OpenSimDrive: Exploring, and Extracting Dynamic Models in Open Source Car Simulators for Accurate Sensor Fusion

The “OpenSimDrive” project is a comprehensive investigation into open source car simulators, aiming to identify a suitable candidate for extracting dynamic models. The project further involves utilizing this model to predict linear and angular acceleration and subsequently validating its accuracy by comparing the outputs with the simulator. Additionally, a crucial aspect of the project is the integration of the validated model into a sensor fusion framework, enhancing the estimated position. The project ends with using the dynamic models as additional measurement in sensor fusion to reduce the drift during GNSS denied conditions.


  • Identify and evaluate various open source car simulators.
  • Select a simulator with a robust dynamic model suitable for extraction.
  • Extract the dynamic model parameters required for predicting linear and angular acceleration
  • Validate the extracted dynamic model by comparing simulated and predicted accelerations.
  • Implement a sensor fusion framework incorporating the validated model as an input.
  • Evaluate the performance of the sensor fusion system.


  • A detailed assessment report on various open source car simulators.
  • Documentation of the selected simulator and the process of dynamic model extraction.
  • Detailed documentation of the extracted dynamic model
  • Validation report comparing simulator outputs and model predictions.
  • Integration of the predictive model into a sensor fusion framework.
  • A comprehensive report on the performance of the sensor fusion system.


Kenneth Joseph Paul, Jan Skaloud