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