Thema5079: Unterschied zwischen den Versionen
Aus Aifbportal
Pu0288 (Diskussion | Beiträge) (Die Seite wurde neu angelegt: „{{Abschlussarbeit |Titel=Graph-Level Anomaly Detection in Traffic Scenarios for Autonomous Driving (AD) |Abschlussarbeitstyp=Bachelor |Betreuer=Ferdinand Müts…“) |
Pu0288 (Diskussion | Beiträge) |
||
| (2 dazwischenliegende Versionen desselben Benutzers werden nicht angezeigt) | |||
| Zeile 8: | Zeile 8: | ||
|Ausschreibung=2024_04_17_Bachelor_Thesis_Graph_Anomaly_Detection_en.pdf | |Ausschreibung=2024_04_17_Bachelor_Thesis_Graph_Anomaly_Detection_en.pdf | ||
|Beschreibung DE=<p> | |Beschreibung DE=<p> | ||
| − | Traffic scenarios and situations that are especially critical and/or occur only very rarely in the real world (i.e. anomalies) are of particular interest for the development and verification of autonomous vehicles. An essential part | + | Traffic scenarios and situations that are especially critical and/or occur only very rarely in the real world (i.e. anomalies) are of particular interest for the development and verification of autonomous vehicles. An essential part towards so called scenario-based testing is to extract such scenarios automatically from data sets as a first step and generate them synthetically as a next step, using deep learning methods on graph-structured data. One direction towards finding edge case scenarios in large-scale datasets is to apply concepts of anomaly detection. Specifically, as traffic scenarios are modeled as heterogeneous, spatio-temporal graphs in our research, the problem boils down to exploring and applying graph anomaly detection to especially large and complex scenario graphs. |
</p> | </p> | ||
<br> | <br> | ||
| − | < | + | <b>Literature</b> |
| + | <ul> | ||
| + | <li>X. Luo et al., “Deep graph level anomaly detection with contrastive learning,” Sci Rep, vol. 12, no. 1, Art. no. 1, Nov. 2022, doi: 10.1038/s41598-022-22086-3.</li> | ||
| + | <li>X. Wang, B. Jin, Y. Du, P. Cui, and Y. Yang, “One-Class Graph Neural Networks for Anomaly Detection in Attributed Networks,” Neural Comput & Applic, vol. 33, no. 18, pp. 12073–12085, Sep. 2021, doi: 10.1007/s00521-021-05924-9.</li> | ||
| + | <li>C. Qiu, M. Kloft, S. Mandt, and M. Rudolph, “Raising the Bar in Graph-level Anomaly Detection.” arXiv, May 27, 2022. doi: 10.48550/arXiv.2205.13845.</li> | ||
| + | <li>E. Meyer, M. Brenner, B. Zhang, M. Schickert, B. Musani, and M. Althoff, “Geometric Deep Learning for Autonomous Driving: Unlocking the Power of Graph Neural Networks With CommonRoad-Geometric.” arXiv, Apr. 24, 2023.</li> | ||
| + | </ul> | ||
| + | |||
| + | <br> | ||
| + | |||
| + | <b>Structure</b> | ||
<ul> | <ul> | ||
<li>Literature research and exploration of the current state-of-the-art in …</li> | <li>Literature research and exploration of the current state-of-the-art in …</li> | ||
<ul> | <ul> | ||
| − | <li>… graph representation learning using Graph Neural Networks (GNN)</li> | + | <li> … graph representation learning using Graph Neural Networks (GNN)</li> |
| − | <li>… graph-anomaly detection, specifically for dynamic and heterogeneous graphs</li> | + | <li> … graph-anomaly detection, specifically for dynamic and heterogeneous graphs</li> |
</ul> | </ul> | ||
<li>Evaluation of existing methods and application to complex traffic scenario graphs</li> | <li>Evaluation of existing methods and application to complex traffic scenario graphs</li> | ||
| Zeile 28: | Zeile 38: | ||
<br> | <br> | ||
| − | < | + | <b>Preferred skills</b> |
<ul> | <ul> | ||
<li>Solid foundations in the field machine learning, specifically deep learning</li> | <li>Solid foundations in the field machine learning, specifically deep learning</li> | ||
| − | <li> | + | <li>Preferably basic knowledge of Graph Neural Networks</li> |
