Education and Teaching

Here you can find an overview of the courses that we teach at TU Delft. We also supervise BSc and MSc projects. If you are interested in joining our group, please see the information below.

Courses Currently Taught

  • Planning and Decision Making (RO47005) at M.Sc. Robotics, TU Delft (Q2).

Past Courses

  • Robot Motion Planning and Control (SC42090/ME47035) at TU Delft in Q3.
  • Invited lecture in the course Introduction to Artificial Intelligence at TU Delft.
  • Invited lecture in the course Intelligent Vehicles at TU Delft
  • Mentor and invited lecture at MIT 2016: Duckietown: 2.166 Autonomous Vehicles
  • Tutorial on Multi-robot Systems at RSS 2015: Optimal Control and Optimization Methods for Multi-Robot Systems

Student Projects

BSc internships / research assistant

Our department does not normally offer any such positions for external students. Contact Javier Alonso-Mora if you are interested in joining our group.

MSc projects

These projects are primarily for students in the TUD MSc Robotics. In exceptional cases, we also supervise students from other MSc studies - if you are interested please see below the information that we require from you. Although projects can start anytime, most projects start in the fall and we try to announce them in the spring. We advise interested students to contact us several months before the intended start date.

All of our MSc Thesis + Literature Survey assignments can be extended with a Research Assignment in the same topic. This is an interesting option for students interested in a longer research experience (e.g. if you would like to publish an article during your MSc thesis or do a PhD afterwards). We do not offer separate Research Assignments - only those linked to an MSc thesis project. You may also choose to do an Internship in a company.

If you do not find an interesting project, but you would like to join our group, or your would like to propose your own project, then, send an email to Prof. J. Alonso-Mora. We can also supervise TUD MSc students in industry or in our partners abroad. For example in one of our industrial partners or collaborators (e.g., MIT, Stanford, ETH Zurich, Harvard, TUM, etc). Send an email to Prof. J. Alonso-Mora if interested.

In the following link you can find a list of available MSc projects. For announced projects, please first contact the daily supervisor to discuss the project.

Internships

Several companies working in robotics or transportation offer internships (and sometimes MSc projects) for MSc students. Some companies that you may reach out to are: 2getthere, SPOTS, Lowpad, Motional, TNO, The Routing Company, MOIA, Vanderlande, Siemens (autonomous cars), Lely, Verity Studios, any car manufacturer, Amazon (application is almost one year in advance), Demcon Unmanned Systems, Via, Uber, Ortec, Prime Vision, Connexxion… You may also find many more companies searching the websites of Robovalley and Yes! Delft.

Recorded Talks

  • February 21, 2024, Lasse Peters: Game-Theoretic Models for Multi-Agent Interaction
    Abstract: When multiple agents operate in a common environment, their actions are naturally interdependent and this coupling complicates planning. In this lecture, we will approach this problem through the lens of dynamic game theory. We will discuss how to model multi-agent interactions as general-sum games over continuous states and actions, characterize solution concepts of such games, and highlight the key challenges of solving them in practice. Based on this foundation, we will review established techniques to tractably approximate game solutions for online decision-making. Finally, will discuss extensions of the game-theoretic framework to settings that involve incomplete knowledge about the intent, dynamics, or state of other agents.
  • May 06, 2023, Lasse Peters: Contingency Games for Multi-Agent Interaction
    Abstract: Contingency planning, wherein an agent generates a set of possible plans conditioned on the outcome of an uncertain event, is an increasingly popular way for robots to act under uncertainty. In this talk, it will be presented a game-theoretic perspective on contingency planning which is tailored to multi-agent scenarios in which a robot's actions impact the decisions of other agents and vice versa. The resulting contingency game allows the robot to efficiently coordinate with other agents by generating strategic motion plans conditioned on multiple possible intents of other actors in the scene. Beyond this new problem formulation, it will be (i) discussed an efficient method for solving $N$-player contingency games with nonlinear dynamics and non-convex costs and constraints, (ii) shown that this framework recovers existing variants of game-theoretic planning under uncertainty as special case, and (iii) demonstrated quantitative performance gains over game-theoretic motion plans that do not account for future uncertainty reduction.