Jeremy Vayssettes of Michelin

0:00 Introduction to Michelin’s Innovations

Today in The Garage, our guest is Jeremy Vayssettes, who is Chief Technology Officer for Tire Digital Twin at Michelin. In today’s conversation, we discuss all about Michelin’s innovation in algorithm and software products. While you may know about Michelin as an incredible tire innovator, there’s much more to it that they do. They’re bringing their know how to make tires safer, make them more sustainable, better predictive maintenance, and more advanced capabilities for ADAS and performance.

It’s a wide ranging conversation showing what’s possible for AI in new applications. Let’s go!

0:47 Introducing Jeremy Vayssettes

Welcome to The Garage. I’m John Heinlein, Chief Marketing Officer with Sonatus. We’re recording today live at the Sonatus booth at CES 2026.

We’re excited to welcome Jeremy from Michelin. Jeremy, welcome to The Garage.

Yeah.

Thank you, John. So start by telling us about you and your background.

So I have a background in automatic control and signal processing. I did engineering school and I have a PhD in this domain. And then I joined Michelin as engineer to develop tire models and now I’m developing software products for connected mobility.

It’s quite a range and you had also in the background in in aerospace engineering.

What was that right?

I started my career as a engineer in aeronautics field in Toulouse in south of France. Doing two years as engineer, then I switched to a PhD. I did my three years of PhD also in this field, and then two more years in research in different labs before joining Michelin ten years ago.

That’s great diverse background. You’ll have to tell us a fun fact about you to get to know you.

So I’m married. I have two sons. And each year, we like with my family to go to do road trips around Europe with a small van, minimal stuff, no technology at all. No technology!?! Going around.

That’s a very big commitment!

I guess my fun fact back to you, right, would be that my my family likes to my my parents like to to do that as well. They like to travel and several months of the year they travel oftentimes in the south of the US, go avoid the wintertime. So it’s it’s a lot of people are are love to do that, but I it’s so exciting for you to to go away from technology. That’s a big commitment.

Yeah. It’s kind of a break every year before coming back to to to work with a stronger commitment.

2:42 Understanding Michelin’s Broader Mission

I think that’s a that’s a great idea. Good for you.

So Michelin is a famous company and many people may know the company. But so tell us a little bit about the company in general and then about what you do for the company.

Yeah. So, yes, people know Michelin usually a bit because of tires.

But actually, Michelin do much more than tire. Michelin DNA is first more about mobility in general. And also now Michelin is diversifying activities to go around tires and beyond tires, leveraging our skills and expertise in high-tech materials to develop high-tech materials to new domains like hydrogen, medical and other many things. And on my side, I’m developing software products. So embedded Tire Digital Twin to be able to provide insight the vehicle information regarding tires so that the vehicle are aware of the tire state performance all the time.

3:55 The Role of Software in Tire Technology

Let’s talk more about that. I’m so interested to hear because the average person might assume, you know, they’re just a just a tire company, but the reality is, as you say, you’re doing so much more. So how does software in the vehicle and and the software defined vehicle change that we we often talk about, How does that give you opportunities to do new things with software in addition to tires?

So with the shift from hardware-centric to more software-centric in automotive industry, It’s actually a great opportunity for us, for Michelin, companies like Michelin to provide much more than only hardware and to also be able to innovate more by providing more smart tires by connecting them to their vehicles.

4:48 AI Innovations in Tire Management

That’s really interesting to hear. Can you help us understand how [your] innovations can benefit tires? What are some of the algorithms you have and kind of how do they work?

Among the product we have we have SmartWear and SmartLoad for instance, a product that we developed to monitor the tire wear, tire load during the usage phase. And thanks to that, we are able to provide useful insights to the fleet, to the vehicle, to the user about the tire state.

And when the tire will have to be changed, for instance. So that you can and fleets can have a predictive maintenance to reduce their costs, reduce downtime and have much more efficient maintenance than when it’s reactive or scheduled maintenance.

You’re right. So that’s a that’s a good point because I think as one driver and another driver might drive the the same vehicle in very different ways that might cause different tire wear. For example, aggressive acceleration caused the tires to wear sooner and perhaps driving in hot conditions or cold conditions could cause different wear. So by by kind of monitoring and studying how the tire was actually used versus some generic schedule, you can be more accurate.

