Latest / Freightvine / Michael Wiesinger, Kodiak AI | Kodiak AI’s Sensor Fusion Future
Transcript
- Chris Caplice: Hello and welcome to the Freightvine Podcast, your source for all things freight transportation. I'm Chris Kaplas, chief scientist here at DAT Freight and Analytics, and this is our second episode in the Autonomous Freight Transportation Series this fall. Today, I'm lucky to be joined by Michael Weisender, the COO of Kodiak AI. Now, founded in 2018, Kodiak took a different approach than most other A V startups. Rather than relying on high definition mapping, They developed a single AI driver system that fully utilizes and fuses together an array of different sensors to include cameras, radar, and LIDAR. This essentially lets them operate anywhere. And so they were able to expand into three different verticals: long-haul trucking, which is the primary one most AV startups started with, but also defense applications and industrial operations like sand hauling in the Permian Basin. The industrial and defense verticals obviously need to be able to operate environments with limited. And constantly changing infrastructure where high def mapping simply isn't possible. Now their trucks in the industrial sector are operating without any humans in the vehicle, while the over-the-road trucking segment still requires safety observers. In our conversation, we discussed Kodiak's drivers-of-service model, when this was what allows fleet owners to integrate virtual drivers into their existing network, because Kodiak believes that autonomous systems will augment rather than entirely replace the current driver workforce. Michael also explains their statistical safety case framework as they prepare to take safety observers out of the cabs in their long haul trucking sector. So after my conversation with Michael, I'll provide a truckload market update. So let's get started. Hi Michael. Welcome to the Freightvine Podcast. Michael Wiesinger: Thanks, Chris. Thanks for having me. I'm excited to be on your podcast. Chris Caplice: You've you've done a million of these. you know, being in your space, there's a lot of interest in what you guys are up to. And so what I wanted to do is first before we talk about Kodiak, let's talk about you. How did your path get you to where you are now with Kodiak? Michael Wiesinger: Yeah, absolutely. so I actually spent most of my career in the automotive industry. started very early on working for Detroit Diesel. everyone in the industry will know Detroit Diesel is a subsidiary of Daimler Trucks. And so I worked there, then moved from operational into consulting, consulted for a Boston consulting group. And during that time was always affiliated to automotive players, mostly in cars, not in trucks. but I, you know. Consulted for most German. really most European OEMs in Europe, North America, South America, and mostly on network optimization and supply chain topics. So naturally you already see that there is a fit with autonomous trucking, right? Then before I actually moved to Kodiak, I also launched a startup for UPS with another and with a team from BCG Digital Ventures, where we actually stood up a warehousing network or marketplace that matches merchants with warehouses. So again, in the transportation kind of the supply chain space. And during that time I got extremely excited about building, about building something from scratch. And then the opportunity came up to join Kodiak and this amazing team and and I wasn't able to pass that up and I'm very excited that I made this decision back then. Chris Caplice: That's you've had a couple of different transitions, but first I have to ask, what made you want to be a paramedic? Michael Wiesinger: Yeah, so Austria still has mandatory either civil service or military service. And Chris Caplice: I didn't know that. Michael Wiesinger: and back in the day, I was actually one of the last cohorts that had like a 12 months mandatory service. So I was like you know, had to decide between military and civil service, and I decided for civil service. And I will say, and I did this for one year full-time, right? Those 12 months. And then I kept doing it for 12 years voluntarily, with a certain amount of hours that you have to do per year, a certain amount of training you have to do per year. And to me, it has been a great school for life. Mostly because you interact with people from different different kinds of lives, from different, you know, completely from kids to senior people, rich people, poor people. And I think it really t it teaches you a great deal of empathy. and I I always look back. I'm you know, since moving to the US it's a different system here. I didn't continue it, but I always look back at Chris Caplice: Yeah. Michael Wiesinger: that time. Chris Caplice: That that's interesting. I have a a brother in law who's who's a surgeon and he ta talks about do you ever see the T V show The Pit? Michael Wiesinger: Yeah. Chris Caplice: Can you watch it? 'Cause he says, you know, it's a little too real for him, you know, he that he doesn't need that after he when he sees it in his real job. Michael Wiesinger: Yeah, I generally don't watch those things because if you understand a little bit, you also know that most of the things are not actually accurate and so it's it's a Chris Caplice: Yeah. Michael Wiesinger: little bit hard to deal with it. Chris Caplice: Yeah, yeah, yeah. Yeah. So but another transition you did is going from consulting to a manufacturing company. How hard was that? 'Cause it it's it's sometimes people find it as a hard transition. there's a lot of golden handcuffs when you leave consulting, but then again you're not on the road four days a week. Michael Wiesinger: Yeah, I mean it's it's just a different different lifestyle for sure, but it's also a different mentality, right? Consulting is and you know, I look back to my BCG times with lots of gratitude and that I learned a lot and it was a great time. But at the same time you're recommending, right? And you're not actually implementing or building. Chris Caplice: Yeah, yeah. Michael Wiesinger: And so what I really realized, I want to build and I want to be responsible and accountable for the things that I'm building and not just say, yeah, this was a good recommendation or this was a bad recommendation in the end. Right. And that really made me exciting, excited. Now what's different? It's definitely, you know, BCG is a large company at this point, lots of structure, lots of support tools, versus them moving to a startup back in the day in 2019 when I moved. Kodiak was still fairly small, right? So exactly. Exactly. Chris Caplice: was only one year old, right? Was it founded the year before by Don Burnett? Michael Wiesinger: Was founded in April 2018. And you know, one year in you don't have a lot of processes, you don't have a lot of tools, you don't have a lot of infrastructure. So you can imagine I came in and was like, okay, let's build those things, right? Let's stand up the infrastructure. Let's make sure we actually make ourselves ready for for deploying a product and scaling a product in the long run. Chris Caplice: So one one last transition question, cause now you're the COO. First seven years you were VP commercialization, you're on the commercial side. I always think of commercialization external, up to COO internal. Did you see a transition there? Was it a big change in your responsibilities or is it just