Trajectory Learning Using HMM: Towards Surgical Robotics Implementation

Autonomy represents one of the most promising directions in the future development of surgical robotics, and Learning from Demonstration (LfD) is a key methodology for advancing technologies in this field. The proposed approach extends the classical Douglas-Peucker algorithm by incorporating multidi...

Descripción completa

Detalles Bibliográficos
Autores: Manrique-Cordoba, J, Martorell-Llobregat, C, de la Casa-lillo, MA, Sabater-Navarro, JM
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2025
País:España
Institución:Fundación para el Fomento de la Investigación Sanitaria y Biomédica de la Comunitat Valenciana (FISABIO)
Repositorio:r-FISABIO. Repositorio Institucional de Producción Científica
OAI Identifier:oai:fisabio.fundanetsuite.com:p19016
Acceso en línea:https://fisabio.portalinvestigacion.com/publicaciones/19016
Access Level:acceso abierto
Palabra clave:hidden markov models
learning from demonstration
robotic trajectory learning
trajectory simplification
surgical robotics
id ES_43e14fced2c8ef1facf7c52a5d82df60
oai_identifier_str oai:fisabio.fundanetsuite.com:p19016
network_acronym_str ES
network_name_str España
repository_id_str
spelling Trajectory Learning Using HMM: Towards Surgical Robotics ImplementationManrique-Cordoba, JMartorell-Llobregat, Cde la Casa-lillo, MASabater-Navarro, JMhidden markov modelslearning from demonstrationrobotic trajectory learningtrajectory simplificationsurgical roboticsAutonomy represents one of the most promising directions in the future development of surgical robotics, and Learning from Demonstration (LfD) is a key methodology for advancing technologies in this field. The proposed approach extends the classical Douglas-Peucker algorithm by incorporating multidimensional trajectory data, including both kinematic and dynamic information. This enhancement enables a more comprehensive representation of demonstrated trajectories, improving generalization in high-dimensional spaces. This representation allows clearer codification and interpretation of the information used in the learning process. A series of experiments were designed to validate this methodology. Motion data and force interaction data were collected, preprocessed, and used to train a hidden Markov model (HMM). Different experimental conditions were analyzed, comparing training using only motion data versus incorporating force interaction data. The results demonstrate that including interaction forces improves trajectory reconstruction accuracy, achieving a lower root mean squared error (RMSE) of 0.29 mm, compared to 0.44 mm for the model trained solely on motion data. These findings support the proposed method as an effective strategy for encoding, simplifying, and learning robotic trajectories in surgical applications.MDPI2025info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttps://fisabio.portalinvestigacion.com/publicaciones/19016SENSORSISSN: 14248220reponame:r-FISABIO. Repositorio Institucional de Producción Científicainstname:Fundación para el Fomento de la Investigación Sanitaria y Biomédica de la Comunitat Valenciana (FISABIO)Inglésinfo:eu-repo/semantics/openAccessoai:fisabio.fundanetsuite.com:p190162026-06-11T12:45:17Z
dc.title.none.fl_str_mv Trajectory Learning Using HMM: Towards Surgical Robotics Implementation
title Trajectory Learning Using HMM: Towards Surgical Robotics Implementation
spellingShingle Trajectory Learning Using HMM: Towards Surgical Robotics Implementation
Manrique-Cordoba, J
hidden markov models
learning from demonstration
robotic trajectory learning
trajectory simplification
surgical robotics
title_short Trajectory Learning Using HMM: Towards Surgical Robotics Implementation
title_full Trajectory Learning Using HMM: Towards Surgical Robotics Implementation
title_fullStr Trajectory Learning Using HMM: Towards Surgical Robotics Implementation
title_full_unstemmed Trajectory Learning Using HMM: Towards Surgical Robotics Implementation
title_sort Trajectory Learning Using HMM: Towards Surgical Robotics Implementation
dc.creator.none.fl_str_mv Manrique-Cordoba, J
Martorell-Llobregat, C
de la Casa-lillo, MA
Sabater-Navarro, JM
author Manrique-Cordoba, J
author_facet Manrique-Cordoba, J
Martorell-Llobregat, C
de la Casa-lillo, MA
Sabater-Navarro, JM
author_role author
author2 Martorell-Llobregat, C
de la Casa-lillo, MA
Sabater-Navarro, JM
author2_role author
author
author
dc.subject.none.fl_str_mv hidden markov models
learning from demonstration
robotic trajectory learning
trajectory simplification
surgical robotics
topic hidden markov models
learning from demonstration
robotic trajectory learning
trajectory simplification
surgical robotics
description Autonomy represents one of the most promising directions in the future development of surgical robotics, and Learning from Demonstration (LfD) is a key methodology for advancing technologies in this field. The proposed approach extends the classical Douglas-Peucker algorithm by incorporating multidimensional trajectory data, including both kinematic and dynamic information. This enhancement enables a more comprehensive representation of demonstrated trajectories, improving generalization in high-dimensional spaces. This representation allows clearer codification and interpretation of the information used in the learning process. A series of experiments were designed to validate this methodology. Motion data and force interaction data were collected, preprocessed, and used to train a hidden Markov model (HMM). Different experimental conditions were analyzed, comparing training using only motion data versus incorporating force interaction data. The results demonstrate that including interaction forces improves trajectory reconstruction accuracy, achieving a lower root mean squared error (RMSE) of 0.29 mm, compared to 0.44 mm for the model trained solely on motion data. These findings support the proposed method as an effective strategy for encoding, simplifying, and learning robotic trajectories in surgical applications.
publishDate 2025
dc.date.none.fl_str_mv 2025
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://fisabio.portalinvestigacion.com/publicaciones/19016
url https://fisabio.portalinvestigacion.com/publicaciones/19016
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv SENSORS
ISSN: 14248220
reponame:r-FISABIO. Repositorio Institucional de Producción Científica
instname:Fundación para el Fomento de la Investigación Sanitaria y Biomédica de la Comunitat Valenciana (FISABIO)
instname_str Fundación para el Fomento de la Investigación Sanitaria y Biomédica de la Comunitat Valenciana (FISABIO)
reponame_str r-FISABIO. Repositorio Institucional de Producción Científica
collection r-FISABIO. Repositorio Institucional de Producción Científica
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869407054611873792
score 15.81155

Similares en LA Referencia