Infinite-Horizon Value Function Approximation for Model Predictive Control
Uložené v:
| Názov: | Infinite-Horizon Value Function Approximation for Model Predictive Control |
|---|---|
| Autori: | Armand Jordana, Sébastien Kleff, Arthur Haffemayer, Joaquim Ortiz-Haro, Justin Carpentier, Nicolas Mansard, Ludovic Righetti |
| Prispievatelia: | Carpentier, Justin |
| Zdroj: | IEEE Robotics and Automation Letters. 10:7563-7570 |
| Publication Status: | Preprint |
| Informácie o vydavateľovi: | Institute of Electrical and Electronics Engineers (IEEE), 2025. |
| Rok vydania: | 2025 |
| Predmety: | FOS: Computer and information sciences, Computer Science - Robotics, [INFO.INFO-RB] Computer Science [cs]/Robotics [cs.RO], Robotics (cs.RO) |
| Popis: | 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. |
| Druh dokumentu: | Article |
| Popis súboru: | application/pdf |
| ISSN: | 2377-3774 |
| DOI: | 10.1109/lra.2025.3577875 |
| DOI: | 10.48550/arxiv.2502.06760 |
| Prístupová URL adresa: | http://arxiv.org/abs/2502.06760 https://laas.hal.science/hal-04948407v1/document https://laas.hal.science/hal-04948407v1 https://doi.org/10.48550/arxiv.2502.06760 |
| Rights: | IEEE Copyright CC BY |
| Prístupové číslo: | edsair.doi.dedup.....de525b97693c09d3fcfdb12c4125c47b |
| Databáza: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstrakt: | 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. |
|---|---|
| ISSN: | 23773774 |
| DOI: | 10.1109/lra.2025.3577875 |