more of the same? Michael Wiesinger: Yeah, so maybe to to quickly describe the trajectory. I actually started at Kodiak as a product manager. And Chris Caplice: Okay. Michael Wiesinger: so back then I did product management, but I also of course supported Don and and the executive team with strategy topics and so on, coming well, coming with my background, right? That was natural. And then at some point, I don't remember which year it was, but You know, I I and Don and I had a conversation. It's like, hey, we need to start commercializing, right? Because we have great technology. but we we weren't yet like selling to customers and said, okay, we have to do this. And so Don was like, okay, build it, right, do it. and I basically built that commercialization function, hired an amazing team while still being responsible for product. And so as we as we went along and as we grew. More more responsibilities were assigned to me. And so at this point, I actually still lead the commercial side. commercial side, the product side, program side, as well as the operations, which were then added at some point. You might remember James Reed, who was our COO at some point, then moved on and now is actually the chairman of our board. And so I was reporting to him, and when when he moved on, I basically moved into the chairman position. I basically took on the responsibilities from him as as he has built the trust with me. And yeah, so it was really more of like a a natural progression than a big shift in responsibilities all at once. Chris Caplice: So it sounds like it's more it's additive. It wasn't a switch. Okay. Yeah, that sounds like Michael Wiesinger: Yes, I guess a hundred percent right now. Chris Caplice: a startup. Sounds like a small company. Six years, eight years in now. Eight years. Michael Wiesinger: Yeah, yeah, eight years in. I mean, you know, we are public companies in September twenty twenty five, but we still operate extremely nimble, extremely fast. We don't want to le kind of lose that culture of being capital efficient, of being fast in developing things. of course doing it the right way with structure, but still maintaining that speed from a startup. Chris Caplice: Okay, so give us an overview of where Kodiak is now. w where where do you stand in terms of the commercialization and eventually the scaling of the technology? Michael Wiesinger: Yeah, twenty twenty six is an extremely exciting year for autonomy, right? If you look across the board and specifically at Kodiak, so Kodiak operates in three verticals long haul, over the road trucking, industrial. Some people call it vocational, but first we call it industrial, and then in the defense space. And I'll walk through the three sectors to give you a good overview. Long haul trucking is where we have been operating a fleet of trucks since twenty nineteen for customers like Warner, GP Hunt, Martin Brouwer, Rural Transport, and many, many more that we actually have been hauling freight for. That's the segment where we still operate with a safety observer in the cap, but we are getting very close to actually taking that out and we can talk about that later. Chris Caplice: Yes, yes. Michael Wiesinger: And in the second segment, industrial, this is where we have operated since December 2024 fully without any human in the cap. So, what does that mean? We actually went out and kind of signed a contract with Atlas Energy Solutions, which operates trucks in the Pyramid Basin to haul sand for fracking. So basically bringing sand to Wellsite. And in 2024, as I said, We actually deployed the first trucks to them. But what's different, and really this is absolutely different compared to how what everyone else is doing, this is actually a model of them owning and operating the trucks. So it's a true sometimes people talk about transport as a service and driver as a service. This is a true driver as a service where they maintain, they dispatch, it's their DOT number and so on on the side of the trucks. We provide the virtual driver to them that does the driving. And so we deployed the first two trucks in December twenty twenty four and have now scaled to thirty five trucks, which to our knowledge is the l largest deployment, real deployment of driverless trucks in the world. And then in the defense space, we have been working with several branches. you know, started early on with the army, now also working with the Marines on a program called Nemesis, but also have forged partnerships with some of the key players. Think about general dynamics land systems, which we announced earlier this year, to really build a foundation to deploy our system in for ground autonomy applications in the future. Chris Caplice: Okay, that's great. So the three big verticals, let me talk of ask questions about them backwards. So I'm gonna start with defense. is that the least developed as far as commercialization where it is now? It's more prototyping at this point, or do you have anything actually in production or in commercialization? Michael Wiesinger: Yeah, I think if you if you think about where the Department of War and and the different branches actually are right now in the autonomy journey, it's still early on, right? It's still like they're trying to find the right use case, where do they want to deploy first, what the product will like exactly look like. And so yeah, I would agree there the the contracts are still early days, right? It's not yet okay. we we're scaling to the hundreds or thousands, but there is lots of traction. And if you look at the budget for twenty twenty seven, right, there's a huge jump in in budget that is actually dedicated towards autonomy for for military applications. So it is an exciting time. We look at it very opportunistic because it's harder to plan. It depends a lot on you know what happens, how decisions are made and lots of changes happen. So it it is exciting, but again very opportunistic. Chris Caplice: Yeah, and it's it's kind of the opposite of the other two, which are it's certainly for long haul trucking, which you're gonna be on highways, well structured, well known. For the military, I've done we've had a fellows program here for twenty years. We have colonels come in and they talk about the need for autonomous, especially in the theater. And and because but in those situations there is no infrastructure. So it's Michael Wiesinger: Yeah. Chris Caplice: a very different problem, right? It's more sensor-driven, you can't have a map. of of the Michael Wiesinger: Absolutely. Chris Caplice: of the area. So is it a different technology or is it more of the same technology, just slightly different parameters? Michael Wiesinger: Yeah, I love what you picked up on there. Actually At Kodiak, we operate one single AI driver for all use cases. And that is actually one key differentiator and a key enabler for us, and why we are able to serve three use cases or verticals at the same time. So very early on, Dawn and the team of founding engineers have actually made a very bold decision, which was to not use high definition maps. There were several decisions, but that that was one key one. Not using high definition maps for any use case or for any vertical. And Back in the day, of course, high definition maps were coming from robot taxi development, right? Everyone was using it because you know that's how things were done in 2018. But they said, let's not do it that way. And that has enabled