlessdigest.com

Listen to this episode on Apple Podcasts, YouTube, Spotify, and Substack. Transcripts are also available by clicking on the “transcripts” button in the top right corner of this post on the app/web version. You can also access them from the email version by clicking here. In today’s episode, I’m speaking with Junko Yoshida, a veteran technology journalist and one of the industry’s leading voices on autonomous vehicles. We discuss where the AV industry stands today, why Waymo has emerged as the clear commercial leader, and whether autonomous driving is really a solved problem, or if the industry’s biggest challenges are still ahead. Junko shares her perspective on the importance of edge cases, what the recent Fourth of July Waymo incident in San Francisco reveals about scaling robotaxi operations, and how AV companies should be judged as commercial deployments continue to expand. We also dive into hybrid autonomy, the role of remote operators, and whether removing the safety driver is truly the right benchmark for autonomy maturity. Junko explains why transparency remains one of the industry’s biggest challenges, how journalists can better cover autonomous vehicles, and why there is often a disconnect between industry reporting and academic research. Finally, we discuss end-to-end AI, exciting developments in London’s AV ecosystem, and preview our upcoming ‘Journalist Panel’ at ATS 2026. Chapters * (00:00) Introduction to Junko Yoshida * (03:30) What journalists still get wrong in their coverage of AVs today * (05:03) Where we are in the AV landscape today and the factors still being overlooked * (08:30) Are AVs a solved problem? Why edge cases still matter * (10:26) Waymo’s 4th of July incident, and what they could have done better * (17:00) Should all AV companies be judged by the same standard as Waymo? * (17:48) Hybrid autonomy as a path to scaling AVs * (19:00) Is removing the safety driver proof of autonomy maturity? * (19:30) The importance of remote operators in scaling AV operations and boosting passenger confidence * (22:40) AV regulation and how to ensure the safest deployments * (26:29) London’s AV landscape and its key players * (27:14) Transparency and why it’s so difficult to cover the AV industry as a journalist * (28:30) The gap between industry reporting and academic research in the AV space * (29:17) End-to-end AI and the potential it could unlock if successful * (30:35) Exciting AV developments in London * (31:40) ATS 2026: What to look out for and our ‘Journalist Panel’ * (35:38) Conclusions and final thoughts I’ll be on stage with Junko Yoshida at SAE International’s Automated Transportation Symposium on July 30th at 11:40 am on the ‘Journalist Panel’ alongside Jane Lappin, Alan Ohnsman of Forbes, and David Welch of Bloomberg. Feel free to reach out if you’ll be in attendance! Notes/Links: * You can find Junko Yoshida on LinkedIn and X. * Junko’s blog: Junko’s Tech Probe (link). * Junko’s podcast/newsletter with Prof. emeritus Phil Koopman: Phil & Junko on AV Safety (link). * Waymo’s article on their remote operators ratio, mentioned at the 20:00 timestamp (link). * Here are some of my food recommendations for ATS 2026 in San Diego, mentioned at the 32:17 timestamp: * Downtown/Midtown * Lucha Libre * Luchador themed taco shop. Must get the Surf and Turf Burrito with fries (California Style) and try the cilantro crema (great salsa bar). * Las Cuatro Milpas * Longtime hole in the wall spot but recently renovated. Love the homemade tortillas and rolled tacos. * Phils BBQ (multiple locations) * Bronx Pizza * Blue Water (middle town) * Great fish tacos * Hodad’s * PB/La Jolla * Leilani’s cafe * El Pescador Fish Market & Restaurant * Famous Fish Sandwich * Other * Lolita’s Mexican Food (Clairemont Mesa) * Punjabi Tandoor (multiple locations) -Harry This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.thedriverlessdigest.com

