paper-with-me

Papers

Euclideanizing Flows: Diffeomorphic Reduction for Learning Stable Dynamical Systems

2020-05-27 · L4DC 2020 6 · Muhammad Asif Rana, Anqi Li, Dieter Fox, Byron Boots, Fabio Ramos, Nathan Ratliff

Robotic tasks often require motions with complex geometric structures. We present an approach to learn such motions from a limited number of human demonstrations by exploiting the regularity properties of human motions e.g. stability, smoothness, and boundedness. The complex motions are encoded as rollouts of a stable dynamical system, which, under a change of coordinates defined by a diffeomorphism, is equivalent to a simple, hand-specified dynamical system. As an immediate result of using diffeomorphisms, the stability property of the hand-specified dynamical system directly carry over to the learned dynamical system. Inspired by recent works in density estimation, we propose to represent the diffeomorphism as a composition of simple parameterized diffeomorphisms. Additional structure is imposed to provide guarantees on the smoothness of the generated motions. The efficacy of this approach is demonstrated through validation on an established benchmark as well demonstrations collected on a real-world robotic system.

📄 PDF Abstract BibTeX arXiv:2005.13143

Code (2)

mrana6/euclideanizing_flows 공식 구현 pytorch
nash169/learn-diffeomorphism pytorch

Tasks

Density Estimation

Similar Papers 제목 키워드 기반

Funnels: Exact maximum likelihood with dimensionality reduction

2021-12-15 · Samuel Klein, John A. Raine, Sebastian Pina-Otey, Slava Voloshynovskiy 외

Normalizing flows are diffeomorphic, typically dimension-preserving, models trained using the likelihood of the model. We use the SurVAE framework to construct dimension reducing surjective flows via a new layer, known a…

Dimensionality Reduction

Neural Diffeomorphic Non-uniform B-spline Flows

2023-04-07 · Seongmin Hong, Se Young Chun

Normalizing flows have been successfully modeling a complex probability distribution as an invertible transformation of a simple base distribution. However, there are often applications that require more than invertibili…

Diffeomorphically Learning Stable Koopman Operators

2021-12-08 · Petar Bevanda, Max Beier, Sebastian Kerz, Armin Lederer 외

System representations inspired by the infinite-dimensional Koopman operator (generator) are increasingly considered for predictive modeling. Due to the operator's linearity, a range of nonlinear systems admit linear pre…

Operator learning

Residual Networks as Flows of Velocity Fields for Diffeomorphic Time Series Alignment

2021-06-22 · Hao Huang, Boulbaba Ben Amor, Xichan Lin, Fan Zhu 외

Non-linear (large) time warping is a challenging source of nuisance in time-series analysis. In this paper, we propose a novel diffeomorphic temporal transformer network for both pairwise and joint time-series alignment.…

Time SeriesTime Series AlignmentTime Series Analysis

Comparing Dynamical Models Through Diffeomorphic Vector Field Alignment

2025-12-21 · Ruiqi Chen, Giacomo Vedovati, Todd Braver, ShiNung Ching arxiv

Dynamical systems models such as recurrent neural networks (RNNs) are increasingly popular in theoretical neuroscience for hypothesis-generation and data analysis. Evaluating the dynamics in such models is key to underst…