us to one be much more flexible and be much more nimble in what we do, where we can deploy, and not have like a rigorous six-month process where you have to map something to then to then basically put a new product out, right? And that is In actually across all three verticals, it's really paying dividends today. But it is in industrial and defense, of course, a massive game changer. Think Chris Caplice: Yes. Michael Wiesinger: about industrial, where we have again hauling sands to well sites. Well sites typically are operational for somewhere between three to five weeks, right? So every three to five weeks, you need to change your route. And obviously at this point, we operate with a s a fleet of 35 trucks. We or Atlas operate several routes at the same time. And sometimes they say, Hey, in a couple days, we need to have Route X ready to go driverless, right? So if we would then say, yeah, let's just create this high definition map, rang lines come back in five months, well, we would have missed the whole well side by four months. And so this approach is really the enabler for actually operating in the pyramid. Same in the fence base. Think about Chris Caplice: Yeah. Michael Wiesinger: You know, going to Ukraine today and saying, never mind, we are just mapping here and we will come back in two years with our fully defined map and and then we will actually it just doesn't work. Right. So really not being reliant on those high definition maps is a key enabler and key differentiator for us. Chris Caplice: Does that does that cause a corresponding negative or a downside? Is it mean do you still have that 'cause I'm trying to think for maps for the highways that you're you're able to ad use that very quickly. Does that slow the adoption rate for like the long haul over the road or is it not have an effect? Michael Wiesinger: No, not at all. quite the opposite. Because when people ask us, like we have customers that ask us, hey, can you do this new route in two weeks? I think we are probably the only company that can say, yes, we are actually able to do that. There is just to to finish that thought, really Chris Caplice: So Yeah, yeah. Michael Wiesinger: early on, high definition maps were to some extent used for localization, right? And Back in the day, you know, we weren't where we are today with all the advancements that have been made. And so we had to do localization slightly different. And it was a little bit of a gamble maybe early on, right? To go a different route. But again, it it worked out it pays is paying the dividend across all sectors right now. Chris Caplice: So so what is the technology then on the vehicle itself? Do you have video, lidar, and radar? Do you have a combination of those? Michael Wiesinger: Absolutely. So we deploy something that's called sensor fusion. Sensor fusion basically means you bring all kinds of sensor modalities together, which is cameras, which is radars, which is lighters. All of them have benefits and and some ERS where they are not as strong, right? Different weather, for example, different distances. But you want to bring all of them together if you want to develop and deploy a real driverless product. Because again, you want to leverage each sensor strength. Chris Caplice: So you called it sense of sensor fusion? Is that what it is? Okay. Okay. Michael Wiesinger: Science of using is taking the inputs from cameras, radars, lighters, and kind of using it together to an accurate picture of the environment. Chris Caplice: That's a really interesting technological problem then, because you've got three sources of the truth and you've got to decide which one is true. that's gotta be interesting. Is that done, I assume, in the software? Okay. Michael Wiesinger: Exactly. The on armboard compute handles all of that. Chris Caplice: Yeah, and so the rise of the improvements in AI and d the just compute power has certainly made that something that is more usable. But same with the defense then. So do you see this being used more in like an industrial back Back of lines type operation or do you see it used on the in the theater of contentious, in the on the battlefield? Michael Wiesinger: definitely has applications in both. Yeah, Chris Caplice: I knew you were gonna say that 'cause you're you're selling, you're commercializing, right? Michael Wiesinger: I mean if you if you talk to the the customers there, right, they think about tactical use cases, they think about more like logistical or supply operations use cases. A as I said, I think the armies general all branches are still exploring where they actually believe it has the biggest impact quickly. that's like something that they try to understand through all of these programs. But certainly you can think about autonomy really everywhere in in the world or everywhere in in supply chains. Chris Caplice: And so then in the industrial for the Permian Basin, was that something when when the company was far formed in twenty eighteen, twenty nineteen, was the initial thought to go to these other things or were they just opportunistic at the time? Michael Wiesinger: Yeah, it was more serendipitous and and a little bit Chris Caplice: Okay. Michael Wiesinger: coming to us. We did in 2019 focus on long haul over the road trucking, right? In 2021 was the first time we started working in the defense or public sector that back in the day that was actually an Air Force project. And then at some point, Atlas came to us saying, Hey, we see what you're doing on the highway. We see what you're doing like off-road, really. We are somewhere in the middle. And so Chris Caplice: Yes. Michael Wiesinger: can can you make something work? Because we do have roads. It's like a structured network of roads. Some of them are paved, some of them are calichi clay, some of them change every day, some of them are kind of more Chris Caplice: Yeah. Michael Wiesinger: steady. And they said, Can you make this work? And we said, Well, let's take a look. We certainly have the the core foundations. We certainly have set up our system that way. And that's what we basically did in twenty four, twenty twenty four. we brought a truck there, we tested it. It really worked out of the box, which we were all, including Atlas, really excited about. And then we said, Okay, how do we make this a product? How do we deploy? And we focused the next twelve months on actually doing that until we deployed the first two trucks there in December twenty fourth. Chris Caplice: And you described it as a driver as a service, so Atlas owns the vehicle, has the DOT license, all that stuff. You're providing the software. That makes it pretty sticky at this point for for for you guys, I would assume. It would be very hard for Atlas to to switch to another provider. Is that a fair statement? Michael Wiesinger: Yeah, and I mean, yes, that is absolutely an a fair and accurate statement. From our perspective, and think about not just Atlas, think about over-the-road trucking. There's a huge driver shortage, we all know about that. Twenty twenty six with you know non-domicile driver issue, there's actually the demand for autonomous trucks is truly rising by by the day almost. Chris Caplice: Yeah. Michael Wiesinger: And so, yeah, do we believe autonomous trucks and our system in general will be extremely sticky? Absolutely. Do we also Chris Caplice: Yeah, yeah. Michael Wiesinger: believe that the driver as a service model, as as you described