Bringing robotics taxonomies to continuous domains via GPLVM on hyperbolic manifolds

10/04/2022
by   Noémie Jaquier, et al.
5

Robotic taxonomies have appeared as high-level hierarchical abstractions that classify how humans move and interact with their environment. They have proven useful to analyse grasps, manipulation skills, and whole-body support poses. Despite the efforts devoted to design their hierarchy and underlying categories, their use in application fields remains scarce. This may be attributed to the lack of computational models that fill the gap between the discrete hierarchical structure of the taxonomy and the high-dimensional heterogeneous data associated to its categories. To overcome this problem, we propose to model taxonomy data via hyperbolic embeddings that capture the associated hierarchical structure. To do so, we formulate a Gaussian process hyperbolic latent variable model and enforce the taxonomy structure through graph-based priors on the latent space and distance-preserving back constraints. We test our model on the whole-body support pose taxonomy to learn hyperbolic embeddings that comply with the original graph structure. We show that our model properly encodes unseen poses from existing or new taxonomy categories, it can be used to generate trajectories between the embeddings, and it outperforms its Euclidean counterparts.

READ FULL TEXT

page 2

page 8

page 9

page 18

page 21

page 23

page 25

page 26

research
09/22/2021

HyperExpan: Taxonomy Expansion with Hyperbolic Representation Learning

Taxonomies are valuable resources for many applications, but the limited...
research
06/05/2019

Every child should have parents: a taxonomy refinement algorithm based on hyperbolic term embeddings

We introduce the use of Poincaré embeddings to improve existing state-of...
research
06/12/2018

Embedding Text in Hyperbolic Spaces

Natural language text exhibits hierarchical structure in a variety of re...
research
05/22/2017

Poincaré Embeddings for Learning Hierarchical Representations

Representation learning has become an invaluable approach for learning f...
research
10/16/2022

HyperMiner: Topic Taxonomy Mining with Hyperbolic Embedding

Embedded topic models are able to learn interpretable topics even with l...
research
12/04/2018

Hyperbolic Embeddings for Learning Options in Hierarchical Reinforcement Learning

Hierarchical reinforcement learning deals with the problem of breaking d...
research
08/12/2023

Visualising category recoding and numeric redistributions

This paper proposes graphical representations of data and rationale prov...

Please sign up or login with your details

Forgot password? Click here to reset