AlgorithmScm β€” Stochastic Cognitive Model (FMU)

⚠️ PREVIEW / EXPERIMENTAL β€” v1.1.0

This is an early preview of the latest SCM updates, which have not yet been officially published on the Eclipse SCM project. It is intended for early evaluation and feedback ahead of the official release. Interfaces, parameters, and behavior may change without notice in future versions. Not recommended for production use.


What is SCM?

The Stochastic Cognitive Model (SCM) is a driver behavior model for traffic simulations and safety analysis. It simulates the full chain of human driving cognition:

  1. Sensory perception β€” gaze behavior and attention allocation
  2. Information handling β€” processing and prioritization of traffic information
  3. Decision making β€” gap acceptance, lane change decisions, speed regulation
  4. Action execution β€” longitudinal and lateral vehicle control

SCM models inter- and intra-individual variation in driver behavior through stochastic parameters, enabling realistic simulation of traffic flow and critical driving situations. It currently supports highway scenarios.

SCM integrates with OpenPASS as an FMU component, but is maintained as a separate Eclipse project.


Repository Contents

File Description
AlgorithmScm.fmu Compiled FMU binary (FMI 2.0, Co-Simulation)
LICENSE Eclipse Public License v2.0
README.md This model card

Source code is not included in this release.


System Requirements

  • FMI standard: FMI 2.0 Co-Simulation
  • Simulation platform: OpenPASS opSimulation
  • OS: Linux (x86-64)
  • Cycle time: 100 ms (default, configurable)

Integration with OpenPASS

Place AlgorithmScm.fmu in your OpenPASS installation directory and reference it in your ProfilesCatalog.xml as an FMU1 component under the AlgorithmScm profile group, e.g.:

<ProfileGroup Type="FMU1">
    <Profile Name="RegularScm">
        <String Key="FmuPath" Value="AlgorithmScm.fmu"/>
        <!-- driver and vehicle parameters -->
    </Profile>
</ProfileGroup>

Refer to the SCM user guide for the full parameter reference and configuration examples.


License

This software is distributed under the Eclipse Public License v2.0 (EPL-2.0). A copy of the license is included in this repository as LICENSE.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support