Modulinformationssystem Informatik

 

Probabilistic Robotics URL PDF XML

Modulcode: infProRo-01a
Englische Bezeichnung: Probabilistic Robotics
Modulverantwortliche(r): Prof. Dr. Kevin Köser
Turnus: unregelmäßig (WS23/24)
Präsenzzeiten: 3V 1Ü
ECTS: 5
Workload: 45 Std. Vorlesung, 15 Std. Präsenzübung, 90 Std. Selbststudium
Dauer: ein Semester
Modulkategorien: BSc-Inf-WP (BSc Inf (21)) BSc-WInf-WP-Inf (BSc WInf (21)) MSc-Inf-WP (MSc Inf (21)) 2F-MA-Inf-WP (2F-MA Inf (21)) MSc-WInf-WP-Inf (MSc WInf (21))
Lehrsprache: Englisch
Voraussetzungen: Info

Kurzfassung:

This course will introduce the key challenges, basic concepts and techniques connected to the field of mobile robotics. As robot perception is uncertain, key tasks involve estimating and representing the robot's state (e.g. its current position) and the surrounding's state (e.g. a map of the world) using probabilistic approaches, as well as techniques (e.g. path planning) to reach a goal.

Lernziele:

Understanding

  • the key challenges for mobile robots as well as general concepts how to deal with them
  • theoretical and practical representations of uncertainty
  • motion models and filtering techniques for state estimation based upon sequential measurements
  • concepts for path planning and exploration

Lehrinhalte:

This course will introduce the key challenges, basic concepts and techniques connected to the field of mobile robotics. As robot perception is uncertain, key tasks involve estimating and representing the robot's state (e.g. its current position) and the surrounding's state (e.g. a map of the world) using probabilistic approaches, as well as techniques (e.g. path planning) to reach a goal. Topics include

  • Kinematics
  • Sensors
  • Vehicle localization
  • Map building
  • SLAM (Simultaneous Localization and Mapping)
  • Path planning

The class will follow the approaches described in the book Probabilitic Robotics, see also http://probabilistic-robotics.org/ .

Weitere Voraussetzungen:

Basic knowledge of linear algebra (equation systems, matrix multiplications) and probability is expected. There will be a repetition of the key concepts at the start of the semester though.

Prüfungsleistung:

written exam

Lehr- und Lernmethoden:

Lectures and exercises.

Verwendbarkeit:

Literatur:

Thrun, Burgard, Fox: "Probabilistic Robotics", see e.g. http://probabilistic-robotics.org/

Verweise:

Kommentar: