Zelch, Christoph ; Peters, Jan ; Stryk, Oskar von (2023)
Clustering of Motion Trajectories by a Distance Measure Based on Semantic Features.
22nd International Conference on Humanoid Robots. Austin, USA (12.-14.12.2023)
doi: 10.1109/Humanoids57100.2023.10375228
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Clustering of motion trajectories is highly relevant for human-robot interactions as it allows the anticipation of human motions, fast reaction to those, as well as the recognition of explicit gestures. Further, it allows automated analysis of recorded motion data. Many clustering algorithms for trajectories build upon distance metrics that are based on pointwise Euclidean distances. However, our work indicates that focusing on salient characteristics is often sufficient. We present a novel distance measure for motion plans consisting of state and control trajectories that is based on a compressed representation built from their main features. This approach allows a flexible choice of feature classes relevant to the respective task. The distance measure is used in agglomerative hierarchical clustering. We compare our method with the widely used dynamic time warping algorithm on test sets of motion plans for the Furuta pendulum and the Manutec robot arm and on real-world data from a human motion dataset. The proposed method demonstrates slight advantages in clustering and strong advantages in runtime, especially for long trajectories.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2023 |
| Autor(en): | Zelch, Christoph ; Peters, Jan ; Stryk, Oskar von |
| Art des Eintrags: | Bibliographie |
| Titel: | Clustering of Motion Trajectories by a Distance Measure Based on Semantic Features |
| Sprache: | Englisch |
| Publikationsjahr: | 15 Dezember 2023 |
| Verlag: | IEEE |
| Buchtitel: | 2023 IEEE-RAS 22nd International Conference on Humanoid Robots (Humanoids) |
| Veranstaltungstitel: | 22nd International Conference on Humanoid Robots |
| Veranstaltungsort: | Austin, USA |
| Veranstaltungsdatum: | 12.-14.12.2023 |
| DOI: | 10.1109/Humanoids57100.2023.10375228 |
| URL / URN: | https://ieeexplore.ieee.org/document/10375228 |
| Kurzbeschreibung (Abstract): | Clustering of motion trajectories is highly relevant for human-robot interactions as it allows the anticipation of human motions, fast reaction to those, as well as the recognition of explicit gestures. Further, it allows automated analysis of recorded motion data. Many clustering algorithms for trajectories build upon distance metrics that are based on pointwise Euclidean distances. However, our work indicates that focusing on salient characteristics is often sufficient. We present a novel distance measure for motion plans consisting of state and control trajectories that is based on a compressed representation built from their main features. This approach allows a flexible choice of feature classes relevant to the respective task. The distance measure is used in agglomerative hierarchical clustering. We compare our method with the widely used dynamic time warping algorithm on test sets of motion plans for the Furuta pendulum and the Manutec robot arm and on real-world data from a human motion dataset. The proposed method demonstrates slight advantages in clustering and strong advantages in runtime, especially for long trajectories. |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Simulation, Systemoptimierung und Robotik |
| Hinterlegungsdatum: | 28 Feb 2024 09:19 |
| Letzte Änderung: | 28 Feb 2024 09:19 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum