Model Identification Adaptive Control with $ρ$-POMDP Planning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ho, Michelle, Jamgochian, Arec, Kochenderfer, Mykel J.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909620742651904
author Ho, Michelle
Jamgochian, Arec
Kochenderfer, Mykel J.
author_facet Ho, Michelle
Jamgochian, Arec
Kochenderfer, Mykel J.
contents Accurate system modeling is crucial for safe, effective control, as misidentification can lead to accumulated errors, especially under partial observability. We address this problem by formulating informative input design and model identification adaptive control (MIAC) as belief space planning problems, modeled as partially observable Markov decision processes with belief-dependent rewards ($ρ$-POMDPs). We treat system parameters as hidden state variables that must be localized while simultaneously controlling the system. We solve this problem with an adapted belief-space iterative Linear Quadratic Regulator (BiLQR). We demonstrate it on fully and partially observable tasks for cart-pole and steady aircraft flight domains. Our method outperforms baselines such as regression, filtering, and local optimal control methods, even under instantaneous disturbances to system parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2505_09119
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Model Identification Adaptive Control with $ρ$-POMDP Planning
Ho, Michelle
Jamgochian, Arec
Kochenderfer, Mykel J.
Robotics
Systems and Control
Accurate system modeling is crucial for safe, effective control, as misidentification can lead to accumulated errors, especially under partial observability. We address this problem by formulating informative input design and model identification adaptive control (MIAC) as belief space planning problems, modeled as partially observable Markov decision processes with belief-dependent rewards ($ρ$-POMDPs). We treat system parameters as hidden state variables that must be localized while simultaneously controlling the system. We solve this problem with an adapted belief-space iterative Linear Quadratic Regulator (BiLQR). We demonstrate it on fully and partially observable tasks for cart-pole and steady aircraft flight domains. Our method outperforms baselines such as regression, filtering, and local optimal control methods, even under instantaneous disturbances to system parameters.
title Model Identification Adaptive Control with $ρ$-POMDP Planning
topic Robotics
Systems and Control
url https://arxiv.org/abs/2505.09119