back to search

IN2107 Variational Inference in Robotics

EI71088Advanced Seminar Course5 ECTSEnglishWintersemester/SommersemesterDepartment Computer Engineering
AI-edited module sheet. Based on the TUMonline module description, edited for readability.Original in TUMonline

What it is about

You will learn how Variational Inference can be used for robotics tasks such as state estimation, localization, and navigation. You will approach complex problems in Bayesian inference using stochastic optimization and investigate how probabilistic models can be used for learning, inference, and control. By the end, you will be able to understand, critically analyze, and implement current research on machine learning for control tasks.

What you will be able to do

  • Understand machine learning methods for control tasks, especially models with latent variables
  • Understand and critically analyze research publications on the topics covered
  • Implement research publications on the topics covered

What the module consists of

  • SeminarIntroductory sessions covering the fundamentals; afterward, you will prepare and present a research paper.

Teaching method

  • Introductory sessionsThe first four sessions will cover the key concepts you need to understand current research.
  • Preparation and analysis of a publicationYou will select a research paper, read it, and analyze it. This may include an implementation, reproducing results, open questions, or comparisons with related work.
  • Presentation and discussionYou will present the paper and your findings to the other participants; your own programming examples may complement the presentation.
No dates in the current semester
There are no course dates for this module this semester, or they haven't been matched yet.

Module ratings

No ratings for this module yet.

Rate this module

Only fill in the categories you can judge – for each one, either stars and text together or nothing at all.

Lecture
Tutorial
Exam

Reviews are automatically checked before they are published.

Official page in TUMonline · Details are not binding.