EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

N-Dimensional Reduction Algorithm for Learning from Demonstration Path Planning

Juliana Manrique-Cordoba iD, Miguel Ángel de la Casa-Lillo iD, José María Sabater-Navarro iD

Sensors · 28.03.2025 · 25 (7) · 2145

DOI: 10.3390/s25072145 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 28.03.2025. Verfasst von Juliana Manrique-Cordoba und 2 weiteren Autor:innen. Beteiligte Einrichtung: Bioengineering Institute, Miguel Hernandez University of Elche, 03202 Elche, Spain. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Spanish Government-Agencia Estatal de Investigación (AEI), Generalitat Valenciana, Spanish Government—Agencia Estatal de Investigación (AEI).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents an n-dimensional reduction algorithm for Learning from Demonstration (LfD) for robotic path planning, addressing the complexity of high-dimensional data. The method extends the Douglas–Peucker algorithm by incorporating velocity and orientation alongside position, enabling more precise trajectory simplification. A magnitude-based normalization process preserves proportional relationships across dimensions, and the reduced dataset is used to train Hidden Markov Models (HMMs), where continuous trajectories are discretized into identifier sequences. The algorithm is evaluated in 2D and 3D environments with datasets combining position and velocity. The results show that incorporating additional dimensions significantly enhances trajectory simplification while preserving key information. Additionally, the study highlights the importance of selecting appropriate encoding parameters to achieve optimal resolution. The HMM-based models generated new trajectories that retained the patterns of the original demonstrations, demonstrating the algorithm’s capacity to generalize learned behaviors for trajectory learning in high-dimensional spaces.

Schlagwörter

Stichwörter der Autor:innen

Douglas–Peucker algorithmdata reductionhidden Markov modelshigh-dimensional data encodinglearning from demonstration

Autor:innen und Institutionen

  • Bioengineering Institute, Miguel Hernandez University of Elche, 03202 Elche, Spain.

ORCID-Profile: Juliana Manrique-Cordoba, Miguel Ángel de la Casa-Lillo, José María Sabater-Navarro

Förderung

  • Spanish Government-Agencia Estatal de Investigación (AEI)
  • Generalitat Valenciana
  • Spanish Government—Agencia Estatal de Investigación (AEI)

Zitieren

APA

Manrique-Cordoba, J., de la Casa-Lillo, M. Á., & Sabater-Navarro, J. M. (2025). N-Dimensional Reduction Algorithm for Learning from Demonstration Path Planning. Sensors, 25(7), 2145. https://doi.org/10.3390/s25072145

Vancouver

Manrique-Cordoba J, de la Casa-Lillo MÁ, Sabater-Navarro JM. N-Dimensional Reduction Algorithm for Learning from Demonstration Path Planning. Sensors. 2025;25(7):2145. doi:10.3390/s25072145

BibTeX
@article{ManriqueCordoba2025,
  author = {Manrique-Cordoba, Juliana and de la Casa-Lillo, Miguel Ángel and Sabater-Navarro, José María},
  title = {N-Dimensional Reduction Algorithm for Learning from Demonstration Path Planning},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {7},
  pages = {2145},
  doi = {10.3390/s25072145}
}
Kostenlos starten →