Toolflownet: Robotic manipulation with tools via predicting tool flow from point clouds
Point clouds are a widely available and canonical data modality which convey the 3D
geometry of a scene. Despite significant progress in classification and segmentation from …
geometry of a scene. Despite significant progress in classification and segmentation from …
Fusion dynamical systems with machine learning in imitation learning: A comprehensive overview
Imitation Learning (IL), also referred to as Learning from Demonstration (LfD), holds
significant promise for capturing expert motor skills through efficient imitation, facilitating …
significant promise for capturing expert motor skills through efficient imitation, facilitating …
Learning safe and stable motion plans with neural ordinary differential equations
A learning-based modular motion planning pipeline is presented that is compliant, safe, and
reactive to perturbations at task execution. A nominal motion plan, defined as a nonlinear …
reactive to perturbations at task execution. A nominal motion plan, defined as a nonlinear …
[HTML][HTML] Learning stable robotic skills on Riemannian manifolds
In this paper, we propose an approach to learn stable dynamical systems that evolve on
Riemannian manifolds. Our approach leverages a data-efficient procedure to learn a …
Riemannian manifolds. Our approach leverages a data-efficient procedure to learn a …
Learning deep robotic skills on Riemannian manifolds
W Wang, M Saveriano, FJ Abu-Dakka - IEEE Access, 2022 - ieeexplore.ieee.org
In this paper, we propose RiemannianFlow, a deep generative model that allows robots to
learn complex and stable skills evolving on Riemannian manifolds. Examples of …
learn complex and stable skills evolving on Riemannian manifolds. Examples of …
Deep metric imitation learning for stable motion primitives
Imitation Learning (IL) is a powerful technique for intuitive robotic programming. However,
ensuring the reliability of learned behaviors remains a challenge. In the context of reaching …
ensuring the reliability of learned behaviors remains a challenge. In the context of reaching …
Unraveling the single tangent space fallacy: An analysis and clarification for applying Riemannian geometry in robot learning
In the realm of robotics, numerous downstream robotics tasks leverage machine learning
methods for processing, modeling, or synthesizing data. Often, this data comprises variables …
methods for processing, modeling, or synthesizing data. Often, this data comprises variables …
Task generalization with stability guarantees via elastic dynamical system motion policies
T Li, N Figueroa - 7th Annual Conference on Robot Learning, 2023 - openreview.net
Dynamical System (DS) based Learning from Demonstration (LfD) allows learning of
reactive motion policies with stability and convergence guarantees from a few trajectories …
reactive motion policies with stability and convergence guarantees from a few trajectories …
Riemannian Flow Matching Policy for Robot Motion Learning
We introduce Riemannian Flow Matching Policies (RFMP), a novel model for learning and
synthesizing robot visuomotor policies. RFMP leverages the efficient training and inference …
synthesizing robot visuomotor policies. RFMP leverages the efficient training and inference …
Kuramoto Oscillators and Swarms on Manifolds for Geometry Informed Machine Learning
V Jacimovic - arXiv preprint arXiv:2405.09453, 2024 - arxiv.org
We propose the idea of using Kuramoto models (including their higher-dimensional
generalizations) for machine learning over non-Euclidean data sets. These models are …
generalizations) for machine learning over non-Euclidean data sets. These models are …