Safe Robot Navigation Using Constrained Hierarchical Reinforcement Learning

Felippe Schmoeller Roza, Hassan Rasheed, Karsten Roscher, Xiangyu Ning, Stephan Günnemann

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

Abstract

Safe navigation is one of the steps necessary for achieving autonomous control of robots. Among different algorithms that focus on robot navigation, Reinforcement Learning (and more specifically Deep Reinforcement Learning) has shown impressive results for controlling robots with complex and high-dimensional state representations. However, when integrating methods to comply with safety requirements by means of constraint satisfaction in flat Reinforcement Learning policies, the system performance can be affected. In this paper, we propose a constrained Hierarchical Reinforcement Learning framework with a safety layer used to modify the low-level policy to achieve a safer operation of the robot. Results obtained in simulation show that the proposed method is better at retaining performance while keeping the system in a safe region when compared to a constrained flat model.

OriginalspracheEnglisch
TitelProceedings - 21st IEEE International Conference on Machine Learning and Applications, ICMLA 2022
Redakteure/-innenM. Arif Wani, Mehmed Kantardzic, Vasile Palade, Daniel Neagu, Longzhi Yang, Kit-Yan Chan
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers Inc.
Seiten737-742
Seitenumfang6
ISBN (elektronisch)9781665462839
DOIs
PublikationsstatusVeröffentlicht - 2022
Veranstaltung21st IEEE International Conference on Machine Learning and Applications, ICMLA 2022 - Nassau, Bahamas
Dauer: 12 Dez. 202214 Dez. 2022

Publikationsreihe

NameProceedings - 21st IEEE International Conference on Machine Learning and Applications, ICMLA 2022

Konferenz

Konferenz21st IEEE International Conference on Machine Learning and Applications, ICMLA 2022
Land/GebietBahamas
OrtNassau
Zeitraum12/12/2214/12/22

Fingerprint

Untersuchen Sie die Forschungsthemen von „Safe Robot Navigation Using Constrained Hierarchical Reinforcement Learning“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren