Introduction to Mobile Robotics

What it is about

You will learn how mobile, especially wheel-driven robots perceive their environment, map it, and move autonomously within it. In the end you can develop probabilistic sensor and motion models, apply filter methods for localization and SLAM, and implement fundamental methods for path planning and obstacle avoidance.

What you will be able to do

• Analysis of navigation sensors (ultrasound, LiDAR, cameras) and design of probabilistic sensor models
• Design of probabilistic motion models
• Implementation of probabilistic localization methods (particle filter, discrete filters, Kalman variants)
• Generation of occupancy grids from sensor data at known poses
• Understanding and derivation of the recursive Bayes filter and evaluation of different representations
• Basic understanding of the SLAM problem (landmark-based, grid-based, graph-based)
• Basic knowledge of motion planning and collision avoidance
• Ability to develop a navigation system for wheel-driven mobile robots

What the module consists of

• VorlesungConveying the concepts of probabilistic methods, SLAM, sensorimotor and planning
• ÜbungenApplication of lecture content to practical examples and in-depth tasks

Teaching method

• Vorlesungsfolien, Tafel oder digitale MedienPresentation of the theoretical content
• Übungsaufgaben und praktische BeispieleConsolidation and application of what has been learned
• Frage- und Abstimmungsformate (z.B. Online-Polls)Encouraging participation and understanding checks
• Eigenständige Implementationen grundlegender AlgorithmenDeepening through practical implementation