Master Thesis Samplingbased Prediction and Planning for Autonomous Driving

Location

Magstadt | Germany

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 GmbHis looking forward to your application!

Job Description

Anticipating the future behavior of surrounding traffic participants is a crucial enabler for safe and performant autonomous driving in challenging urban scenarios. It enables a downstream planner to avoid collisions and progress toward its goal while interacting with other traffic participants. There are different approaches to integrate prediction with planning: the traditional pipeline that feeds prediction feeding into planning, performing a tree search during planning and calling prediction, prediction conditioned on the ego, and jointly planning and predicting. However each of these presents certain downsides. Therefore, we anticipate the need to depart from traditional integration approaches and propose alternatives that find both safe and assertive solutions. 

In this thesis we want to integrate a probabilistic prediction module with an interactive planning component, benchmark and evaluate the system in simulations and on research datasets, and extend it to address limitations in the state of the art. In particular, the proposed integration aims to address highly interactive scenarios in which the ego must decide if, how and when to influence the other road users.

• In the scope of your research, you will implement and evaluate an integrated self-driving system based on available components, e.g. sampling-based prediction and planning.
• Moreover, you will investigate your approaches on realistic open-source benchmarks and extend the integrated system to appropriately trade-off defensiveness and assertiveness.
• Later, you will be able to develop and test additional improvements on your own and discuss them within the scientific community to receive valuable feedback.
• Last but not least you will conduct independent research and present results in publishable manner.  

Qualifications

• Education: studies in the field of Computer Science, Electrical Engineering or comparable with a robotics/machine learning focus and very good grades
• Experience and Knowledge: Experience in reading research papers and coding experience for machine learning applications, in Python with PyTorch, TensorFlow or JAX
• Personality and Working Practice: eager to learn and open-minded to publish new findings
• Enthusiasm: to dive into a topic at the frontiers of machine learning research and autonomous driving applications
• Languages: fluent in English

Additional Information

Start: according to prior agreement
Duration: 6 months thesis and 3 months internship if applicable

Requirement for this thesis is the enrollment at university. Please attach your CV, transcript of records, examination regulations and if indicated a valid work and residence permit.

Diversity and inclusion are not just trends for us but are firmly anchored in our corporate culture. Therefore, we welcome all applications, regardless of gender, age, disability, religion, ethnic origin or sexual identity.

Need further information about the job?
Faris Janjos (Business Department)
+49 711 811 49109
Marcel Hallgarten (Business Department)
+49 711 811 58842

#LI-DNI

Summary

• Type: Full-time
• Function: Research

Job tags

Salary