Listen to this episode on Apple Podcasts, YouTube, Spotify, and Substack. Transcripts are also available by clicking on the “transcripts” button in the top right corner of this post on the app/web version. You can also access them from the email version by clicking here. In today’s episode, I’m speaking with Michael Arens, Founder and CEO of Clean Earth Rovers. We discuss how Michael went from an early failed prototype to building an autonomous maritime robotics company focused on cleaning waterways and collecting environmental data. Michael explains how Clean Earth Rovers’ autonomous vessels operate, the types of debris they collect, and the different deployment models they use for ports, marinas, municipalities, and other customers. We also dive into the company’s approach to autonomy, including where human operators remain in the loop, why a hybrid human-autonomous model makes sense for maritime applications, and how the hardware stack compares to what’s used in robotaxis. Michael shares his perspective on the broader maritime autonomy landscape, why the economics differ from autonomous driving, and where he sees the biggest opportunities for automation on the water. We also discuss the growing role of environmental data in Clean Earth Rovers’ business, how remote operations could evolve over time, and what the future holds for autonomous systems beyond roads and into waterways. Chapters * (00:00) Introduction to Michael Arens * (01:40) What inspired Michael to start Clean Earth Rovers * (04:10) From a failed prototype to Clean Earth Rovers * (04:50) Their Rover’s specifications, how it works, and its use cases * (06:44) Where Clean Earth Rovers operates, and how debris migrates there * (09:00) How the Rovers are deployed, and the different operating models for various clients * (11:10) How autonomous are the Rovers, and where human intervention comes in * (12:20) What kind of debris do the Rovers collect, and how is it handled? * (17:00) Advantages of the Human-Autonomous hybrid approach * (21:15) The hardware stack of the Rovers, and how they compare to robotaxis * (25:30) The maritime autonomy landscape and the innovations popping out of it * (28:20) The value of autonomy in the maritime industry * (30:34) The data side of the business and how they use the collected data * (35:22) How remote operation and autonomy would evolve for Clean Earth Rovers * (39:18) Conclusions and final thoughts Notes/Links: * You can find Michael Arens on LinkedIn. * Clean Earth Rovers website (link). -Harry This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.thedriverlessdigest.com

Listen to this episode on Apple Podcasts, YouTube, Spotify, and Substack. Transcripts are also available by clicking on the “transcripts” button in the top right corner of this post on the app/web version. You can also access them from the email version by clicking here. In today’s episode, I’m speaking with Henrik Green, Chief Technology Officer at Einride. Henrik shares his journey from a long career in the traditional automotive industry to helping lead one of the most unique companies in autonomous freight. We discuss the differences between building vehicles for consumers versus commercial autonomy, what attracted him to Einride, and why he believes the AV industry is entering an exciting new phase. We also take a deep dive into Einride’s business model, including its cabless autonomous trucks, hybrid network of autonomous and human-driven vehicles, and how the company combines electric trucking, autonomy, and logistics into a single platform. Henrik explains the technical and economic realities of Einride’s purpose-built vehicle design, how the company approaches scaling deployments, and the regulatory considerations unique to autonomous freight. We also explore some of the biggest technical challenges facing the industry today, Einride’s hardware choices and operational design, mapping, AI, and how they handle edge cases in real-world deployments. Finally, Henrik shares his outlook on the future of autonomous freight, where he sees the industry over the next five years, and what he’s most excited about as commercialization continues to accelerate. Chapters * (00:00) Introduction to Henrik Green * (02:33) Henrik’s background in the automotive industry * (04:00) The differences between the B2C automotive industry and the AV industry * (05:09) What drew Henrik to Einride * (05:50) Trends in the AV career space * (06:50) Einride’s background, and what makes them stand out in the industry * (07:35) Einride’s footprint, and their focus * (10:40) Einride’s cabless autonomous trucks, their specs, and current applications * (13:11) How Einride plans to scale, and their goals for the next year * (13:50) The economics of Einride’s autonomous trucks, and technical specs * (15:29) What hardware/software is unique to their cabless autonomous truck design? * (16:30) Regulatory requirements for autonomous freight vs robotaxi operations * (17:12) Hardware/operational differences: autonomous freight vehicles vs. robotaxis * (19:12) How Einride’s autonomous truck form