Internship | Ontology Based Scenario Definition and Detection – TNO – Helmond

  • Helmond

TNO

About this position

At TNO, we develop software for Automated Driving vehicles. In order to have automated driving accepted by the public, it is extremely important to be able to explain the behavior of the vehicle. Are you interested in improving our AD vehicles? Please read further!

What will be your role?

One of the challenges in Automated Driving is “How the vehicle makes its’ decisions”. The vehicle decision is based on the current assessment of the vehicles’ surrounding. Often all situations that could occur on public road are simplified into a discrete set of scenarios or use-cases. This jeopardizes the generalizability and specificity of the system solution. Therefore a designer should delicately tradeoff between the details captured in a scenario and the number of scenarios resulting from adding more and more details. In order to tackle this scalability issue TNO is investigating whether AI – using a knowledge graph – could be used for scenario detection, from which expected behaviour could be inferred.

For that you will:

  • Build an ontology to capture a specified set of scenarios;
  • Assess whether the graph based approach allows for easier scenario detection and definition;
  • Check completeness of existing standards and possibly contribute on extensions of those.
  • Proposed approach:

  • Define a challenging set of scenarios in a predefined operational domain;
  • Familiarize with standards such as ASAM OpenXOntology and ISO as well as the Cetran Scenario Catalogue;
  • Search for and weigh up the pro’s and con’s of existing graph modelling frameworks;
  • Implement existing Ontology proposals in a graph modelling framework of choice;
  • Check for opensource data sets that could support your work, and relate these to TNO-internally available datasets or implement your work in an AD simulator (e.g. Carla);
  • Present results regarding the feasibility and complexity of the graph based approach for scenario detection.
  • What we expect from you

    We require that you are familiar with statistics for data science and have experience with data processing as well as clustering and classification methods. You are knowledgeable in programming (please indicate your programming language strengths in your application) and you are willing to learn. Experience with Linux and ROS is beneficial. We like you to start as soon as possible. The thesis fits to a 9 month project (based on full time availability). Familiarity vehicle automation would be considered a plus. Finally, successful candidates should be able to spend at least 2 days a week in our TNO Helmond premises to enable you to work with our tools and to have short communication lines.

    What can you expect of your work situation?
    You will work at the Integrated Vehicle Safety department of TNO on the Automotive Campus in Helmond. In this department people are working on developing software for automated driving vehicles. The developed software is tested in pilots and on the public road. (more info on the department: ). The people are young, enthusiastic and driven. You will work in an open area, within your own team. One of our employees will be your mentor. He will help you to get acquainted with the department and give you guidelines for your research in order to help you to get the best out of it.

    Related videos:
    Integrated Vehicle Safety:

    Previous Demonstrator on Risk Averse Motion Planning:
    TNO Video:
    Linkedin Post:

    What you’ll get in return

    You want to work on the precursor of your career; a work placement gives you an opportunity to take a good look at your prospective future employer. TNO goes a step further. It’s not just looking that interests us; you and your knowledge are essential to our innovation. That’s why we attach a great deal of value to your personal and professional development. You will, of course, be properly supervised during your work placement and be given the scope for you to get the best out of yourself. Naturally, we provide suitable work placement compensation.

    Lees hier meer

    Deel deze vacature: