DriveSim : Creation of a rural scenario for a semi-autonomous driving simulator

Semester project, HES-SO // University of Applied Sciences Western Switzerland, 2019

  • 1 student to supervise.
  • The student worked 4 hours per week for 4 months.
  • 1 meeting per week.

Context of the project

To date, technological advances have made it possible to automate vehicles. For example, a level 2 automated car offers partial autonomy, i.e. the system can manage the acceleration, deceleration and steering of a vehicle thanks to the information perceived by various vehicle sensors. However, vehicle automation still causes road accidents during testing. This is why the HumanTech Institute, in collaboration with He-Arc and the University of Freiburg, has launched the “Ad Vitam” project to study critical situations (called limitations) that could endanger the users of an automated car. Based on a litterature review, critical situations for automated cars were identified. It includes narrow and winding road, bad weather conditions, slippery and wet roads, and many more. Thus, driving scenarios are required with the intention of studying these risk situations in the simulator. Therefore, the goal of the DriveSim project is to design a driving scenario in a 3D engine (Unity) containing challenging stuations for the car. The scenario will be then used by the project team to perform user tests in the driving simulator.

Tasks done by the student

  • Implementation of 3 critical situations (e.g. limitations) from the initial scenario :
    • an area with bad weather (Rain)
    • an area with erased road markings
    • an area with a winding road and relief
  • Creation of a Python script allowing the automated modification of the shape of the road
  • Test of the implemented scenario on the driving scenario with 3 users
  • Evaluation the realism of the elements integrated in the scenario, based on user ratings