Logo of Acerta
Book a demo

Case Study

Estimating road friction in milliseconds

Objectives

Enable real-time estimation of road surface friction to improve vehicle safety and performance, using efficient machine learning models deployable on embedded systems.

Challenge

Normal driving data lacks clear road grip signals, and the model had to be under 5 MB to fit the vehicle’s hardware.

Key Results

  • Detected road surface changes in less than 1 second
  • Shrunk model size by 97% (from ~100MB to under 3MB) for real-time use on the vehicle

>1 sec

Detection time

97%

Reduction in model size

Background

A North American OEM sought to improve vehicle dynamics by accurately estimating the maximum available friction (surface μ) between tires and road surfaces in real time. Identifying optimal wheel slip ratios is essential not only for anti-lock braking systems (ABS), but also for torque vectoring, transmission shift timing, and other key vehicle functions. However, gathering sufficient friction data typically requires high-excitation driving events like sudden braking—impractical in many real-world conditions, especially for electric vehicles (EVs) utilizing regenerative braking. To address this, the OEM partnered with Acerta to use machine learning for estimating road friction based solely on low-excitation vehicle data, enabling real-time insights without requiring extreme driving maneuvers.

Problem

Low-Excitation Data Limitations

The vehicle’s data was generated under low to moderate acceleration and deceleration, meaning traditional methods struggled to identify friction levels without the vehicle approaching slip conditions.

Model Size Constraints

Initial machine learning models were around 100MB, far exceeding the 12MB hardware constraints of the OEM’s onboard systems.

Solution

Custom Model Development

Acerta worked with the OEM’s training data, which included instances of controlled high-excitation braking events across varied surfaces (wet asphalt, dry asphalt, ice, gravel) to label the friction coefficients.

Using this data, Acerta’s team engineered features and tested several machine learning models, including proprietary algorithms, to accurately recognize transitions between road surfaces—even under low-excitation conditions.

Model Compression

Once optimal models were selected, Acerta’s engineers focused on compression techniques, successfully reducing the models and associated libraries from ~100MB to under 3MB—small enough to be deployed on a 12MB MicroAutoBox embedded system.

Results

  • <1 Second Detection Speed: The model identified road surface transitions in less than one second on average, enabling real-time friction estimation.
  • >97% Model Size Reduction: Machine learning models and libraries were compressed from approximately 100MB to under 3MB, meeting strict embedded hardware constraints.
  • Edge Deployment on 12MB System: Successfully integrated the compressed models into a 12MB MicroAutoBox, allowing real-time, onboard deployment without compromising performance.

Case Studies

Proven Impact