<li>Hands-on experience with Python and frameworks like PyTorch and / or TensorFlow</li> | <li>Hands-on experience with Python and frameworks like PyTorch and / or TensorFlow</li> | ||
<li>Willingness to acquire new technical knowledge, read and understand scientific papers and work independently</li> | <li>Willingness to acquire new technical knowledge, read and understand scientific papers and work independently</li> | ||
| Zeile 39: | Zeile 49: | ||
<br> | <br> | ||
| − | < | + | <b>Required documents</b> |
<ul> | <ul> | ||
<li>Brief cover letter (3-4 sentences)</li> | <li>Brief cover letter (3-4 sentences)</li> | ||
<li>Brief CV (max. 2 pages)</li> | <li>Brief CV (max. 2 pages)</li> | ||
| − | <li> | + | <li>Your current grades (Notenauszug)</li> |
</ul> | </ul> | ||
}} | }} | ||
Aktuelle Version vom 17. April 2024, 11:31 Uhr
Graph-Level Anomaly Detection in Traffic Scenarios for Autonomous Driving (AD)
Informationen zur Arbeit
Abschlussarbeitstyp: Bachelor
Betreuer: Ferdinand Mütsch
Forschungsgruppe: Angewandte Technisch-Kognitive Systeme
Archivierungsnummer: 5079
Abschlussarbeitsstatus: Offen
Beginn:
17. April 2024
Abgabe: unbekannt
Weitere Informationen
Traffic scenarios and situations that are especially critical and/or occur only very rarely in the real world (i.e. anomalies) are of particular interest for the development and verification of autonomous vehicles. An essential part towards so called scenario-based testing is to extract such scenarios automatically from data sets as a first step and generate them synthetically as a next step, using deep learning methods on graph-structured data. One direction towards finding edge case scenarios in large-scale datasets is to apply concepts of anomaly detection. Specifically, as traffic scenarios are modeled as heterogeneous, spatio-temporal graphs in our research, the problem boils down to exploring and applying graph anomaly detection to especially large and complex scenario graphs.
Literature
- X. Luo et al., “Deep graph level anomaly detection with contrastive learning,” Sci Rep, vol. 12, no. 1, Art. no. 1, Nov. 2022, doi: 10.1038/s41598-022-22086-3.
- X. Wang, B. Jin, Y. Du, P. Cui, and Y. Yang, “One-Class Graph Neural Networks for Anomaly Detection in Attributed Networks,” Neural Comput & Applic, vol. 33, no. 18, pp. 12073–12085, Sep. 2021, doi: 10.1007/s00521-021-05924-9.
- C. Qiu, M. Kloft, S. Mandt, and M. Rudolph, “Raising the Bar in Graph-level Anomaly Detection.” arXiv, May 27, 2022. doi: 10.48550/arXiv.2205.13845.
- E. Meyer, M. Brenner, B. Zhang, M. Schickert, B. Musani, and M. Althoff, “Geometric Deep Learning for Autonomous Driving: Unlocking the Power of Graph Neural Networks With CommonRoad-Geometric.” arXiv, Apr. 24, 2023.
Structure
- Literature research and exploration of the current state-of-the-art in …
- … graph representation learning using Graph Neural Networks (GNN)
- … graph-anomaly detection, specifically for dynamic and heterogeneous graphs
- Evaluation of existing methods and application to complex traffic scenario graphs
- Improvement and extension of existing methods to the specific domain of scenario-based testing in AD
- Benchmark, quantitative and qualitative evaluation of different approaches
- Composition of a scenario catalog / dataset of semantically “abnormal” traffic scenarios
Preferred skills
- Solid foundations in the field machine learning, specifically deep learning
- Preferably basic knowledge of Graph Neural Networks
- Hands-on experience with Python and frameworks like PyTorch and / or TensorFlow
- Willingness to acquire new technical knowledge, read and understand scientific papers and work independently
- Fluent in German and / or English
Required documents
- Brief cover letter (3-4 sentences)
- Brief CV (max. 2 pages)
- Your current grades (Notenauszug)
Ausschreibung: Download (pdf)