N-Dimensional Reduction Algorithm for Learning from Demonstration Path Planning

This paper presents an <i>n</i>-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 positi...

Full description

Saved in:
Bibliographic Details
Main Authors: Juliana Manrique-Cordoba, Miguel Ángel de la Casa-Lillo, José María Sabater-Navarro
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/7/2145
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850212752247750656
author Juliana Manrique-Cordoba
Miguel Ángel de la Casa-Lillo
José María Sabater-Navarro
author_facet Juliana Manrique-Cordoba
Miguel Ángel de la Casa-Lillo
José María Sabater-Navarro
author_sort Juliana Manrique-Cordoba
collection DOAJ
description This paper presents an <i>n</i>-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.
format Article
id doaj-art-c74bafd0cfde4be8abeb1a66eb6f0cb6
institution OA Journals
issn 1424-8220
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-c74bafd0cfde4be8abeb1a66eb6f0cb62025-08-20T02:09:17ZengMDPI AGSensors1424-82202025-03-01257214510.3390/s25072145N-Dimensional Reduction Algorithm for Learning from Demonstration Path PlanningJuliana Manrique-Cordoba0Miguel Ángel de la Casa-Lillo1José María Sabater-Navarro2Bioengineering Institute, Miguel Hernandez University of Elche, 03202 Elche, SpainBioengineering Institute, Miguel Hernandez University of Elche, 03202 Elche, SpainBioengineering Institute, Miguel Hernandez University of Elche, 03202 Elche, SpainThis paper presents an <i>n</i>-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.https://www.mdpi.com/1424-8220/25/7/2145learning from demonstrationhidden Markov modelsdata reductionDouglas–Peucker algorithmhigh-dimensional data encoding
spellingShingle Juliana Manrique-Cordoba
Miguel Ángel de la Casa-Lillo
José María Sabater-Navarro
N-Dimensional Reduction Algorithm for Learning from Demonstration Path Planning
Sensors
learning from demonstration
hidden Markov models
data reduction
Douglas–Peucker algorithm
high-dimensional data encoding
title N-Dimensional Reduction Algorithm for Learning from Demonstration Path Planning
title_full N-Dimensional Reduction Algorithm for Learning from Demonstration Path Planning
title_fullStr N-Dimensional Reduction Algorithm for Learning from Demonstration Path Planning
title_full_unstemmed N-Dimensional Reduction Algorithm for Learning from Demonstration Path Planning
title_short N-Dimensional Reduction Algorithm for Learning from Demonstration Path Planning
title_sort n dimensional reduction algorithm for learning from demonstration path planning
topic learning from demonstration
hidden Markov models
data reduction
Douglas–Peucker algorithm
high-dimensional data encoding
url https://www.mdpi.com/1424-8220/25/7/2145
work_keys_str_mv AT julianamanriquecordoba ndimensionalreductionalgorithmforlearningfromdemonstrationpathplanning
AT miguelangeldelacasalillo ndimensionalreductionalgorithmforlearningfromdemonstrationpathplanning
AT josemariasabaternavarro ndimensionalreductionalgorithmforlearningfromdemonstrationpathplanning