• KernelSOS for Global Sampling-...

Treffer: KernelSOS for Global Sampling-Based Optimal Control and Estimation via Semidefinite Programming

Title:
KernelSOS for Global Sampling-Based Optimal Control and Estimation via Semidefinite Programming
Authors:
Groudiev, Antoine, Schramm, Fabian, Berthier, Eloïse, Carpentier, Justin, Dümbgen, Frederike
Contributors:
Département d'informatique - ENS-PSL (DI-ENS), École normale supérieure - Paris (ENS-PSL), Université Paris Sciences et Lettres (PSL)-Université Paris Sciences et Lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS), Models of visual object recognition and scene understanding (WILLOW), Université Paris Sciences et Lettres (PSL)-Université Paris Sciences et Lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS-PSL), Université Paris Sciences et Lettres (PSL)-Université Paris Sciences et Lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Centre Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria), École Nationale Supérieure de Techniques Avancées (ENSTA), Institut Polytechnique de Paris (IP Paris), DIM AI4IDF, ANR-22-CE33-0008,NIMBLE,Apprentissage et contrôle de modèles sensori-moteurs en robotique(2022), ANR-23-IACL-0008,PR[AI]RIE-PSAI,PR[AI]RIE-PSAI - Paris School of Artificial Intelligence(2023), ANR-22-EXOD-0006,AS2,Robot motion with physical interactions and social adaptation(2022), European Project: 101070165,HORIZON-CL4-2021-DIGITAL-EMERGING-01,HORIZON-CL4-2021-DIGITAL-EMERGING-01,AGIMUS(2022)
Publisher Information:
CCSD, 2025.
Publication Year:
2025
Collection:
collection:ENS-PARIS
collection:CNRS
collection:INRIA
collection:INRIA-ROCQ
collection:TESTALAIN1
collection:INRIA2
collection:PSL
collection:INRIA-PSL
collection:IP_PARIS
collection:ENS-PSL
collection:ANR
collection:AGIMUS
collection:DIENS
collection:PEPR_O2R
collection:ANR-IA-23
collection:ANR-IA
collection:AS2
collection:ENSTA
Subject Terms:
[INFO.INFO-SY]Computer Science [cs], Systems and Control [cs.SY], [INFO.INFO-RB]Computer Science [cs], Robotics [cs.RO], [STAT.ML]Statistics [stat], Machine Learning [stat.ML]
Original Identifier:
HAL: hal-05184030
Document Type:
E-Ressource preprint<br />Preprints<br />Working Papers
Language:
English
Relation:
info:eu-repo/grantAgreement//101070165/EU/Next generation of AI-powered robotics for agile production/AGIMUS
Access URL:
https://inria.hal.science/hal-05184030
https://inria.hal.science/hal-05184030v1/document
https://inria.hal.science/hal-05184030v1/file/KernelSOS_for_Global_Sampling_Based_Optimal_Control_and_Estimation.pdf
Rights:
info:eu-repo/semantics/OpenAccess
URL: http://creativecommons.org/licenses/by/
Accession Number:
edshal.hal.05184030v1
Database:
HAL

Weitere Informationen

Global optimization has gained attraction over the past decades, thanks to the development of both theoretical foundations and efficient numerical routines to cope with optimization problems of various complexities. Among recent methods, Kernel Sum of Squares (KernelSOS) appears as a powerful framework, leveraging the potential of sum of squares methods from the polynomial optimization community with the expressivity of kernel methods widely used in machine learning. This paper applies the kernel sum of squares framework for solving control and estimation problems, which exhibit poor local minima. We demonstrate that KernelSOS performs well on a selection of problems from both domains. In particular, we show that KernelSOS is competitive with other sum of squares approaches on estimation problems, while being applicable to non-polynomial and non-parametric formulations. The samplebased nature of KernelSOS allows us to apply it to trajectory optimization problems with an integrated simulator treated as a black box, both as a standalone method and as a powerful initialization method for local solvers, facilitating the discovery of better solutions.