it, will help with that even further? Because they own the truck, they operate them truck, they need the drivers. And you know, we provide the driver, yeah, we absolutely think that way. Chris Caplice: If so let's say Atlas has a a truck and and you're providing the driver as a service, can can a human actually go in and use that truck? They can override. Okay, Michael Wiesinger: Absolutely. Yeah, I think Chris Caplice: so it's not the the the hardware's not designed to not allow a human in there. It's not cabless. Michael Wiesinger: No, it it wouldn't make sense as w where we stand today, right? There are scenarios, Chris Caplice: Mm-hmm. Michael Wiesinger: let's say they want to take the truck and drive it into a maintenance bay, right? Or they want to take the truck and do something completely different than redesigned together. They want to have the ability. I know you know, back in the day there was like concepts maybe five or ten years ago at this point where of a cabless autonomous truck. It has never materialized because I think everyone understood that there are just situations where you still want to put a driver in. And so we believe right now this is this is still the best approach. Chris Caplice: Yeah, it's funny as I talk to more and more companies in this space, they you you realize and everyone's realized, drivers do more than drive. Right? Michael Wiesinger: Yeah. Chris Caplice: There's these other activities you need to do and how how do you get those do the robot can't do it by it by itself. So what about for other like mining operations? Because that seems like another natural fit as well as agriculture, because those are if you go from a battlefield where you you know, you can do anything, right? to a controlled environment like what you described in the Permian Basin or mining or agriculture. And this seems the most the riskiest as far as involving other people would be the long haul on the highways. Have you have you looked into mining as well or agriculture aspects, or are those two different? Michael Wiesinger: Yeah, when when we talk about our industrial vertical, we generally think about three use cases and I will explain why. One is what we call oil and gas kind of fields and and everything that's happening in India, right? The second one that we have actually worked on and have deployed a a pilot in is logging transportation. So there's actually a huge demand because those are extremely remote locations, very Chris Caplice: Sure. Yeah. Michael Wiesinger: hard to find drivers, reliable drivers, right? So this is another use case that is huge. And then third, we think about mineral transport. So minimal transport comes close to what you consider mining, but isn't necessarily mining. Chris Caplice: Yes. Yeah yeah. Michael Wiesinger: Think about taking goods from a mine to a port, from a mine to a rail yard, right? Those sometimes are fifty miles, can be a hundred fifty miles, can be longer distances. Think about Australia, right? It's all it's Chris Caplice: I was gonna say, Australia seems to be a a huge market for you guys. Michael Wiesinger: Abs absolutely. Yeah, we are exploring all of that. Now, to answer your question about mining, mining has very different software requirements. It's actually very simple, right? And you have seen some companies deploy some version of its remote control, but anyways, right? Some version of autonomy. And we could absolutely deploy there. Our stack is almost over sophisticated for actually deploying in mine. And so we need to be smart and really think about where do we get the biggest bang for the buck. And that is in other verticals, in other use cases, and it is specifically in long haul trucking, right? The the stack that we have built, the sophistication that we have built is actually good enough to work on on highways. And so this is the biggest ham. So naturally, this is where we will put our focus. Chris Caplice: makes that makes sense. So last thing before in industrial before we get to the long haul, the main reason why I'm here. is for the industrial, for when they're in the Permian Basin, do you have a remote driver? Is there someone monitoring it? Or is it pretty much you say gotta get from A to B and you let it go? Michael Wiesinger: Now it's actually the truck is truly on their own. We do have a 24-7 command center, and the truck can call for help. If there's Chris Caplice: Okay. Yeah. Michael Wiesinger: any if there's any issue, if the truck gets stuck, or let's just assume there's a tire blowout or something like that, right? We have a 24-7 command center that can respond to any kind of support the truck needs. And we can then triage is it something on the truck? And we will tell Atlas about it. Is it something with our system? We can kind of take care of that, right? So there is a command center, but it's not like there's a remote driver. That is that is important. It is truly wild. I've been out there a couple of weeks ago. and you know, you you we obviously I know that we are working on this every single day, but then you see a truck driving by no one in the cab. It doesn't get old. I'll I'll tell you Chris Caplice: Yeah, yeah. Michael Wiesinger: this. You you should absolutely come and and visit us because it's just so Chris Caplice: Love to. Michael Wiesinger: cool. Chris Caplice: Next time I'm I'm in the Permian Basin. No but Michael Wiesinger: Yeah, if you if you ever kind of trying to go on vacation in premium basin exactly stop by. Chris Caplice: It's it's a vacation spot. no, but it's it's so how does that work? They so it has to have some kind of map, right? It has to have so it doesn't have to be high def, but it has to have some kind of map to route or else it's just gonna go across the countryside and the point. So is is it a rudimentary map that it's then uses its sensors to stay roughly in line with? Michael Wiesinger: Yeah, we have very accurate description, actually. It is a we call it a light map. we sometimes describe it as mostly a routing layer, right? That's what people understand. Think about Google Maps, right? It yeah, it knows Chris Caplice: Got it. Yeah, yeah. Michael Wiesinger: it knows where the roads roughly are. But the thing is, especially in the Pyramid, it cannot fully rely on it because the map slightly changes, right? So we Chris Caplice: Sure. Yeah. Michael Wiesinger: still need to use all the sensors and pick up if there were any changes, and we can actually live update those, right? Because It is important, even though the the map or the kind of the rope might have had this edge, a certain edge yesterday, today it might be different because there was a windstorm or whatever it was. So yeah, there is a rudimentary map, but really the truck is acting based on what it's seeing life. Chris Caplice: That that makes sense. And I've I don't know, we're focusing on T V shows here. Do you watch Landman? Have you seen that show? Michael Wiesinger: Yes, o of course. I mean I I'm not much of a T V watcher, but you know, getting into the Atlas business and working with them, I felt obligated to do it. And and I will tell you, I've heard I've heard everything from some people say yeah, it's pretty accurate. Some people say yeah, eighty five percent is is made up, but I think it's a great Chris Caplice: Yeah. Michael Wiesinger: show regardless. Chris Caplice: Yeah, yeah. So that that that's really interesting. Okay, let's get to the to the main reason for this podcast. Over the road, long haul. So what was the big challenges? 