Yeah. Better safety, maybe some cost savings. All of the above, I guess. Is that right?

Yes.

Yeah. And so let’s talk about these two different models. You mentioned SmartWear and SmartLoad. So let’s start with SmartLoad. Can you explain what that does and some of the inputs that go into that?

Yeah, sure. So those models take as inputs the data coming from the vehicle, from the sensor that are equipping already the vehicle. So it means it’s only software without specific additional sensor that we put in the tire for instance. And from those data, we use the tire physics and what we know about the tire, the interaction with the road, the vehicle and some advanced AI techniques and signal processing to convert those data into a useful insight to know what is the tire wear, what is the tire load in real time so that the vehicle can adapt to the change in the tire wear for instance.

But also the driver can know what is the wear level of the tire. He can be warned when the tire have to be changed. And also the fleet managers can also get all those data from all their vehicles to know how they need to plan the maintenance to optimize it and to be sure that they will change the tire at the right time. So not too soon but not too late.

7:54 The Benefits of Smart Sensors vs. AI

So many interesting things you said there. So I wanna I wanna touch on a couple of ideas. First, there’s a lot of focus and there’s been some conversation in the years past with putting smart sensors in vehicles, in tires. Of course, every tire in many cases required by law has a TPMS sensor, tire pressure monitoring system sensor.

But there’s been a conversation in years past about adding an an extra smart sensor that does additional diagnostics. But I think what you’re saying, and I think one of the key innovations of this AI is you get the benefits of those smart sensors without the additional cost, without the additional complexity of those of those sensors. So you can use, you know, any kind of tire or, you know, any kind of tire to get these kind of benefits. Is that right?

Yes. Completely.

And then the second thing that was so interesting is how it can really benefit in multiple ways. Because, of course, there’s a there’s a benefit to if your maintenance is is proper. You you don’t waste money replacing the tires sooner than necessary, but also not later. Because you know when it’s the right time to replace it, which provides better safety.

Right?

Yes. Exactly.

And then I think that the last part that really struck me with what you said is using your knowledge of the materials and using your knowledge of the tires, you can create you didn’t say, but kind of a digital twin of the of the tire And that you understand how that specific tire or that specific set of tires has been used.

And and it’s really smart that to use your unique know how to be kind of the world’s expert in your tires and to create this value added solution on top.

9:34 Developing a Comprehensive Tire Digital Twin

Yes, exactly. The ambition is not to only develop two products like SmartWear and SmartLoad but a full tire digital twin that will provide a full package of insight regarding tires. To provide useful insights to the driver, so the the consumer. To the vehicle so that the ADAS system can adapt also or to the fleets so that they can optimize their maintenance and reduce their costs.

And this full digital twin would come with SmartWear, SmartLoad that provides useful useful information regarding the tire state because during the usage phase, the tire is changing a lot. For instance, it’s wearing out and it affects a lot the performance of the tire and all the performance. So when we talk about grip, for instance, it plays a potential role in vehicle safety and performance.

Right.

Once we know in real time what is the wear level of the tire, then we can also provide useful insight regarding grip and the grip prediction.

So that the vehicle, the braking system for instance or the steering system can know what is the maximum level of grip the tire can provide

This instant, anytime, anywhere so that the system can leverage the optimal level of tire performance all along the usage phase.

It’s a really really great point because of course when your tires are new, your vehicle performs better, your braking is more responsive, you stop in shorter time.

So as the ADAS system is able to be informed that the tire is more worn, it can provide automatic emergency braking and other kind of braking system tuning more proactively to provide better safety. So actually, the driver receives not just at the tire replacement time, but throughout the life of the vehicle, they get a better experience, better performance experience, better safety experience. And then of course later on they get a better knowledge of when to replace your tire. That’s fantastic. Yes.

By doing this, we are able to make the tire last longer because people won’t change the tire too soon. Right.

But also leveraging the really the performance potential of the tire. So if we do better tires, the user will benefit more this all along the tire life because the vehicle will be able to leverage those performance better than what it’s done actually.

12:37 Sustainability in Tire Management

Well, you mentioned that because the tires don’t get replaced prematurely, I’m assuming that provides a great sustainability benefit as well because we’re not wasting materials and we’re not obsoleting tires that have perfectly good life left in them. Is that right? I know that sustainability is a big focus for you as well, right?

