Reinforcement Learning of Bipedal Walking Using a Simple Reference Motion
Applied Sciences · 22.02.2024 · 14 (5) · 1803
DOI: 10.3390/app14051803 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 22.02.2024. Verfasst von Naoya Itahashi und 3 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: JSPS KAKENHI.
Abstract (Originalsprache)
In this paper, a novel reinforcement learning method that enables a humanoid robot to learn bipedal walking using a simple reference motion is proposed. Reinforcement learning has recently emerged as a useful method for robots to learn bipedal walking, but, in many studies, a reference motion is necessary for successful learning, and it is laborious or costly to prepare a reference motion. To overcome this problem, our proposed method uses a simple reference motion consisting of three sine waves and automatically sets the waveform parameters using Bayesian optimization. Thus, the reference motion can easily be prepared with minimal human involvement. Moreover, we introduce two means to facilitate reinforcement learning: (1) we combine reinforcement learning with inverse kinematics (IK), and (2) we use the reference motion as a bias for the action determined via reinforcement learning, rather than as an imitation target. Through numerical experiments, we show that our proposed method enables bipedal walking to be learned based on a small number of samples. Furthermore, we conduct a zero-shot sim-to-real transfer experiment using a domain randomization method and demonstrate that a real humanoid robot, KHR-3HV, can walk with the controller acquired using the proposed method.
Förderung
- JSPS KAKENHI
Zitieren
APA
Itahashi, N., Itoh, H., Fukumoto, H., & Wakuya, H. (2024). Reinforcement Learning of Bipedal Walking Using a Simple Reference Motion. Applied Sciences, 14(5), 1803. https://doi.org/10.3390/app14051803
Vancouver
Itahashi N, Itoh H, Fukumoto H, Wakuya H. Reinforcement Learning of Bipedal Walking Using a Simple Reference Motion. Applied Sciences. 2024;14(5):1803. doi:10.3390/app14051803
BibTeX
@article{Itahashi2024,
author = {Itahashi, Naoya and Itoh, Hideaki and Fukumoto, Hisao and Wakuya, Hiroshi},
title = {Reinforcement Learning of Bipedal Walking Using a Simple Reference Motion},
journal = {Applied Sciences},
year = {2024},
volume = {14},
number = {5},
pages = {1803},
doi = {10.3390/app14051803}
}
EUVIMED