factors could be optimized in the coming years * (20:14) Einride’s competitive advantage: Hybrid network of human-driven and autonomous freight vehicles * (22:50) Biggest technical challenges involved in building and operating autonomous freight vehicles today * (23:30) How Einride’s autonomous freight trucks are trained for deployment, and edge cases * (25:48) Pre-mapping vs. end-to-end AI: how Einride uses a hybrid approach for safe deployments * (28:40) Balancing commercialization with scaling: Einride’s approach * (31:00) What are you most excited about over the coming years * (34:55) 5-year outlook for the autonomous freight and robotaxi industry * (36:24) Conclusions and final thoughts See You at ATS 2026 The SAE Automated Transportation Symposium (ATS) is one of the premier gatherings for the autonomous vehicle industry, bringing together engineers, researchers, regulators, policymakers, and executives from across the ecosystem. I’ll be speaking on the Journalist Panel on Thursday, July 30 at 11:40 a.m. This year’s keynote speakers include Uber’s Head of Autonomous Mobility & Delivery, Sarfraz Maredia, Zoox Co-Founder and CTO Jesse Levinson, along with other leaders helping shape the future of automated transportation. Drop me a note if you’ll be in attendance, and registration is still open if you haven’t signed up yet. I hope to see you in San Diego. Notes/Links: * You can find Henrik Green on LinkedIn. * Einride’s website (link). * You can find details/pictures of their cabless autonomous trucks here. -Harry This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.thedriverlessdigest.com

Listen to this episode on Apple Podcasts, YouTube, Spotify, and Substack. Transcripts are also available by clicking on the “transcripts” button in the top right corner of this post on the app/web version. You can also access them from the email version by clicking here. In today’s episode, I’m speaking with Crijn Bouman, CEO and Co-founder of Rocsys. Crijn shares his background in the EV charging industry, what led him to found Rocsys, and why he believes charging has become one of the biggest operational bottlenecks for autonomous vehicle fleets. We discuss why depot operations deserve far more attention as robotaxi fleets scale, how much of fleet management can ultimately be automated, and why charging is the logical place to start. Crijn also discusses the Rocsys M1, the company’s hands-free charging solution designed specifically for autonomous fleets. We explore how the system works, why it is designed to be vehicle- and charger-agnostic, the challenges Rocsys faced bringing it to market, and what operators should consider when designing an efficient robotaxi depot. We also cover where the M1 is already deployed, what the AV depot of the future could look like, and the common mistakes companies make when planning fleet operations. Finally, we zoom out to discuss the global robotaxi landscape, including the differences between the U.S. and Europe, what Europe needs to do to become more competitive, and Crijn’s vision for how automation will transform depot operations over the coming years. Chapters * (00:00) Introduction to Crijn Bouman * (01:30) Crijn’s background, his history in the charging industry, and how he founded Rocsys * (04:31) How Rocsys supports AV fleets * (05:30) How much of AV fleet management can be automated? * (07:35) Why charging is such an important part of AV depot management, and why it should be automated first * (09:51) Initial challenges faced with automating AV fleet charging * (13:22) The Rocsys M1 hands-free charging solution for AV fleets * (14:50) The ease of deploying the Rocsys M1, and its other benefits * (18:20) Where the Rocsys M1 chargers are currently deployed and future deployments * (20:15) The ideal robotaxi partner/depot layout for deploying the Rocsys M1 * (22:40) What the AV depot of the future will look like * (27:05) Common oversights AV companies make when designing depot operations * (28:28) Rocsys’ global scale and the benefits of operating from the U.S. and Europe * (30:00) What Europe needs to do to catch up in the robotaxi space * (32:10) How Rocsys will transform the AV depot of the future * (35:15) What can’t be automated in the AV fleet depot, and why * (36:47) Conclusions and final thoughts Notes/Links: * You can find Crijn Bouman on LinkedIn and X. * Rocsys website (link). * Check out the Rocsys M1 (link). -Harry This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.thedriverlessdigest.com