A neural network architecture for learning a feedback controller from demonstration

Name: A neural network architecture for learning a feedback controller from demonstration
Author: Oztop, Erhan, Mehrabi, Arash

İsim	A neural network architecture for learning a feedback controller from demonstration
Yazar	Oztop, Erhan, Mehrabi, Arash
Basım Tarihi:	2024-01-01
Basım Yeri	- IEEE
Konu	Deep learning, Learning feedback controller, Robot trajectory, Neural networks, Learning from demonstration
Tür	Belge
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	979-8-3503-5932-9
Kayıt Numarası	e568c2fa-3a98-4005-aed4-be6ebed1cd7f
Lokasyon	Computer Science
Tarih	2024-01-01
Notlar	Japan Science and Technology Agency ; New Energy and Industrial Technology Development Organization ; Japan Society for the Promotion of Science ; Core Research for Evolutional Science and Technology
Örnek Metin	Learning from demonstration (LfD) is an effective way of generating robot behaviors by transferring human demonstrated movements to robots. One common method to accomplish LfD is 'Behavior Cloning' (BC) with human-in-the-loop control, where the data obtained by human teleoperation of the robot is used to construct a non-linear controller by learning the state-to-action mapping. In this study, we propose a novel BC system where the learning architecture parallels a feedback controller that is tasked with producing the demonstrated motor output data. The motivation behind this design is that encoding such structure in the learning mechanism is expected to endow our system with prior bias to outperform controller-agnostic BC systems, especially in resource scarce situations. The current report presents the developed novel BC model, and gives its implementation for a two degrees-of-freedom robotic system as a proof of concept. To evaluate the performance of the system, systematic experiments are run in comparison with a controller-agnostic BC system. The results show that the proposed model performs significantly better than the baseline, indicating that it is a strong candidate for LfD tasks when the demonstrated data can be assumed to be generated through a feedback controller.
DOI	10.1109/IJCNN60899.2024.10650889

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

A neural network architecture for learning a feedback controller from demonstration

Yazar Oztop, Erhan, Mehrabi, Arash

Basım Tarihi 2024-01-01

Basım Yeri - IEEE

Konu Deep learning, Learning feedback controller, Robot trajectory, Neural networks, Learning from demonstration

Tür Belge

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 979-8-3503-5932-9

Kayıt Numarası e568c2fa-3a98-4005-aed4-be6ebed1cd7f

Lokasyon Computer Science

Tarih 2024-01-01

Notlar Japan Science and Technology Agency ; New Energy and Industrial Technology Development Organization ; Japan Society for the Promotion of Science ; Core Research for Evolutional Science and Technology

Örnek Metin Learning from demonstration (LfD) is an effective way of generating robot behaviors by transferring human demonstrated movements to robots. One common method to accomplish LfD is 'Behavior Cloning' (BC) with human-in-the-loop control, where the data obtained by human teleoperation of the robot is used to construct a non-linear controller by learning the state-to-action mapping. In this study, we propose a novel BC system where the learning architecture parallels a feedback controller that is tasked with producing the demonstrated motor output data. The motivation behind this design is that encoding such structure in the learning mechanism is expected to endow our system with prior bias to outperform controller-agnostic BC systems, especially in resource scarce situations. The current report presents the developed novel BC model, and gives its implementation for a two degrees-of-freedom robotic system as a proof of concept. To evaluate the performance of the system, systematic experiments are run in comparison with a controller-agnostic BC system. The results show that the proposed model performs significantly better than the baseline, indicating that it is a strong candidate for LfD tasks when the demonstrated data can be assumed to be generated through a feedback controller.

DOI 10.1109/IJCNN60899.2024.10650889