Yeah, yeah. It’s one of the big focus and the added value because the automotive industry has a lot of pressure to reduce the environmental costs and to be more sustainable.

And for instance, when we talk about tire wear, the average the tire is removed on average at when there is still 3.5 millimeters [worldwide average] of tread When the legal limit is 1.6 millimeter. And when a tire in general starts between six and seven millimeters. Right.

So it’s more than twenty percent.

Of life left over.

Of, the, yeah. The material that is wasted.

That’s great. Well, that’s a that’s a great benefit. And I’m so excited to have have had this conversation with you that I’m even learning some additional benefits along the way that I hadn’t thought of.

13:50 Collaboration with Sonatus

But we have to shift over to talking about our fantastic Sonatus and Michelin, who had a fantastic collaboration. And just as we’re recording this, just right outside the the podcast studio, we have our demonstration with you where we have your algorithms running on our Sonatus Director infrastructure. I’d love you to talk about why did you partner with Sonatus and what are some of the benefits that our Sonatus AI Director deployment infrastructure was able to bring to Michelin as you deploy your algorithms into vehicles?

Yes. So first, we are very complementary.

We work and focus on the tire part. And with our expertise, we are able to provide and to develop those software that could provide all the benefits we mentioned before. Sonatus, on your side, you are developing the vehicle infrastructure, the software part and also the ability to manage quite efficiently and properly the AI models and deploying.

And thanks to [Collector AI] , we have a way to calibrate quite efficiently our models because they need to be calibrated for specific vehicles before being deployed.

So we can do this efficiently and then deploy to the vehicle — thanks to AI Director — our models. So it’s a very efficient way to be able to provide and deploy our models at scale to many constructors and carmakers.

We’re so grateful for your collaboration.

And first thing as you say, it’s absolutely complimentary because we’re providing we’re not trying to replace your expertise and nor could we possibly be an expert in the tire physics and materials that you have.

But the infrastructure we provide allows vendors like you to bring that intelligence you’ve generated into the vehicle more easily. So it’s fantastic collaboration.

The second thing I think is really interesting that you mentioned is when sometimes people think about AI models and they say, oh, you train the AI model and now it’s trained and that’s it. We’re done. Well, first thing, of course, AI models improve over time in general. There’s no there’s no finished.

It’s we learn new things, we improve the AI models. But even more importantly than that, as you mentioned, and I learned this in in working with you that the specific model when deployed to a specific vehicle still has some calibration parameters that need to be set for the exact tires, the exact load, the exact weight, the specific vehicle. So that then after some amount of driving on that particular vehicle, then the model is is more accurate and ready to be fully operational with that vehicle. So we’re excited to be able to deploy not only our AI Director deployment and AI management platform for in vehicle edge AI, but also the ability to help you get that data for that vehicle tuning more easily.

So it’s a great multi-way collaboration I think.

Yes. And actually having a tire digital twin and products like SmartWear or SmartLoad is not only about having good algorithms or models to make good predictions and accurate predictions.

It’s also a matter of being able to deploy it to at scale, to the carmakers in an easy and efficient way, taking into account all the constraints we can face when we want to do that. And yeah, as we mentioned, we developed those products for any tires. So it’s tire-agnostic, not only for Michelin tires, for any vehicles.

But the “one size fits all” does not exist or at least it will be at the cost of loss of accuracy.

So we need to be a bit specific. And the choice we made is to have this specificity at the vehicle model level so that when a carmaker want to adopt the solution, we have a setup for the vehicle model. And all the vehicles of this model have the same setup so we can deploy in any of these vehicles.

18:29 Future Prospects and Closing Thoughts

Fabulous. Well, it’s so exciting to see what’s possible. I’ve learned a lot in our collaboration with you.

I think that the ability to help accelerate the deployment of such exciting technologies like yours is very inspiring for us.

And we’re we’re thrilled for your partnership and there’s been incredible. I hope you’ve had experience. We’ve had incredible interest in the demo nonstop. People have been watching it outside the the hall, the booth all day today and yesterday. So thank you for coming to visit with us, and thank you for joining us on the podcast, and thank you for your partnership.

Yeah. Thank you very much.

If you like what you’re seeing on this episode, please like and subscribe to see more like it, both from CES and other events around the world. We look forward to seeing you in another episode of The Garage very soon.