Kreutz, Thomas ; Esbel, Ousama ; Mühlhäuser, Max ; Sanchez Guinea, Alejandro (2022)
Unsupervised Driving Event Discovery Based on Vehicle CAN-data.
25th International Conference on Intelligent Transportation Systems. Macau, Peoples Republik of China (08.10.2022-12.10.2022)
doi: 10.1109/ITSC55140.2022.9922158
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
The data collected from a vehicle's Controller Area Network (CAN) can quickly exceed human analysis or annotation capabilities when considering fleets of vehicles, which stresses the importance of unsupervised machine learning methods. This work presents a simultaneous clustering and segmentation approach for vehicle CAN-data that identifies common driving events in an unsupervised manner. The approach builds on self-supervised learning (SSL) for multivariate time series to distinguish different driving events in the learned latent space. We evaluate our approach with a dataset of real Tesla Model 3 vehicle CAN-data and a two-hour driving session that we annotated with different driving events. With our approach, we evaluate the applicability of recent time series-related contrastive and generative SSL techniques to learn representations that distinguish driving events. Compared to state-of-the-art (SOTA) generative SSL methods for driving event discovery, we find that contrastive learning approaches reach similar performance.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2022 |
| Autor(en): | Kreutz, Thomas ; Esbel, Ousama ; Mühlhäuser, Max ; Sanchez Guinea, Alejandro |
| Art des Eintrags: | Bibliographie |
| Titel: | Unsupervised Driving Event Discovery Based on Vehicle CAN-data |
| Sprache: | Englisch |
| Publikationsjahr: | 1 November 2022 |
| Verlag: | IEEE |
| Buchtitel: | 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC) |
| Veranstaltungstitel: | 25th International Conference on Intelligent Transportation Systems |
| Veranstaltungsort: | Macau, Peoples Republik of China |
| Veranstaltungsdatum: | 08.10.2022-12.10.2022 |
| DOI: | 10.1109/ITSC55140.2022.9922158 |
| Zugehörige Links: | |
| Kurzbeschreibung (Abstract): | The data collected from a vehicle's Controller Area Network (CAN) can quickly exceed human analysis or annotation capabilities when considering fleets of vehicles, which stresses the importance of unsupervised machine learning methods. This work presents a simultaneous clustering and segmentation approach for vehicle CAN-data that identifies common driving events in an unsupervised manner. The approach builds on self-supervised learning (SSL) for multivariate time series to distinguish different driving events in the learned latent space. We evaluate our approach with a dataset of real Tesla Model 3 vehicle CAN-data and a two-hour driving session that we annotated with different driving events. With our approach, we evaluate the applicability of recent time series-related contrastive and generative SSL techniques to learn representations that distinguish driving events. Compared to state-of-the-art (SOTA) generative SSL methods for driving event discovery, we find that contrastive learning approaches reach similar performance. |
| Freie Schlagworte: | emergenCITY, emergenCITY_INF |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Telekooperation LOEWE LOEWE > LOEWE-Zentren LOEWE > LOEWE-Zentren > emergenCITY |
| Hinterlegungsdatum: | 23 Jan 2023 14:25 |
| Letzte Änderung: | 19 Jan 2024 19:31 |
| PPN: | 505591537 |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum