A Research Platform for Singapore

Master Thesis / Internship (Investigation of the Potential of Reinforcement Learning for Trajectory Planning for Autonomous Vehicles)

Department: Individual Mobility Vehicles and Services
Posted Date:11 February 2020
Closing Date:Open until filled
Hours:Full Time
Duration:Fixed Term

Project Title: Investigation of the Potential of Reinforcement Learning for Trajectory Planning for Autonomous Vehicles 

Specialization: Neural Networks, Reinforcement Learning, Trajectory Planning

TUMCREATE is a research platform for the improvement of Singapore's public transportation, including the deployment of electric and autonomous mobility. Researchers from Technical University Munich and Nanyang Technological University join forces and are funded by Singapore’s National Research Foundation as part of the Campus for Research Excellence and Technological Enterprise (CREATE).


In TUMCREATE, over 100 scientists, researchers and engineers work together, led by Professors from the Technical University of Munich and Nanyang Technological University. The Mission of TUMCREATE is to seek the ultimate public transport system for the people of Singapore. Our innovative road transport solutions will provide high comfort and a positive travel experience, best protection of the environment and maximum benefit to the society and the economy.


In TUM CREATE Phase II, the IMVS team focuses, from vehicle to component level, on the development of concepts and technologies for a new electrified and autonomous minibus for the megacity Singapore. This vehicle will be operated in a new public transportation system, with adapted infrastructure and dynamic routing. In order to ensure save selfdriving in an urban environment, different approaches for the trajectory planning are investigated in simulations. 

Objective and Tasks

The major task of the master’s thesis is within the area of neural network algorithm development for autonomous vehicles. The work involves an initial literature survey on state-of-the-art methods for reinforcement learning (RL) for autonomous driving as well as a research on current challenges in end-to-end self-driving approaches. A reinforcement learning (RL) algorithm should be implemented in an existing end-to-end self-driving framework and should be trained as well as tested in a simulation environment. Finally, the performance of the implementation should be compared with that of the state-of-the-art approaches.

• Literature survey in the field of autonomous driving and reinforcement learning

• Implementation of a reinforcement learning environment using Python

• Training and testing of the implemented RL architecture in a simulator for autonomous vehicles

• Comparison of the achieved performance with that of the state-of-the-art methods

• High quality documentation in the form of a thesis 

 What we expect from you

• Student in the fields of mechanical engineering, computer science, electrical engineering or similar

• Experience in the field of autonomous driving, reinforcement learning and neural networks

• Very good programming skills, preferred Python

 Fluency in English 

What we offer you 
 • Interesting innovative research topic

• Dynamic, young and self-defined work environment

• Financial support

• A great experience in one of the most dynamic megacities in Asia

Enquiries and How to Apply

Please send your complete application including cover letter, CV, university transcripts and degree certificates to sebastian.huch@tum-create.edu.sg.