Kreutz, Thomas ; Mühlhäuser, Max ; Sanchez Guinea, Alejandro (2024)
Common Sense Initialization of Mixture Density Networks for Motion Planning with Overestimated Number of Components.
12th International Conference on Learning Representations (ICLR 2024). Vienna, Austria (07.05.2024-11.05.2024)
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Mixture density networks (MDNs) are a natural choice to model multi-modal predictions for trajectory prediction or motion planning. However, MDNs are often difficult to train due to mode collapse and a need for careful initialization, which becomes even more problematic when the number of mixture components are strongly overestimated. To address this issue in motion planning problems, we propose a pre-training scheme for MDNs called common sense initialization (CSI). Pre-training with CSI allows variety-encouraging optimization such as Winner-Takes-All (WTA) to exploit the initialized weights during training, so that the MDN can converge when the number of components are overestimated. This paper presents empirical evidence for the effectiveness of CSI when applied to motion planning of pedestrian agents in urban environments.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2024 |
| Autor(en): | Kreutz, Thomas ; Mühlhäuser, Max ; Sanchez Guinea, Alejandro |
| Art des Eintrags: | Bibliographie |
| Titel: | Common Sense Initialization of Mixture Density Networks for Motion Planning with Overestimated Number of Components. |
| Sprache: | Englisch |
| Publikationsjahr: | 19 März 2024 |
| Verlag: | OpenReview |
| Buchtitel: | The Second Tiny Papers Track at ICLR 2024 |
| Veranstaltungstitel: | 12th International Conference on Learning Representations (ICLR 2024) |
| Veranstaltungsort: | Vienna, Austria |
| Veranstaltungsdatum: | 07.05.2024-11.05.2024 |
| URL / URN: | https://openreview.net/forum?id=C6EHiLaiBT |
| Kurzbeschreibung (Abstract): | Mixture density networks (MDNs) are a natural choice to model multi-modal predictions for trajectory prediction or motion planning. However, MDNs are often difficult to train due to mode collapse and a need for careful initialization, which becomes even more problematic when the number of mixture components are strongly overestimated. To address this issue in motion planning problems, we propose a pre-training scheme for MDNs called common sense initialization (CSI). Pre-training with CSI allows variety-encouraging optimization such as Winner-Takes-All (WTA) to exploit the initialized weights during training, so that the MDN can converge when the number of components are overestimated. This paper presents empirical evidence for the effectiveness of CSI when applied to motion planning of pedestrian agents in urban environments. |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Telekooperation LOEWE LOEWE > LOEWE-Zentren LOEWE > LOEWE-Zentren > emergenCITY |
| Hinterlegungsdatum: | 28 Nov 2024 08:40 |
| Letzte Änderung: | 28 Nov 2024 08:40 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum