Module: Perception, Mapping, and Localization (Part 1)
| Study level | Bachelor |
|---|---|
| ECTS credits | 1 ECTS |
| Study forms | Hybrid or fully online |
| Module aims | The aim of the module is to introduce perception, mapping and localisation methods for autonomous systems. The course develops students’ ability to combine data from multiple sensors to detect and interpret the environment, build maps, estimate vehicle pose in real time and handle uncertainty using modern AI-based perception and sensor fusion techniques. |
| Pre-requirements | Basic knowledge of linear algebra, probability and signal processing, as well as programming skills. Familiarity with control systems, kinematics, Linux/ROS environments or computer vision libraries is recommended but not mandatory. |
| Learning outcomes | Knowledge • Describe perception, mapping, and localization processes in autonomous systems. • Explain principles of sensor fusion, simultaneous localization and mapping. • Understand AI-based perception, including object detection, classification, and scene understanding. Skills • Implement basic perception and mapping algorithms using data from multiple sensors. • Apply AI models to detect and classify environmental objects. • Evaluate uncertainty and performance in localization and mapping using simulation tools. Understanding • Appreciate challenges of perception under varying environmental conditions. • Recognize the role of data quality, calibration, and synchronization in sensor fusion. • Adopt responsible practices when designing AI-driven perception modules for safety-critical applications. |
| Topics | 1. Cameras, LiDARs, radars, and IMUs in perception and mapping. 2. Sensor calibration, synchronization, and uncertainty modeling. 3. Principles of multi-sensor fusion (Kalman/Particle filters, deep fusion networks). 4. Object recognition and classification under variable conditions. 5. SLAM, Visual Odometry, and GNSS. 6. Map representation and maintenance for autonomous navigation. 7. CNNs, semantic segmentation, and predictive modeling of dynamic environments. 8. Perception under poor visibility, occlusions, and sensor noise. 9. Integration of perception and localization pipelines in ROS2. |
| Type of assessment | The prerequisite of a positive grade is a positive evaluation of module topics and presentation of practical work results with required documentation |
| Learning methods | Lecture — Theoretical background on perception, mapping, and AI-based scene understanding. Lab works — Implementation of sensor fusion and mapping algorithms using ROS2, Python, and simulated data. Individual assignments — Analysis of perception pipeline performance and report preparation. Self-learning — Study of academic papers, datasets, and open-source AI perception frameworks. |
| AI involvement | AI tools can assist in code debugging, model training, and visualization of perception results. Students must cite AI-generated assistance transparently and verify the correctness of outcomes. |
| Recommended tools and environments | SLAM, CNN, OpenCV, PyTorch, TensorFlow, KITTI, NuScenes |
| Verification and Validation focus | |
| Relevant standards and regulatory frameworks | ISO 26262, ISO 21448 (SOTIF) |