'Cause it's it's kind of what you were originally starting to do, but these two other ones were diversions that Very profitable. I assume that it's a revenue source and it's really interesting. It's helping you be better on the long haul trucking. What are the big challenges that you're facing now for long haul trucking? Because I think it's the only one you said that still has the observer driver. Yeah. Michael Wiesinger: Correct. We still have a sub server in the cab for our long haul operations. Chris Caplice: Right? Michael Wiesinger: So you know, we are currently working through what is called the safety case. we just announced an update to our autonomous readiness measure, which is basically how we measure ourselves to be already or to have closed our safety case. We announced ninety three percent per the end of August, up from ninety one percent by the end of July. So you see a really, really solid progression. We have communicated that we are targeting the end of the year to actually do the first runs without the safes safety observer in the cap and and we we believe based on that trajectory that I just laid out that we are really on track. So what Chris Caplice: What is a safety case though? I I didn't don't quite understand exactly what that means. Michael Wiesinger: Yeah, safety case is a it's a buzzword that's used a lot. And think about it in very simple terms. It's a statistical argument that says how safe your system is. So you kind of have a top claim. Top claim can be: I we want our system to be at least as safe as the average human truck driver, right? And then you need to find statistics to actually back that up. So there's different things you do. Safety case has like all kinds of hardware related things from the truck perspective think about functional safety from a software related thing it's safety of the intended function and many many other aspects where you also need to have safe operational processes, cybersecurity processes, and all of that. But generally speaking, what we deploy, and I think this is something that that that resonates and people can easily understand, a probabilistic risk assessment. Meaning when we assess how well we handle a certain situation, we work with a model that's used and was developed actually by NASA, that's used for nuclear reactors and all kinds of safety critical industries. And basically says, okay, there are like thousands of things that could happen. Right. And everything has a certain exposure, and a certain severity, and a certain probability. And so you basically have those values, and those values you have comparison, right? From for example, we work with the University of Michigan, Michigan Transportation Research Institute, and you basically then came up come up with values that compare against human values. You take that from Your on-road data, your simulation data, your different OED analysis, different other scenario databases, right? So really you basically say, okay, I want to make sure that in all those cases, including some unknowns and knowns that we just don't know yet, that we are safe enough and that we meet our safety bar. That's really what the safety case does. That's a lot of work, right? Working through all these scenarios, but that's exactly the work that we are currently working through. Now, mind you, In the industrial space, we have worked through the same safety case, right? We have worked through getting to 100% in December 2024. So we have built the muscle on what we need to do, how we run through the through the process. And that's what we are now applying to the over-the-road business. And that's what we are aiming for 100% by the end of this year. Chris Caplice: Okay, so you're at ninety-three percent, and that that's not like ninety-three percent of the times your trips won't have an accident. It's it's much, it's much higher than that. But the the 93%, Michael Wiesinger: No. Yes. Chris Caplice: so that means 7% is there. Where is that 7% coming from, do you think? Is it technology? Is it the the the redundancy of the hardware? Is it the regulatory side? What what is causing that 7% if that you want to shrink down? Where do Michael Wiesinger: Yeah. Chris Caplice: you think the sources are if you did like a failure mode analysis? Michael Wiesinger: Yeah, so so what's important is that the seven percent doesn't mean that that there is seven percent of things we wouldn't handle. That that is not the case. It basically Chris Caplice: Sure, sure. Right, Drake. Michael Wiesinger: means that there are seven percent of things left that we haven't fully validated yet. So the technology might actually already be there, but we still have validation work to do. I'll make an example on validation work is mostly edge cases. Think about I don't know, there's a vehicle on the shoulder that has a ladder sticking out into the right lane, right? And our truck needs to handle it by you know either making a lane change if possible, slowing down, coming to a stop. so that would be one of the edge cases. There are there's other edge cases like that, but it's really not anything core technology anymore. You mentioned redundancy, our trucks have redundant braking, redundant steering, redundant power, right? There's no core technology. Technology element, it's really just about validating all the scenarios that could happen. Chris Caplice: So what there was a recent FMCSA ruling about the triangles, Michael Wiesinger: Mm-hmm. Chris Caplice: which is kind of a seems like a silly thing if there's an accident, who's gonna put the triangle out? And I Michael Wiesinger: Yeah. Chris Caplice: don't know, different companies have are trying to arrange that they use some other signal. With your current safety operator there, they can take care of that. Is that part does that figure into the safety cases or is that something totally different? Michael Wiesinger: So the morning triangle well, first of all, I mean, going back to your initial question about me being a paramedic, I will tell you all the accidents I have attended to I have never seen safety triangles actually being put out the way they should be, not a single time. Second, I think it's the unsafest spot for anyone to be on the highway to walk like next to the fog line with this this triangle in your hand, right? So, you know, we can all debate about the whole safety triangle topic. But importantly, the autonomy industry really worked together. Everyone came together and said, Hey, we need something better, because first of all, it doesn't make sense. Second, it doesn't actually work for a truck that doesn't have a human in the cab. So what we did is we developed a pr an approach To basically put a warning beacon super bright on the top of the truck. In our case it's on the it's on the top of our sensor pods, and then applied for an exemption. And that exemption was granted now many, many months ago. And that's basically the way we we I don't love to say circumvent because I actually think it's the better approach, but I will call it circumvent for for now. but that's how we don't actually ha need to have somebody to put out the warning triangle. Chris Caplice: Makes sense. let's switch topics a little bit and talk about Bosch. Is that okay? And can you talk about that Michael Wiesinger: Mm-hmm. Chris Caplice: partnership and where that fits in the