Learning Robot-Environment Interaction Using Echo State Networks

Autor:	Mohamed Oubbati, Günther Palm, Bahram Kord
Rok vydání:	2010
Předmět:	Computer science business.industry Robot environment Echo (computing) Mobile robot Robot learning Recurrent neural network Human–computer interaction Robot Computer vision State (computer science) Artificial intelligence Echo state network business
Zdroj:	From Animals to Animats 11 ISBN: 9783642151927 SAB
Popis:	Learning robot-environment interaction with echo state networks (ESNs) is presented in this paper. ESNs are asked to bootstrap a robot's control policy from human teacher's demonstrations on the robot learner, and to generalize beyond the demonstration dataset. Benefits and problems involved in some navigation tasks are discussed, supported by real-world experiments with a small mobile robot.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::bc87e6f5af035fff0603ac43288a8149 https://doi.org/10.1007/978-3-642-15193-4_47 Zobrazit plný text záznamu