Michelin digital twin provides tyre insights

  • June 9, 2026
  • Steve Rogerson

Tyre maker Michelin has developed a digital twin that can convert in-vehicle data into actionable insights in real time to make recommendations to the vehicle or its driver.

The company is leveraging 130 years of expertise in tyre physics combined with mathematical modelling, AI and data science algorithms. This aims to ensure a safer driving experience for everyone by allowing the vehicle to anticipate its behaviour and improve performance without requiring input from physical tyre sensors.

“Thanks to its universal digital twin, Michelin not only listens to the vehicle, it whispers words of wisdom in its ear in real time,” said Philippe Jacquin, Michelin executive vice president. “Every tyre, whatever the brand, has its very own embedded intelligence. By making its tyres smarter, Michelin is bringing a new dimension to the role of tyre manufacturer and is once again proving its commitment to enhancing safety for all road users.”

The digital twin is a dynamic virtual replica of a tyre. It continuously analyses and predicts the state of tyres at a given time factoring in tyre pressure, wear, load, grip and driving conditions and comparing them with in-vehicle data.

It directly interacts with embedded systems to optimise their performance, helping enhance safety by predicting maximum grip, preventing aquaplaning, boosting the effectiveness of driver-assistance systems such as ABS, monitoring tyre pressure and detecting any overloading. This means the vehicle can anticipate grip, improve its stability, optimise fuel consumption and adapt braking distances by as much as several metres.

The system is fully integrated, and drivers are not even aware it is working behind the scenes. It offers real-time assistance depending on the condition of the tyres. For the driver, this means smoother, safer and more predictable navigation without changing driving habits.

By supplying a continuous flow of data based on vehicle signals, it also facilitates predictive maintenance, thus extending the tyre’s lifespan. By ensuring the tyre remains in optimum usage condition and can stay on the road longer, the digital twin also contributes to reducing the amount of material used and mitigates the environmental impact of a tyre’s lifecycle.

The software-enabled embedded intelligence-driven system makes use of existing in-vehicle data without requiring additional tyre-mounted sensors. It is compatible with all tyre brands and models and can be fitted to all types of vehicle – passenger cars, trucks or even self-driving shuttles.

This is the result of over ten years of research and development secured by several patents and validated by tests covering several million kilometres. It harnesses existing in-vehicle data combined with the physical and mathematical modelling developed by Michelin over the years.

The digital twin is embedded and can be adapted to future software-defined vehicle (SDV) architectures.

The arrival of SDVs and self-driving vehicles means performance, features and user experience can continually be enhanced throughout the vehicle’s lifetime. The SDV market was valued at $213.5bn in 2024 and could reach almost $1240bn in 2030. Michelin (www.michelin.com) says it is supporting the transition to vehicles whose functions are increasingly enabled through software. This journey is driven by collaborations, in particular with Brembo, Hyundai, QNX, Etas and Sonatus, covering innovation from fundamental research to industrial integration at scale.

The recent partnership with Italian automotive parts maker Brembo (www.brembo.com) provides a tangible illustration of the benefits of the Michelin digital twin on ABS performance. Integrating data on the actual state of the tyre in braking algorithms has made it possible to boost braking system performance leading to shorter braking distances up to four metres and improved stability in particular during hard braking.

Read more at www.michelin.com/en/media/magazine/michelin-innovative-connected-solutions.