evolution of what Kodiak wants to achieve? Michael Wiesinger: Yeah, absolutely. I mean, in general, we are a company that approaches things from an ecosystem perspective, right? We don't believe that we need to build everything ourselves. Right. There is great companies that have built manufacturing capabilities, that have massive supply chains that are really, really good in certain things. We obviously haven't had the time and the rigor to develop those yet, right? And Bosch is one of them. Bosch is one of the, if not the largest automotive OEM. Extremely good reputation. And so we said, hey, you know, we know what we need to do in the future to deploy and scale. And they know how to manufacture, they know how to scale, they know how to build the right supply chain for the components that we need. And so this that that's really the partnership. We we basically work with them on evaluating the components they have and then making it into an autonomous, fully autonomous system together. Chris Caplice: Okay, so so if I look at some the path for companies in the space, there's some proof of technology, proof of concept, then there's pilots, the proof that it works in operations, then there's commercialization. We actually get paid for it, and then there's scale for this. And so where do you is is is Bosch the thing that's helping you go from commercialization to scale? Okay, and so where is the core expertise of Kodiak then? is it in the software? Is it in the the system that the what you call the the the sense sensor fusion? Michael Wiesinger: And the possible Chris Caplice: Is that the core essence of it? And then you're using partners for manufacturing of the equipment around it? Michael Wiesinger: Yeah, I would say it's it's several things. One of is of course the software, right? The AI driver. Again, having built a single AI driver that works across use cases, that can be trained. One use case helps the other, helps the other, and so on, right? that's of course core of what we have done. Second is how we have actually designed the system around it, meaning the hardware, the sensors, and so on, right? We have We have done things a little bit differently than most of our competitors with putting all the sensors in what we call the sensor parts, meaning the cameras, the lighters, the radars that we discussed earlier on, they all are in one rigid structure that can be easily taken off and replaced in case something would go wrong, which is good for uptime and reliability, right? And so that design, including the software, are really our kind of key IP Chris Caplice: Okay. Michael Wiesinger: if if you want to. Chris Caplice: Sure, sure. Michael Wiesinger: But the manufacturing of those components and and subcomponents and sub-assemblies, that's not core of what we do, right? That's where we want to work with suppliers, Bosch one of them, but of course we work with many, many others. Chris Caplice: So if I I have a fleet of trucks and if I want to work with Kodiak, can you retrofit my existing vehicles to be autonomous? Michael Wiesinger: Yeah, our system is platform agnostic. So basically we have designed the system to integrate into any truck, into any model. We have actually at this point deployed several different truck makes and models, including DCAP, which we recently announced on the Western Star 49X, which is a Daimler platform that that Atlas picked for their next 65 trucks that they want. And so we have really designed it to be modular. and so yes, the answer the answer is yes. Now when you say retrofit, would I or we as a company want to take a five year old truck with five hundred thousand miles and then put autonomy on top? I don't think that's the best use of the autonomy system, right? I think it's always better in a in a new truck. but yeah, in theory it it's possible to to upfit any truck with our system. Chris Caplice: So whenever you make a design, you you're an industrial engineer, I I'm an engineer, there are trade offs involved. And so what what is the major trade off that you think that Kodiak made by making it so that you're agnostic to platforms? Does that mean what what does that mean? Is there a downside at all for that? Michael Wiesinger: I wouldn't call it the downside. I mean, I I think it took there was more onus on us to actually make this work, right? The the reality is the OEMs don't yet have the ability to manufacture thousands of those or ten thousands of those trucks, right? And so since we live in this reality, but we couldn't wait for that to happen, we basically said we have to find our own path and we have to develop a system that we can integrate into any truck. Does that take work? Absolutely. Right. You you have to make different design decisions, Chris Caplice: Sure. Michael Wiesinger: especially when you say we want to be able to integrate in a decap. We want to be able to integrate in a European cab over even, right? So yeah, you make some trade-off and some different decisions. And sometimes it takes more work to actually say, yeah, this is a good solution. but that's really the approach that we have taken. Chris Caplice: Yeah. And so what is Kodiak's business model then going forward? Right now you you describe driver as a service to Atlas. Do you see the same kind of model going to carriers now that would be going, or would you sell this as a service? Do do you see yourself, Kodiak, as a provider of the trucks and becoming a carrier? How do you see this falling out for the long haul trucking side? Michael Wiesinger: Yeah, we we want to bring the drive as a service model to all to all sectors that we work in. Right. So we have deployed that drive as a service model with Atlas since now, you know, over one and a half years, almost two years at this point, and we believe that's the right model for the future also for long haul trucking. So yeah, we work with some of the carriers. I'm I mentioned them earlier on already, but we work with them and saying how do we make this a product and a solution that works within your operations, right? Within how all the processes that you have already set up. We don't want to replace them, right? We don't want to become a competitor to them. I mean, they have decades of experience of how to acquire freight, how to maintain trucks, how to dispatch trucks, right? I want to be able to partner with them so they can do their core competences and we can bring our core competences, which is the virtual driver, and create a solution that is beneficial and driving value for all of us. So yes, Chris Caplice: So that Michael Wiesinger: driver as a service is the model for us. Chris Caplice: Okay, so I'm a I'm a carrier and I've got, I don't know, two hundred and fifty drivers. And so I wanna start working with Kodiak. So I have some other trucks and I modify them to make it so that they can be autonomous. And then is it up to me to how I use them within my network? Is it essentially you just turn on the services and then they it's up to them to utilize and and set things, or d are you the middleman for them to operate those trucks? Michael Wiesinger: It's a it's a tight collaboration, right? I I think autonomy is a is a product. It it's not like you go to a supermarket and buy whatever product you want and you just consume it, right? Autonomy is much more requires more sophistication. So the the thing that we have actually built with carriers, with Atlas is Chris Caplice: Yeah, yeah. Michael