Could you tell us a bit about Monolith and how its technology is helping car manufacturers?
Monolith enables engineers to use AI to solve their most intractable physics problems. We do this by enabling engineers to use their existing data from the current product development process.
Using their existing data, they can create self-learning models to instantly predict the outcomes of challenges that would otherwise have to be solved using extensive and time-consuming physical testing. These self-learning models learn from existing data and identify patterns to solve problems that until now were beyond what the human engineer or simulation technology can do. Instead of performing costly and time-consuming testing to resolve this uncertainty, engineers can work with the Monolith platform to quickly understand and predict performance without having to program models or perform coding.
And because Monolith was designed specifically for domain experts rather than statisticians or expert coders, our no-code interface allows engineers to leverage their expertise to solve highly complex problems that capitalize on the wealth of data that already exist and remove dependencies on other teams that are less familiar with the data or the issue.
What previously impossible R&D challenges can AI now help solve?
As an engineer, you may have been tasked with building a model and then using that model to virtually design the perfect product in hopes that the physics-based simulation approach will do its job. But what I’ve discovered is that if you want to radically accelerate the speed of new product development, you need a radically different solution to understanding the physics challenges that aren’t yet fully understood. .
This is exactly what one of our customers in the industrial sector does. Honeywell engineers previously used computational fluid dynamics (CFD) simulations to understand the complexity of gaseous fluid dynamics in the development of their smart gas meter, but the simulations were not 100% accurate, leaving a critical gap in understanding between simulation and reality. Using Monolith, engineers use machine learning statistical methods to bridge the gap, allowing them to instantly and accurately understand the impact of varying temperature conditions and gas types across all operating conditions. , including extreme and unstable settings. As a result, Honeywell’s engineering team builds higher quality products in significantly shorter lead times.
The ideal use case for AI is when engineers are trying to understand the physics of complex systems that cannot be fully represented by simulation and therefore require substantial physical testing to calibrate. When faced with unsolvable physics problems, they can use Monolith to immediately leverage their existing data and instantly solve what was previously unsolvable and in the process literally reclaim weeks or months of their time.
Could you give us specific examples of how OEMs are using AI in the R&D process?
By training Monolith self-learning models with the company’s test data, BMW engineers are using AI to solve previously intractable physical challenges and predict the performance of highly complex systems.
We started working with the BMW Group crash test engineering team in 2019 to see if AI could predict crash performance and, importantly, do so much earlier in the development process of the vehicle. BMW engineers built self-learning models using the wealth of their existing crash data and were able to accurately predict the force on the human shin for a range of different crash types without crashing. physical.
Going forward, the accuracy of the self-learning models will continue to improve as more data becomes available and the platform becomes more integrated into BMW’s engineering workflow. This means engineers can optimize crash performance earlier in the design process and reduce reliance on costly, time-consuming testing while making historical data infinitely more valuable.
Should AI be considered a threat to engineers and potentially to their jobs?
Rather the opposite. In fact, one of our customers recently called Monolith augmented intelligence because it amplifies the engineering expertise of their team. It’s an ideal tool for time-poor engineers who are, frankly, under immense pressure to develop the next generation of vehicles.
With Monolith, an automotive customer reported a 70% reduction in track test time, as well as up to a 50% reduction in overall costs. This is just one example of how efficiencies achieved through AI free up time to focus on building even better products. As one Honda executive said of our technology, “It almost gives us superpowers.”
Do you see any emerging trends where AI could help?
No matter what new technology is introduced, whether autonomous, connected or electric, engineers will always have to create a fundamentally great car to stay competitive and drive demand – from premium acoustics and greater fuel efficiency to safety and vehicle dynamics.
AI technology can radically transform vehicle development by enabling engineers to extract the best possible insights and predict outcomes from existing engineering data, much earlier in the development process. This allows engineers to make design and engineering decisions faster and more efficiently, giving them time to explore even more design parameters and operating conditions.
Ultimately, this means OEMs can bring better vehicles to market faster, which is not only vital to achieving our collective EV ambitions, but allows engineers to do what they love most. : designing incredible products.
We hear that while manufacturers remain enthusiastic about automated driving, the challenge will take more time and effort to fully realize. What is your view on the path to autonomous driving?
It’s true. Last year, AV companies Waymo and Cruise traveled 3.2 million miles in an effort to train and robustly test their autonomous technology. Engineering teams are barely able to afford this time around – competitors move too quickly – and yet the complexity of vehicle development has never been higher.
When engineers struggle to understand the intractable physics of complex vehicle systems, self-learning models can supplement the resolution of the underlying physics with AI-powered statistical predictions. Autonomous technology is the perfect example where a lot of data has been created to understand a complex system.
OEMs can use AI to extract existing engineering data from simulations or physical tests to create self-learning models that instantly predict other test outcomes or uncover new insights buried in the data.
Do you expect to see a bigger role for simulation and AI as part of VA training, validation, and testing?
Yes, but we understand that introducing new tools into an age-old product development process requires vision, courage and experimentation. This experimentation is much easier when engineers understand that AI does not completely replace physical simulations and testing – rather, it is the essential piece of the puzzle to enable engineers to achieve design convergence much more quickly and efficiently. .
The introduction of AI into modern vehicle development is a similar change: engineers suddenly no longer have to solve the physics that underpins a mathematical system, but can now instantly access information already hidden in their engineering data. existing engineering.
What’s next for Monolith?
The world’s best engineering teams, from Rolls Royce to Honda and Siemens, use Monolith to reduce product development while creating even higher quality products. In the automotive space in particular, engineering teams are integrating Monolith into more and more engineering functions that generate large amounts of data, from crash testing to aerodynamics, motorsports and, as mentioned, at ADAS.
We are poised to scale rapidly, powered by world-class engineering teams from leading OEMs who embrace our technology and extensive intellectual property portfolio.