Taxonomy-aware Dynamic Motion Generation on Hyperbolic Manifolds
This addresses the disconnect between generated robot motions and their hierarchical structure, offering a domain-specific improvement for robotics and biomechanics.
The paper tackled the problem of generating human-like robot motions that preserve hierarchical taxonomies and physical consistency, introducing the GPHDM model which extends dynamics to hyperbolic manifolds and integrates taxonomy-aware biases, achieving faithful encoding and generation of novel, physically-consistent trajectories in hand grasping experiments.
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 generates novel physically-consistent trajectories.