Wiesinger: the partner deployment program, where we basically have laid out the a program that is like sometimes a multi-year program where it says, okay. We start with analyzing where in your network would autonomy actually make sense. Where does it bring the biggest value? Because there are lanes where it has more value. There are lanes where maybe I wouldn't start with, right? Second, then analyze, okay, what does the end-to-end process look like in the future? Who is doing fueling? Who is doing maintenance? Who is launching and landing those trucks, right? Or supporting the launch and land of those trucks. Then lay out kind of how do we integrate with your systems? Typically, Carrie has a transport management system. They have a flip fleet management system, right? So we need to integrate with all of those for them to actually have a solution that really works seamlessly and actually brings them the value. And then of course define KPIs, define metrics, define the rollout. Why do I think this is so critical? Because I'm convinced that in the future, autonomy companies will not necessarily differentiate each other by, you have built cool technology and your technology is slightly better in that scenario versus this one, right? I think they will differentiate by how reliable the system will work and how effectively it's integrated into the carriers and fleets operations. That I think is key. That's exactly what we have done the last again, one and a half, almost two years, where we defined what are all the things that we need to build around the technology to make this a product that we can actually deploy to our customers. Chris Caplice: And your customers are the carriers. Or for a shipper if they have a private fleet, but whoever's earning their fleet, okay. Michael Wiesinger: Correct it can be any anyone really that operates a fleet, is is a potential customer. Chris Caplice: Got it, got it. So if I look at my network, what are the types of lanes that are more attractive, you think, to autonomous trucking? Is it short length the hall, long length the hall? Is it the consistent freight versus the infrequent lanes? Or is it drop and swap lanes where you're just picking up and dropping off or live load? Is there a certain sweet spot of a type of lane that that you see that a carrier would generally adopt autonomous? Michael Wiesinger: Definitely. I mean and we have had many of those conversations with with the carrier partners that we work with. It it's not that the technology really cares, right? The technology is like, yeah, I'm gonna I'm gonna do the driving no matter what. But what how the way we actually approach this is what brings the most value to the carriers or difference, Chris Caplice: Right, right. Michael Wiesinger: right? And basically if you look at the landscape, long lanes, it's really, really hard to find team drivers, especially for time sensitive freight. Are some carriers who have kind of implemented a relay concept, but it's always Chris Caplice: Right, right. Michael Wiesinger: kind of nascent, right? again, because it's hard. And so we believe autonomous trucks is just an additional modality. Think about intermodal when that was introduced. So autonomous trucks are an additional modality just like that. And I believe the benefits will be highest, everything that's it that is longer lanes. Think about everything above one hour of service because. Once you get above one hour of service, you either have to lay over a driver where you need a team. and and and and all of that costs either time or money, right? So naturally to me, those are the longer lanes are absolutely the the biggest value lanes. Does that mean we couldn't do shorter ones? No. But at the same time, we are working with the carriers to say, okay, you have drivers, they have core competences, we have autonomy system, that has kind of its strengths. So, how can we combine those? How can we create a network for you together where you say, for example, you have drivers on kind of the shorter lanes, maybe even the store deliveries, right? For somebody who has like a ton of store deliveries, and then you use autonomous trucks on the long haul shuttles to kind of complement that, allowing the drivers to be home every day. And so they don't need to be on the on the road. So it's really about understanding what makes most sense. There is no one Chris Caplice: Yeah, yeah. Michael Wiesinger: size fits all. so it's really a collaboration with our Chris Caplice: I think people are still trying to figure that out. But one one thing you mentioned, the hours of service, to me that makes the most sense, right? If you can go longer and you don't need to have a driver needs to to to stop a day and rest and all that. But even the bar is even lower than that. We just finished a study looking at ELDs and the average and I forget how many thousand of drivers we looked at Long haul trucking, on average, they only drive six and a half to seven hours a day. And yeah, we say eleven, but they don't. They just don't. It's very rare. And so the bar to make it sense, if you can fully drive all eleven hours, that that is a game changer by itself. You don't need to go more than that. but then you the short haul, I was wondering, 'cause I've done some drive alongs with companies with Schneider where in Chicago, where you know they're you're driving five miles back and forth, just moving containers. how does How does auton how do autonomous vehicles do with backing up? Do they? Michael Wiesinger: Yeah, I mean it it's absolutely possible to back up. I mean think about it from a from a sensor perspective, right? We have three sixty degree coverage all around the truck. Again, sensor cameras, radars, lighters. Right. And the human Chris Caplice: But you've got a forty foot long trailer behind you, or fifty three foot trailer. Michael Wiesinger: right, and the human has the same. So so no it Chris Caplice: Yeah, but I've seen some I've seen some mad skills with these drivers who especially Michael Wiesinger: Yeah. Chris Caplice: they've been doing it for a while, back in and it's it's insane what they can do. Is that a tech I mean, it seems like a totally different skill. Michael Wiesinger: Yeah, the the technology is absolutely capable of backing up. Now, is is again this multi-stop lanes, lots of backing up, even sometimes driver assist. Would should we start with that? Do we recommend that to our customers? No, absolutely not, right? Chris Caplice: Yeah, yeah. Yeah, yeah. Und understand. Understand. And and so is it safe to say for long haul trucking you're more of the the hub to hub? Where however you define your hubs for that, that it's mainly gonna be the middle mile, the long middle mile? Your sweet spot? Yeah. Michael Wiesinger: Yeah, I would say that's an accurate statement to say the long amounts. When when people talk about hub to hub, I wanna be careful because sometimes they said hub to hub like several years ago. To mean it has to be an auto a dedicated autonomy hub to a dedicated autonomy hub. In creating Chris Caplice: Yeah, parking lot. Michael Wiesinger: this like inefficient moves on on kind of the first and last mile. No, that's not what we do, right? We go absolutely dock to dock. We we go really you know from a DC to a store, from a DC to another DC. So that is important that that we don't misunderstand what hub to hub means. But Chris Caplice: Yep, sure. Michael Wiesinger: