Taxonomy-aware Dynamic Motion Generation on Hyperbolic Manifolds

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Augenstein, Luis, Jaquier, Noémie, Asfour, Tamim, Rozo, Leonel
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917316969627648
author Augenstein, Luis
Jaquier, Noémie
Asfour, Tamim
Rozo, Leonel
author_facet Augenstein, Luis
Jaquier, Noémie
Asfour, Tamim
Rozo, Leonel
contents Human-like motion generation for robots often draws inspiration from biomechanical studies, which often categorize complex human motions into hierarchical taxonomies. While these taxonomies provide rich structural information about how movements relate to one another, this information is frequently overlooked in motion generation models, leading to a disconnect between the generated motions and their underlying hierarchical structure. This paper introduces the \ac{gphdm}, a novel approach that learns latent representations preserving both the hierarchical structure of motions and their temporal dynamics to ensure physical consistency. Our model achieves this by extending the dynamics prior of the Gaussian Process Dynamical Model (GPDM) to the hyperbolic manifold and integrating it with taxonomy-aware inductive biases. Building on this geometry- and taxonomy-aware frameworks, we propose three novel mechanisms for generating motions that are both taxonomically-structured and physically-consistent: two probabilistic recursive approaches and a method based on pullback-metric geodesics. Experiments on generating realistic motion sequences on the hand grasping taxonomy show that the proposed GPHDM faithfully encodes the underlying taxonomy and temporal dynamics, and it generates novel physically-consistent trajectories.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21281
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Taxonomy-aware Dynamic Motion Generation on Hyperbolic Manifolds
Augenstein, Luis
Jaquier, Noémie
Asfour, Tamim
Rozo, Leonel
Robotics
Machine Learning
Human-like motion generation for robots often draws inspiration from biomechanical studies, which often categorize complex human motions into hierarchical taxonomies. While these taxonomies provide rich structural information about how movements relate to one another, this information is frequently overlooked in motion generation models, leading to a disconnect between the generated motions and their underlying hierarchical structure. This paper introduces the \ac{gphdm}, a novel approach that learns latent representations preserving both the hierarchical structure of motions and their temporal dynamics to ensure physical consistency. Our model achieves this by extending the dynamics prior of the Gaussian Process Dynamical Model (GPDM) to the hyperbolic manifold and integrating it with taxonomy-aware inductive biases. Building on this geometry- and taxonomy-aware frameworks, we propose three novel mechanisms for generating motions that are both taxonomically-structured and physically-consistent: two probabilistic recursive approaches and a method based on pullback-metric geodesics. Experiments on generating realistic motion sequences on the hand grasping taxonomy show that the proposed GPHDM faithfully encodes the underlying taxonomy and temporal dynamics, and it generates novel physically-consistent trajectories.
title Taxonomy-aware Dynamic Motion Generation on Hyperbolic Manifolds
topic Robotics
Machine Learning
url https://arxiv.org/abs/2509.21281