Výsledky vyhledávání - "Mariyama, Toshisada"

Akademický článek

On Robust Assembly of Flexible Flat Cables Combining CAD and Image Based Multiview Pose Estimation and a Multimodal Robotic Gripper

Autor: Junbang Liang, Joao Buzzatto, Bryan Busby, Haodan Jiang, Saori Matsunaga, Rintaro Haraguchi, Mariyama Toshisada, Bruce A. MacDonald, Minas Liarokapis

Publikováno v: IEEE Open Journal of the Industrial Electronics Society, Vol 5, Pp 1104-1114 (2024)

In robotic assembly of flexible flat cables (FFCs), a unique challenge is the inherent difficulty in manipulating such flexible objects compared to their rigid counterparts and the precise estimation of the cable pose. This work proposes a framework

Externí odkaz: https://doaj.org/article/78d608ce99e74b8cb3acd3a94967d2c6

Zobrazit plný text záznamu

Report

Stability-Certified Reinforcement Learning via Spectral Normalization

Autor: Takase, Ryoichi, Yoshikawa, Nobuyuki, Mariyama, Toshisada, Tsuchiya, Takeshi

In this article, two types of methods from different perspectives based on spectral normalization are described for ensuring the stability of the system controlled by a neural network. The first one is that the L2 gain of the feedback system is bound

Externí odkaz: http://arxiv.org/abs/2012.13744

Zobrazit plný text záznamu

Report

Deep Reactive Planning in Dynamic Environments

Autor: Ota, Kei, Jha, Devesh K., Onishi, Tadashi, Kanezaki, Asako, Yoshiyasu, Yusuke, Sasaki, Yoko, Mariyama, Toshisada, Nikovski, Daniel

The main novelty of the proposed approach is that it allows a robot to learn an end-to-end policy which can adapt to changes in the environment during execution. While goal conditioning of policies has been studied in the RL literature, such approach

Externí odkaz: http://arxiv.org/abs/2011.00155

Zobrazit plný text záznamu

Report

Can Increasing Input Dimensionality Improve Deep Reinforcement Learning?

Autor: Ota, Kei, Oiki, Tomoaki, Jha, Devesh K., Mariyama, Toshisada, Nikovski, Daniel

Deep reinforcement learning (RL) algorithms have recently achieved remarkable successes in various sequential decision making tasks, leveraging advances in methods for training large deep networks. However, these methods usually require large amounts

Externí odkaz: http://arxiv.org/abs/2003.01629

Zobrazit plný text záznamu

Report

Trajectory Optimization for Unknown Constrained Systems using Reinforcement Learning

Autor: Ota, Kei, Jha, Devesh K., Oiki, Tomoaki, Miura, Mamoru, Nammoto, Takashi, Nikovski, Daniel, Mariyama, Toshisada

In this paper, we propose a reinforcement learning-based algorithm for trajectory optimization for constrained dynamical systems. This problem is motivated by the fact that for most robotic systems, the dynamics may not always be known. Generating sm

Externí odkaz: http://arxiv.org/abs/1903.05751

Zobrazit plný text záznamu