yes, do I believe it's kind of the middle miles is where where autonomy will start to scale? Yes, absolutely. Chris Caplice: It seems like some of the a a sweet spot area would be for retailers bringing agriculture in from the say the southwest or from southern California all the way up because that's I mean, like for apples coming in from the northwest, they they use unit trains to come 'cause Michael Wiesinger: Mm-hmm. Chris Caplice: they will keep rolling all day long. But being able to bring that on a truck that can bring something in, they can cut a day off. That's that that seems like that would be a sweet spot. So let me ask you one last question. You've been very generous with your time, Michael. I want to ask one last question. and I'm not gonna hold you to this, but how many years do you expect it will be where at least 50% of all over-the-road long haul full trucking miles are done autonomously? Michael Wiesinger: That's that's a good question. you know, me need to be again, yeah, Chris Caplice: I won't hold you to it. I won't hold you to it. Michael Wiesinger: yeah, no, no, but the public markets might so I need to need to be careful in what I'm saying. But I I'll I'll I'll I'll offer you this. There's Chris Caplice: Okay. Michael Wiesinger: currently roughly three million class A trucks, right? And let's just assume for now we focus on class A trucks. There's Chris Caplice: Got it. Michael Wiesinger: roughly 200 class A trucks produced every year. So let's just assume every of those trucks would be autonomous, right? It's more than a decade to replace old trucks. So let's just assume ten percent of those. Let's be let's be conservative. Ten percent of those. We are more than a century, right? So you can do the math on on fifty percent, but again, it's I think your question is maybe informed by some drivers being concerned that there won't be a driving job in the future. And I think that is absolutely not the case, right? Again, I I see autonomous trucks as an additional modality that has its strengths, Chris Caplice: Yes. Michael Wiesinger: but I also see the drivers having their strengths. And so I think we will see an augmented network that is really gonna be more reliable, more efficient, faster, and basically serve the demands that the that the supply chain has. And quite honestly. those demands are constantly rising. And if we can just fill kind of that supply versus demand gap with autonomous trucks, I think we have all done a a a a great thing. Chris Caplice: Your consulting background showed you're giving us numbers without really answering the question. That's okay. Michael Wiesinger: Trying your best. Chris Caplice: But but but of course your your analysis ignored that we could convert some of the more recent ones, right? And so Michael Wiesinger: Yeah. Chris Caplice: because I I I assume y 'cause the the answer I took away was a century. Do you really think it's gonna be a century? Is that what we're gonna go with? Less than a hundred years. Michael Wiesinger: I think it's gonna be less than that, as I said. because I think the rate of new trucks will be higher than ten percent, right? If it was just ten Chris Caplice: Really? Michael Wiesinger: percent every year, then it was a century. But I think the rate at some point, not today, but at some point will be much higher than ten percent of of replacement with autonomous trucks. And so I think it will be way less than a century, but you know, somewhere between the the decade and the century. Chris Caplice: be here a hundred years from now unless something Michael Wiesinger: Okay. Chris Caplice: dramatic changes. but Michael, thank you so much. I really enjoyed talking to you today. I learned a lot about Kodiak in just the A V space. Thank you. Michael Wiesinger: Thank you, Chris. It was a pleasure having been on. Chris Caplice: Okay, everyone stay tuned for the truckload market update. Hi, welcome to Truckload Market Update for 1 October 2026. As you can tell, once again, I'm in a hotel room, so I'm recording this from the Inland 26 Journal of Commerce conference in Chicago. it's Tommy Year, conference to conference. But let's get to the truckload market update. In the dry van market, we saw that contract rates dropped 2%, spot rates rose 0.3%. And the current level of replacement rates for dry van is 11.2%. That means new contract rates coming in are on average 11% higher than the rates they're replacing. The gap between spot and contract is 13 cents a mile, where spot is above contract. Year-over-year change in spot rates, 37.2%, and 11.7% for contract. Temp Control, we saw contract rates rise slightly, 0.6%. Spot rates dropped 1.6%. And the current level of replacement rates for temp controls positive 8.3%. The gap is 13 cents a mile between spot and contract, spot above contract, of course. And the year-over-year change in spot rates is about 30% and about 12.5% for contract. For intermodal, we saw contract rates go up 1.6%. We saw spot rates slightly rise 0.6%. We saw current level of replacement rates a positive 7.6% for intermodal. market gap is about five cents a mile. Again, spot intermodal is pretty small, so I don't even much pay attention to that. Year-over-year change in spot rates about 20%, and about 11% for contract rate change. That was for intermodal. Flatbed, finally, contract rates went up 0.3%, spot rates up 1.7%. We saw the current level of replacement rates at 6.4%. Market gap is two cents a mile negative, where spot is actually below contract for flatbed. It's so volatile. You never that just bounces up and down with a plus or minus a penny or two each time period. year-over-year change in spot rates for flatbed is 33%, and it's 20% for contract rates. All right, more the same. Active contract rates for dry van drops slightly, but everything else increased slightly, you know, one one to two percent, somewhere in that range. Replacement rates for all the modes are positive, four to twelve percent. You know, the dry van. Is down from what it was. They're all slightly down from what they were. two weeks ago, dry van replacement rates was 14%, temp control was nine, and flatbed was nine. So those have all come down a handful of points. It's still high. And the year-over-year increase in contract rates are in the 10 to 20 percent year over year. Spot rates increased slightly, point three to two percent, and the year over year they're between twenty and forty percent above where they were. We're going to start hitting the time of year where the rates were increasing last year, so that year over year is going to start shrinking a little bit, I think. And the gap between spot and contract is positive between five and thirteen cents a mile for everything except flatbed, which I had mentioned earlier, dropped about two cents a mile. Anyway, that's the state of the market, the truckload market for drive-and-temp control, intermodal, and flatbed on one October 2026. It's a tight market. It's going to continue to be tight. Capacity is scarce. carriers are making up for the last three years of a really soft market. And I see these bids starting to strengthen up. So it's time for shippers to start strengthening the routing guide, building in some consistency. it's it's gonna be a challenging market throughout the end of the year. Maybe there'll be some easing of this in the second or third quarter of next year of 2027. We'll see. And that's it for one October, 2026.