paper-with-me

Papers

A Black-Box Physics-Informed Estimator based on Gaussian Process Regression for Robot Inverse Dynamics Identification

2023-10-10 · Giulio Giacomuzzos, Ruggero Carli, Diego Romeres, Alberto Dalla Libera

Learning the inverse dynamics of robots directly from data, adopting a black-box approach, is interesting for several real-world scenarios where limited knowledge about the system is available. In this paper, we propose a black-box model based on Gaussian Process (GP) Regression for the identification of the inverse dynamics of robotic manipulators. The proposed model relies on a novel multidimensional kernel, called \textit{Lagrangian Inspired Polynomial} (\kernelInitials{}) kernel. The \kernelInitials{} kernel is based on two main ideas. First, instead of directly modeling the inverse dynamics components, we model as GPs the kinetic and potential energy of the system. The GP prior on the inverse dynamics components is derived from those on the energies by applying the properties of GPs under linear operators. Second, as regards the energy prior definition, we prove a polynomial structure of the kinetic and potential energy, and we derive a polynomial kernel that encodes this property. As a consequence, the proposed model allows also to estimate the kinetic and potential energy without requiring any label on these quantities. Results on simulation and on two real robotic manipulators, namely a 7 DOF Franka Emika Panda, and a 6 DOF MELFA RV4FL, show that the proposed model outperforms state-of-the-art black-box estimators based both on Gaussian Processes and Neural Networks in terms of accuracy, generality and data efficiency. The experiments on the MELFA robot also demonstrate that our approach achieves performance comparable to fine-tuned model-based estimators, despite requiring less prior information.

📄 PDF Abstract BibTeX arXiv:2310.06585

Code (1)

merlresearch/LIP4RobotInverseDynamics 공식 구현 jax

Tasks

Gaussian Processes

Methods 이 논문이 사용한 방법론

GPS Greedy Policy Search (GPS) is a simple algorithm that learns a policy for test-time data augmentation based on the predictive performance on a validation set. GPS starts with…
Gaussian Process Gaussian Processes are non-parametric models for approximating functions. They rely upon a measure of similarity between points (the kernel function) to predict the value for…

Similar Papers 제목 키워드 기반

Label Propagation Training Schemes for Physics-Informed Neural Networks and Gaussian Processes

2024-04-08 · Ming Zhong, Dehao Liu, Raymundo Arroyave, Ulisses Braga-Neto

This paper proposes a semi-supervised methodology for training physics-informed machine learning methods. This includes self-training of physics-informed neural networks and physics-informed Gaussian processes in isolati…

Gaussian ProcessesPhysics-informed machine learning

Online tuning and light source control using a physics-informed Gaussian process Adi

2019-11-04 · A. Hanuka, J. Duris, J. Shtalenkova, D. Kennedy 외

Operating large-scale scientific facilities often requires fast tuning and robust control in a high dimensional space. In this paper we introduce a new physics-informed optimization algorithm based on Gaussian process re…

regression

Physics-informed kernel learning

2024-09-20 · Nathan Doumèche, Francis Bach, Gérard Biau, Claire Boyer

Physics-informed machine learning typically integrates physical priors into the learning process by minimizing a loss function that includes both a data-driven term and a partial differential equation (PDE) regularizatio…

Physics-informed machine learning

An interpretation of the Brownian bridge as a physics-informed prior for the Poisson equation

2025-02-28 · Alex Alberts, Ilias Bilionis

Physics-informed machine learning is one of the most commonly used methods for fusing physical knowledge in the form of partial differential equations with experimental data. The idea is to construct a loss function wher…

FormGaussian ProcessesPhysics-informed machine learningregression

Structural Constraints for Physics-augmented Learning

2024-10-07 · Simon Kuang, Xinfan Lin

When the physics is wrong, physics-informed machine learning becomes physics-misinformed machine learning. A powerful black-box model should not be able to conceal misconceived physics. We propose two criteria that can b…

Physics-informed machine learning