| Title: |
Infinite-Horizon Value Function Approximation for Model Predictive Control |
| Authors: |
Jordana, Armand; Kleff, Sébastien; Haffemayer, Arthur; Ortiz-Haro, Joaquim; Carpentier, Justin; Mansard, Nicolas; Righetti, Ludovic |
| Contributors: |
Machines in Motion Laboratory New York University (MiM); New York University New York (NYU); NYU System (NYU)-NYU System (NYU); NYU System (NYU); Continental Automotive France Toulouse; Équipe Mouvement des Systèmes Anthropomorphes (LAAS-GEPETTO); Laboratoire d'analyse et d'architecture des systèmes (LAAS); Université Toulouse Capitole (UT Capitole); Communauté d'universités et établissements de Toulouse (Comue de Toulouse)-Communauté d'universités et établissements de Toulouse (Comue de Toulouse)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse); Institut National des Sciences Appliquées (INSA)-Communauté d'universités et établissements de Toulouse (Comue de Toulouse)-Institut National des Sciences Appliquées (INSA)-Communauté d'universités et établissements de Toulouse (Comue de Toulouse)-Université Toulouse - Jean Jaurès (UT2J); Communauté d'universités et établissements de Toulouse (Comue de Toulouse)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP); Communauté d'universités et établissements de Toulouse (Comue de Toulouse)-Université de Toulouse (EPE UT); Communauté d'universités et établissements de Toulouse (Comue de Toulouse)-Université Toulouse Capitole (UT Capitole); Communauté d'universités et établissements de Toulouse (Comue de Toulouse); Models of visual object recognition and scene understanding (WILLOW); 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)-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); 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); This work was in part supported by the National Science Foundation grants 1932187, 2026479, 2222815 and 2315396 and ANITI (ANR 19-P3IA-0004). This work was supported by a grant overseen by the French National Research Agency (ANR) and France 2030 as part of the PR AI RIE-PSAI AI cluster (ANR-23-IACL-0008), by the French government underthe management of Agence Nationale de la Recherche through the project NIMBLE (ANR-22-CE33-0008), and by the European Union through the AGIMUS project (GA no.101070165).; ANR-22-CE33-0008,NIMBLE,Apprentissage et contrôle de modèles sensori-moteurs en robotique(2022); ANR-19-P3IA-0001,PRAIRIE,PaRis Artificial Intelligence Research InstitutE(2019); ANR-23-IACL-0008,PR AI RIE-PSAI,PR AI RIE-PSAI - Paris School of Artificial Intelligence(2023); ANR-19-P3IA-0004,ANITI,Artificial and Natural Intelligence Toulouse Institute(2019); European Project: 101070165,HORIZON-CL4-2021-DIGITAL-EMERGING-01,HORIZON-CL4-2021-DIGITAL-EMERGING-01,AGIMUS(2022) |
| Source: |
ISSN: 2377-3766 ; IEEE Robotics and Automation Letters ; https://laas.hal.science/hal-04948407 ; IEEE Robotics and Automation Letters, 2025, 10 (7), pp.7563 - 7570. ⟨10.1109/LRA.2025.3577875⟩. |
| Publisher Information: |
CCSD; IEEE |
| Publication Year: |
2025 |
| Collection: |
Université Toulouse III - Paul Sabatier: HAL-UPS |
| Subject Terms: |
Robotics (cs.RO); FOS: Computer and information sciences; [INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO] |
| Description: |
International audience ; Model Predictive Control has emerged as a popular tool for robots to generate complex motions. However, the real-time requirement has limited the use of hard constraints and large preview horizons, which are necessary to ensure safety and stability. In practice, practitioners have to carefully design cost functions that can imitate an infinite horizon formulation, which is tedious and often results in local minima. In this work, we study how to approximate the infinite horizon value function of constrained optimal control problems with neural networks using value iteration and trajectory optimization. Furthermore, we demonstrate how using this value function approximation as a terminal cost provides global stability to the model predictive controller. The approach is validated on two toy problems and a real-world scenario with online obstacle avoidance on an industrial manipulator where the value function is conditioned to the goal and obstacle. |
| Document Type: |
article in journal/newspaper |
| Language: |
English |
| Relation: |
info:eu-repo/semantics/altIdentifier/arxiv/2502.06760; info:eu-repo/grantAgreement//101070165/EU/Next generation of AI-powered robotics for agile production/AGIMUS; ARXIV: 2502.06760 |
| DOI: |
10.1109/LRA.2025.3577875 |
| Availability: |
https://laas.hal.science/hal-04948407; https://laas.hal.science/hal-04948407v1/document; https://laas.hal.science/hal-04948407v1/file/RAL%20-%20Infinite-Horizon%20Value%20Function%20Approximation%20for%20Model%20Predictive%20Control.pdf; https://doi.org/10.1109/LRA.2025.3577875 |
| Rights: |
https://creativecommons.org/licenses/by/4.0/ ; info:eu-repo/semantics/OpenAccess |
| Accession Number: |
edsbas.58711609 |
| Database: |
BASE |