The Geotab Connect in Luxembourg was entirely focused on artificial intelligence. Fabian Seithel explained to us in a detailed interview how it can be used and how the topics of security, fleet management, and route planning are developing in telematics.
We have the impression that the USA, Canada and in Europe also the UK are already significantly further ahead when it comes to the use of cameras in fleets – can you confirm that?
Seithel (laughs): I have a two-part answer to that. First: The fact that we discussed the topic of cameras now, among other things with two panel participants from the UK, is a coincidence. But in fact the video safety penetration in the UK is higher than in continental Europe. Even there, however, interest is growing, albeit this in the UK has tended to be higher anyway. Second: The interest in proactive video telematics has fundamentally risen, though we repeatedly find that it is never an implementation overnight, but participants must always be engaged. And typically you start with pilots.
How does that typically work?
Seithel: In almost every workforce there are almost always volunteers who are open to new things or like to try new things. They are usually quick to find. Then you only have to show that you act correctly, respect privacy, handle data with particular care, and that video telematics helps everyone by making inconsistencies easier to resolve or errors clearly documented.
I also remember the proof of a truck driver in the USA who was wrongly accused of driving into a left-turning car. The video cleared him unequivocally, and he was acquitted. That was a crystal-clear case. But what can be read from proactive video telematics when things get trickier?
Seithel: A lot, I use it myself as well, and I always welcome the differentiation when tailgating is too close. I can be at fault, but it can also be forced when someone closes in tightly into a narrow gap right in front of you. Proactive AI can evaluate that differently; the previous simple telematics approach lacked the context.
I remember a case that was exactly about such a scenario, which then had to be clarified in court for a long time…
Seithel: Here proactive video telematics can be clarifying. And since it would be crazy to watch and evaluate driving impressions in large fleets for days, the AI must be trained to select only the strongest driving situations. And the AI then also decides in which points to train the
drivers. Example: If I’m on the highway with my family and am told that the time to impact is only 0.24 seconds, it becomes clear that that is not very smart. Here a real-time alert must be set, immediately indicating to the driver – in this case to me – his mistake. Criticizing in hindsight isn’t so effective – better to pass the impulse on directly. Usually such a “live coaching” is well received and increases safety.
The topic of safety seems to have gained significantly in importance. How about the “classic” competencies of telematics – fleet or driving-profile transitions?
Seithel: In general sustainability remains important. And here too we can use AI to analyze data, merge it, and provide a targeted assessment. For example, we have the suitability assessment for electromobility, for which I enter several parameters and can then have it output at the push of a button. We run this proactively in the Sustainability Center in the background. There you can also input other driving profiles or driving profiles changed for future use. Basically you should know: The data don’t change much, but the more you have, the more you can read from them. And here especially look for “outliers,” which with AI is much easier and faster. This is how we also determine the theoretically possible accident rate or the likelihood of breakdowns. The important thing is only to draw the right conclusions from it and derive actions from it.
Would you have a concrete example for that?
Seithel (smiles): Take, for example, a worn summer tire, about which we know it has already run a lot. If it is then driven with low air pressure, it is especially in autumn, during the tire-change season, extremely unfavorable, when tire dealers and workshops are already fully booked. So better to change beforehand and always set the correct air pressure.
How does Geotab know how the AI should be further developed – and isn’t that very complex for customers who also need the prompts for it?
Seithel: Take our AI assistant Geotab Ace: Of course we also look at the questions that come in, and analyze whether our system provides precise, tailored answers. Here we can also fine-tune the systems. The customer does not have to adjust anything with Ace; the AI is an integral part of the product. The advantage is that the return on investment with AI can be realized faster, and if needed you can also deploy targeted training. There are so many possibilities;
I always call it “congestual power” or in German “gestaute Kraft”…
In what sense?
Seithel: We collect so much data that can be combined and analyzed in many different ways…
That some users found excessive and confusing…
Seithel (smiles): …the possibility indeed existed. But thanks to AI we now have the possibility to combine it smartly and precisely derive why what, how, where happened. And you can then merge that and put it on a map or in a graphic, because people find it easier to understand with images or graphics. The next step also goes further in visualization.
What is the feedback from your customers on this?
Seithel: They welcome it, but in the end everyone has individual demands, because every fleet is different: In car sharing different rules apply than in rental cars, KEP fleets or tradesmen fleets. The latter make their money when the vehicle is stationary, the former when it is moving! That means our platform must detect the usage to show how to optimize it.
With AI you can also easily ask questions to the system. Is that used, and what kinds of questions?
Seithel: We started the pilot in May 2024; at that time we had 100 users on board, now it's already over 1,500, with a trend of further growth. The questions vary depending on background, but in the next step it is about preparing them well so that the platform is easier to use. ACE has prepared them very well, and you only need to prompt the topics now. For example, you can also make suggestions in the Sustainability and Maintenance Center under the motto: “Did you know…?”
Could telematics then become a partner and advisor that proactively makes suggestions?
Seithel: Of course! Artificial intelligence is very powerful, especially when it comes to generating insights from data. That suggests action, and in practice it is then about prompting or nudging something based on these data, insights, or recommendations. A good example here is the proactive maintenance of a car, which I can schedule for myself at the most opportune moment. That might be a five-minute investment that saves me two days later because the car fails or parts are not available.
What does that look like on the OEM side? In an ideal world the car would sign up for service itself, or the person responsible would do so, then the workshop would take care of everything necessary and you would have minimal downtime. How far are we there in practice?
Seithel (smiles): Our business is to provide data, generate insights, that allow the customer to do something with it. In maintenance we know when and if the vehicle was serviced, but the details are not fully integrated into our systems. Many customers try to integrate these data into systems or maintenance software, but the feedback to us is lacking. Nevertheless we can build algorithms from data to determine the probability of a potential breakdown. And regarding OEMs—we work very closely with vehicle manufacturers and are now integrated with more than 80 percent of leading OEMs and continually expanding the joint offering for fleets.
What is interesting, however, is that the weighting seems to have shifted: driving safety is now absolutely in focus, followed by service and maintenance topics. But originally telematics came from route planning?
Seithel: Indeed the weighting has changed, and driver safety is in focus – also in Europe. The maintenance topic is particularly important in fleets that are used very intensively, i.e., in last-mile delivery, where outages are disproportionately expensive. But sustainability remains big as well, and the shift to electric vehicles is definitely a topic: For example, the Belgian Post plans to deliver CO2-neutral on the last mile by 2030, and is also optimizing the charging infrastructure. The variables here are also interesting.
In what sense?
Seithel: Let me give you an example: If electric vehicles operate in multiple shifts and in the afternoon only drive very short routes, they do not need to be charged to 80 or 100%; 40% state of charge may be sufficient, which after the tour may have dropped to just 32%. This is something completely different from sending an electric truck on long-haul from Helsinki to Lisbon. Here you can also create valuable and important linkages to charging infrastructure.
And that brings us back to the end to the original core topic, route planning. What role does it play there?
Seithel: Route planning remains a very individual topic, and it depends a lot on whether I have 20 or 200 stops, what time windows there are for deliveries. That involves a lot of context – think of refrigerated goods where time windows plus temperature windows come into play, or courier services that are required very differently around Christmas than during the rest of the year. Here you need a lot of extra information, and there isn’t a single question the customer asks. But one thing is clear: artificial intelligence certainly helps in finding the answers!
the interview was conducted
