Thesis Occlusion Handling in Planning for Automated Driving with Neural Networks

Job title: Thesis Occlusion Handling in Planning for Automated Driving with Neural Networks

Company: Bosch

Job description: Company Description

At Bosch, we shape the future by inventing high-quality technologies and services that spark enthusiasm and enrich people’s lives. Our promise to our associates is rock-solid: we grow together, we enjoy our work, and we inspire each other. Join in and feel the difference.

The Robert Bosch GmbH is looking forward to your application!

Job Description

Behaviour planning is a key challenge in autonomous driving. Map information and complex interactions with other traffic participants must be taken into account to come up with a plan that balances safety with driving progress. Deep Learning (DL) has shown promising results over hand-engineered algorithms.

In this work, we want to improve an existing DL-based planner in situations with limited visibility. We focus on occlusions, which can have different sources: buildings and other intrastructure elements, dynamic objects (e.g. trucks) in line of sight, sensor degradation (e.g. dirt), etc. The challenge is to extend the neural network policy and DL algorithm to perform well in the presence of occlusions.

  • During your thesis you will integrate a simple occlusion algorithm into our training and evaluation pipeline.
  • You will train a neural network policy and observe performance degradation due to occlusions.
  • Not least, you will implement additional inputs to the neural network policy for modelling visibility and improve the learning algorithm to recover performance.


  • Education: studies in the field of science, technology, engineering, mathematics (STEM) or comparable
  • Personality and Working Practice: structured and analytical
  • Experience and Knowledge: good programming skills and coding experience for machine learning applications in Python

Additional Information

Start: according to prior agreement
Duration: 6 months

Requirement for this thesis is the enrollment at university. Please attach a motivation letter, your CV, transcript of records, examination regulations, if available publicly available code (github repos, etc) and if indicated a valid work and residence permit.

Need further information about the job?
Martin Stoll
+49 711 811-14077

Apply now in just 3 minutes!

Expected salary:

Location: Renningen, Baden-Württemberg

Job date: Wed, 18 Aug 2021 02:40:14 GMT

Apply for the job now! – Submit your Resume

Work and Live in Germany? find jobs and information about visa language and applications here