Výsledky vyhledávání - "Hiraoka, Naoki"

Report

Estimation and Control of Motor Core Temperature with Online Learning of Thermal Model Parameters: Application to Musculoskeletal Humanoids

Autor: Kawaharazuka, Kento, Hiraoka, Naoki, Tsuzuki, Kei, Onitsuka, Moritaka, Asano, Yuki, Okada, Kei, Kawasaki, Koji, Inaba, Masayuki

The estimation and management of motor temperature are important for the continuous movements of robots. In this study, we propose an online learning method of thermal model parameters of motors for an accurate estimation of motor core temperature. A

Externí odkaz: http://arxiv.org/abs/2407.08055

Zobrazit plný text záznamu

Report

CoverLib: Classifiers-equipped Experience Library by Iterative Problem Distribution Coverage Maximization for Domain-tuned Motion Planning

Autor: Ishida, Hirokazu, Hiraoka, Naoki, Okada, Kei, Inaba, Masayuki

Library-based methods are known to be very effective for fast motion planning by adapting an experience retrieved from a precomputed library. This article presents CoverLib, a principled approach for constructing and utilizing such a library. CoverLi

Externí odkaz: http://arxiv.org/abs/2405.02968

Zobrazit plný text záznamu

Report

Development of a Whole-body Work Imitation Learning System by a Biped and Bi-armed Humanoid

Autor: Matsuura, Yutaro, Kawaharazuka, Kento, Hiraoka, Naoki, Kojima, Kunio, Okada, Kei, Inaba, Masayuki

Imitation learning has been actively studied in recent years. In particular, skill acquisition by a robot with a fixed body, whose root link position and posture and camera angle of view do not change, has been realized in many cases. On the other ha

Externí odkaz: http://arxiv.org/abs/2309.15756

Zobrazit plný text záznamu

Report

HumanMimic: Learning Natural Locomotion and Transitions for Humanoid Robot via Wasserstein Adversarial Imitation

Autor: Tang, Annan, Hiraoka, Takuma, Hiraoka, Naoki, Shi, Fan, Kawaharazuka, Kento, Kojima, Kunio, Okada, Kei, Inaba, Masayuki

Transferring human motion skills to humanoid robots remains a significant challenge. In this study, we introduce a Wasserstein adversarial imitation learning system, allowing humanoid robots to replicate natural whole-body locomotion patterns and exe

Externí odkaz: http://arxiv.org/abs/2309.14225

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Akademický článek

Online generation and control of quasi-static multi-contact motion by PWT Jacobian matrix with contact wrench estimation and joint load reduction*.

Autor: Hiraoka, Naoki¹ (AUTHOR) hiraoka@jsk.imi.i.u-tokyo.ac.jp, Murooka, Masaki¹ (AUTHOR), Noda, Shintaro¹ (AUTHOR), Okada, Kei¹ (AUTHOR), Inaba, Masayuki¹ (AUTHOR)

Publikováno v: Advanced Robotics. Jan2021, Vol. 35 Issue 1, p48-63. 16p.