Bethge, Johanna ; Pfefferkorn, Maik ; Rose, Alexander ; Peters, Jan ; Findeisen, Rolf (2023)
Model Predictive Control with Gaussian-Process-Supported Dynamical Constraints for Autonomous Vehicles.
In: IFAC-PapersOnLine, 56 (2)
doi: 10.1016/j.ifacol.2023.10.1618
Artikel, Bibliographie
Kurzbeschreibung (Abstract)
We propose a model predictive control approach for autonomous vehicles that exploits learned Gaussian processes (GPs) for predicting human driving behavior. The proposed approach employs the uncertainty about the GP's prediction to achieve safety. The multi-mode predictive control approach considers the possible intentions of the human drivers. While the intentions are represented by different Gaussian processes, their probabilities foreseen in the observed behaviors are determined by a suitable online classification. Intentions below a certain probability threshold are neglected to improve performance. The proposed multi-mode model predictive control approach with Gaussian process regression support enables probabilistic constraint satisfaction with high probability. The approach is underlined in simulation, considering real-world measurements for training the Gaussian processes.
| Typ des Eintrags: | Artikel |
|---|---|
| Erschienen: | 2023 |
| Autor(en): | Bethge, Johanna ; Pfefferkorn, Maik ; Rose, Alexander ; Peters, Jan ; Findeisen, Rolf |
| Art des Eintrags: | Bibliographie |
| Titel: | Model Predictive Control with Gaussian-Process-Supported Dynamical Constraints for Autonomous Vehicles |
| Sprache: | Englisch |
| Publikationsjahr: | Juli 2023 |
| Verlag: | Elsevier |
| Titel der Zeitschrift, Zeitung oder Schriftenreihe: | IFAC-PapersOnLine |
| Jahrgang/Volume einer Zeitschrift: | 56 |
| (Heft-)Nummer: | 2 |
| Veranstaltungsdatum: | 09.07.2023-14.07.2023 |
| DOI: | 10.1016/j.ifacol.2023.10.1618 |
| URL / URN: | https://www.sciencedirect.com/science/article/pii/S240589632... |
| Zugehörige Links: | |
| Kurzbeschreibung (Abstract): | We propose a model predictive control approach for autonomous vehicles that exploits learned Gaussian processes (GPs) for predicting human driving behavior. The proposed approach employs the uncertainty about the GP's prediction to achieve safety. The multi-mode predictive control approach considers the possible intentions of the human drivers. While the intentions are represented by different Gaussian processes, their probabilities foreseen in the observed behaviors are determined by a suitable online classification. Intentions below a certain probability threshold are neglected to improve performance. The proposed multi-mode model predictive control approach with Gaussian process regression support enables probabilistic constraint satisfaction with high probability. The approach is underlined in simulation, considering real-world measurements for training the Gaussian processes. |
| Zusätzliche Informationen: | 22nd IFAC World Congress 2023, Yokohama, Japan, 09.07. - 14.07.2023 |
| Fachbereich(e)/-gebiet(e): | 18 Fachbereich Elektrotechnik und Informationstechnik 18 Fachbereich Elektrotechnik und Informationstechnik > Institut für Automatisierungstechnik und Mechatronik 18 Fachbereich Elektrotechnik und Informationstechnik > Institut für Automatisierungstechnik und Mechatronik > Control and Cyber-Physical Systems (CCPS) |
| Hinterlegungsdatum: | 05 Mär 2024 13:26 |
| Letzte Änderung: | 11 Jun 2024 12:47 |
| PPN: | 519029062 |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum