Saved in:
Bibliographic Details
Main Authors: Jordana, Armand, Kleff, Sébastien, Haffemayer, Arthur, Ortiz-Haro, Joaquim, Carpentier, Justin, Mansard, Nicolas, Righetti, Ludovic
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.06760
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917055947603968
author Jordana, Armand
Kleff, Sébastien
Haffemayer, Arthur
Ortiz-Haro, Joaquim
Carpentier, Justin
Mansard, Nicolas
Righetti, Ludovic
author_facet Jordana, Armand
Kleff, Sébastien
Haffemayer, Arthur
Ortiz-Haro, Joaquim
Carpentier, Justin
Mansard, Nicolas
Righetti, Ludovic
contents 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 experimentally 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_06760
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Infinite-Horizon Value Function Approximation for Model Predictive Control
Jordana, Armand
Kleff, Sébastien
Haffemayer, Arthur
Ortiz-Haro, Joaquim
Carpentier, Justin
Mansard, Nicolas
Righetti, Ludovic
Robotics
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 experimentally 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.
title Infinite-Horizon Value Function Approximation for Model Predictive Control
topic Robotics
url https://arxiv.org/abs/2502.06760