Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Rui, Shi, Guangyao, Tokekar, Pratap
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2303.02293
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918152596619264
author Liu, Rui
Shi, Guangyao
Tokekar, Pratap
author_facet Liu, Rui
Shi, Guangyao
Tokekar, Pratap
contents Distributionally Robust Optimal Control (DROC) is a framework that enables robust control in a stochastic setting where the true disturbance distribution is unknown. Traditional DROC approaches require given ambiguity sets and KL divergence bounds to represent the distributional uncertainty; however, these quantities are often unavailable a priori or require manual specification. To overcome this limitation, we propose a data-driven approach that jointly estimates the uncertainty distribution and the corresponding KL divergence bound, which we refer to as $\mathrm{D}^3\mathrm{ROC}$. To evaluate the effectiveness of our approach, we consider a car-like robot navigation task with unknown noise distributions. The experimental results show that $\mathrm{D}^3\mathrm{ROC}$ yields robust and effective control policies, outperforming iterative Linear Quadratic Gaussian (iLQG) control and demonstrating strong adaptability to varying noise distributions.
format Preprint
id arxiv_https___arxiv_org_abs_2303_02293
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Data-Driven Distributionally Robust Optimal Control with State-Dependent Noise
Liu, Rui
Shi, Guangyao
Tokekar, Pratap
Robotics
Distributionally Robust Optimal Control (DROC) is a framework that enables robust control in a stochastic setting where the true disturbance distribution is unknown. Traditional DROC approaches require given ambiguity sets and KL divergence bounds to represent the distributional uncertainty; however, these quantities are often unavailable a priori or require manual specification. To overcome this limitation, we propose a data-driven approach that jointly estimates the uncertainty distribution and the corresponding KL divergence bound, which we refer to as $\mathrm{D}^3\mathrm{ROC}$. To evaluate the effectiveness of our approach, we consider a car-like robot navigation task with unknown noise distributions. The experimental results show that $\mathrm{D}^3\mathrm{ROC}$ yields robust and effective control policies, outperforming iterative Linear Quadratic Gaussian (iLQG) control and demonstrating strong adaptability to varying noise distributions.
title Data-Driven Distributionally Robust Optimal Control with State-Dependent Noise
topic Robotics
url https://arxiv.org/abs/2303.02293