Skip to content

Latest commit

 

History

History
31 lines (26 loc) · 1.96 KB

README.md

File metadata and controls

31 lines (26 loc) · 1.96 KB

Motion Manifold Learning from Demonstration (MMLfD) Tutorial

This repository includes codes for generating figures and videos used in YH's tutoral talk on A Geometric Take on Motion Manifold Learning from Demonstration at Riemann and Gauss meet Asimov: 2nd Tutorial on Geometric Methods in Robot Learning, Optimization and Control in ICRA 2024.

Presentation slides

PDF

Trained models

You can download pre-trained models from HERE. Put these files in the directory MMLfD-Tutorial/results/.

References

Geometric aspects on autoencoders

  • The Riemannian Geometry of Deep Generative Models (Shao et al., CVPR workshops 2018)
  • Latent Space Oddity: on the Curvature of Deep Generative Models (Arvanitidis et al., ICLR 2018)
  • Learning Flat Latent Manifolds with VAEs (Chen et al., ICML 2020)
  • Geometrically Enriched Latent Spaces (Arvanitidis et al., AISTATS 2021)
  • Neighborhood Reconstructing Autoencoders (Lee et al., NeurIPS 2021)
  • Pulling back information geometry (Arvanitidis et al., AISTATS 2022)
  • Regularized Autoencoders for Isometric Representation Learning (Lee et al., ICLR 2022)
  • A Statistical Manifold Framework for Point Cloud Data (Lee et al., ICML 2022)
  • Geometric Autoencoders – What You See is What You Decode (Nazari., ICML 2023)
  • On Explicit Curvature Regularization of Deep Generative Models (Lee et al., TAG-ML 2023)
  • Geometrically regularized autoencoders for non-Euclidean data (Jang et al., ICLR 2023)

Motion manifold primitives

  • Task-Conditioned Variational Autoencoders for Learning Movement Primitives (Noseworthy et al., CoRL 2019)
  • Equivariant Motion Manifold Primitives (Lee et al., CoRL 2023)
  • MMP++: Motion Manifold Primitives with Parametric Curve Models (Lee et al., Arxiv 2024)