Learning to exploit passive compliance for energy-efficient gait generation on a compliant humanoid

Name: Learning to exploit passive compliance for energy-efficient gait generation on a compliant humanoid
Author: Kormushev, P., Uğurlu, Regaip Barkan, Caldwell, D. G., Tsagarakis, N. G.

İsim	Learning to exploit passive compliance for energy-efficient gait generation on a compliant humanoid
Yazar	Kormushev, P., Uğurlu, Regaip Barkan, Caldwell, D. G., Tsagarakis, N. G.
Basım Tarihi:	2019-01
Basım Yeri	- Springer Nature
Konu	Bipedal walking, Energy efficiency, Reinforcement learning, Passive compliance
Tür	Süreli Yayın
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	0929-5593
Kayıt Numarası	a0ae91cf-57bb-4ed3-9446-ee83c9e30625
Lokasyon	Mechanical Engineering
Tarih	2019-01
Notlar	EU project AMARSi
Örnek Metin	Modern humanoid robots include not only active compliance but also passive compliance. Apart from improved safety and dependability, availability of passive elements, such as springs, opens up new possibilities for improving the energy efficiency. With this in mind, this paper addresses the challenging open problem of exploiting the passive compliance for the purpose of energy efficient humanoid walking. To this end, we develop a method comprising two parts: an optimization part that finds an optimal vertical center-of-mass trajectory, and a walking pattern generator part that uses this trajectory to produce a dynamically-balanced gait. For the optimization part, we propose a reinforcement learning approach that dynamically evolves the policy parametrization during the learning process. By gradually increasing the representational power of the policy parametrization, it manages to find better policies in a faster and computationally efficient way. For the walking generator part, we develop a variable-center-of-mass-height ZMP-based bipedal walking pattern generator. The method is tested in real-world experiments with the bipedal robot COMAN and achieves a significant 18% reduction in the electric energy consumption by learning to efficiently use the passive compliance of the robot.
DOI	10.1007/s10514-018-9697-6
Cilt	43

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Learning to exploit passive compliance for energy-efficient gait generation on a compliant humanoid

Yazar Kormushev, P., Uğurlu, Regaip Barkan, Caldwell, D. G., Tsagarakis, N. G.

Basım Tarihi 2019-01

Basım Yeri - Springer Nature

Konu Bipedal walking, Energy efficiency, Reinforcement learning, Passive compliance

Tür Süreli Yayın

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 0929-5593

Kayıt Numarası a0ae91cf-57bb-4ed3-9446-ee83c9e30625

Lokasyon Mechanical Engineering

Tarih 2019-01

Notlar EU project AMARSi

Örnek Metin Modern humanoid robots include not only active compliance but also passive compliance. Apart from improved safety and dependability, availability of passive elements, such as springs, opens up new possibilities for improving the energy efficiency. With this in mind, this paper addresses the challenging open problem of exploiting the passive compliance for the purpose of energy efficient humanoid walking. To this end, we develop a method comprising two parts: an optimization part that finds an optimal vertical center-of-mass trajectory, and a walking pattern generator part that uses this trajectory to produce a dynamically-balanced gait. For the optimization part, we propose a reinforcement learning approach that dynamically evolves the policy parametrization during the learning process. By gradually increasing the representational power of the policy parametrization, it manages to find better policies in a faster and computationally efficient way. For the walking generator part, we develop a variable-center-of-mass-height ZMP-based bipedal walking pattern generator. The method is tested in real-world experiments with the bipedal robot COMAN and achieves a significant 18% reduction in the electric energy consumption by learning to efficiently use the passive compliance of the robot.

DOI 10.1007/s10514-018-9697-6

Cilt 43