Lernende Generalisierte Fähigkeiten zur Symbolischen Planung für Autonome Vorrichtungen

Details

Veröffentlichungs-Nr.

EP4318327

Aktenzeichen

EP23155823

Anmeldetag

9. Februar 2023

Veröffentlichung

28. Mai 2025

Erteilung

28. Mai 2025

Rechtsraum

EP

IPC

G06N5/022G06N20/00

Abstract

The present disclosure relates to a computer-implemented method for learning operators for planning a behavior of an autonomous device. The method comprises obtaining a set of training data D including observations of a plurality of skills executable by the autonomous device in an interaction with at least one entity for addressing a first task. The method further includes obtaining a predetermined set of data defining a hierarchy of entities including the at least one entity. The method proceeds by learning a set of individual skills based on the obtained set of training data D, generating a set of generalized skills by generalizing the learned set of individual skills based on the predetermined set of data that defining a hierarchy of entities. The method then performs behavior planning of the autonomous device for addressing a second task different from the first task based on the generalized set of skills. The method may perform behavior planning of the autonomous device for addressing the second task different from the first task based on the generalized set of skills and, potentially, based on further imagined skills added during planning and execution of the second task.

Anmelder

Firmen

HONDA MOTOR CO., LTD.
Honda Motor Co., Ltd.
Honda Research Institute Europe GmbH

Land

🇯🇵 Japan

Fachgebiete