Master Praktikum: Automatic Diagnosis of Drone Crashes (IN2106, IN4250)
Master-Praktikum: Automatic Diagnosis of Drone Crashes (IN2106, IN4250)
Lehrveranstaltung 0000004095 im SS 2019
Basisdaten
| LV-Art | Praktikum |
|---|---|
| Umfang | 6 SWS |
| betreuende Organisation | Informatik 4 - Lehrstuhl für Software & Systems Engineering (Prof. Pretschner) |
| Dozent(inn)en |
Ehsan Zibaei Leitung/Koordination: Alexander Pretschner |
| Termine |
Di, 14:00–15:30, MI 00.11.038 |
Zuordnung zu Modulen
-
IN2106: Master-Praktikum / Advanced Practical Course
Dieses Modul ist in den folgenden Katalogen enthalten:- weitere Module aus anderen Fachrichtungen
weitere Informationen
Lehrveranstaltungen sind neben Prüfungen Bausteine von Modulen. Beachten Sie daher, dass Sie Informationen zu den Lehrinhalten und insbesondere zu Prüfungs- und Studienleistungen in der Regel nur auf Modulebene erhalten können (siehe Abschnitt "Zuordnung zu Modulen" oben).
| ergänzende Hinweise | Drones are becoming increasingly popular in different applications however at the same time number of drone incidents is increasing. See for example the incident which was caused by a bug in the drone controller: https://vimeo.com/93915783 One way to improve the safety of drones is to look at the vast amount of data produced by them and automatically learn the causes of the incidents. This way the next versions of the drone will be designed safer against similar problems. Although data of drones and data mining techniques are available, still a methodology is needed to transform the data mining outputs into useful diagnosis results. The focus of this practical course is on using data mining methods to deduce the causal relationship between components or events in the context of cyber-physical systems in general and drones in particular. Students will be provided with the data and information of a quadcopter drone, where they will use data mining methods to generate correlational knowledge from the data. Then, students will deduce causal models from correlational knowledge using causality principles such as prediction improvement or counterfactual reasoning. The output of the analysis, in the form of structural equation models (SEMs), will be represented in a graph consisting of the components as nodes and causal connections as edges. This graph will be evaluated by comparing it with the ground truth. The topics to be covered in this practical course include (but not limited to): - CPS components and architecture - Rule-based diagnosis - Data-driven diagnosis - Causality concepts and definitions - Time series data mining - Diagnosis of real-world drone crashes |
|---|---|
| Links |
LV-Unterlagen E-Learning-Kurs (z. B. Moodle) TUMonline-Eintrag |