Zobrazeno 1 - 10
of 533
pro vyhledávání: '"Okada, Masashi"'
In this paper, a novel approach is proposed for learning robot control in contact-rich tasks such as wiping, by developing Diffusion Contact Model (DCM). Previous methods of learning such tasks relied on impedance control with time-varying stiffness
Externí odkaz:
http://arxiv.org/abs/2403.13221
Publikováno v:
IEEE Open Journal of Signal Processing, vol. 5, pp. 831-840, 2024
In this paper, we propose a new self-supervised learning (SSL) method for representations that enable logic operations. Representation learning has been applied to various tasks, such as image generation and retrieval. The logical controllability of
Externí odkaz:
http://arxiv.org/abs/2309.04148
Rather than traditional position control, impedance control is preferred to ensure the safe operation of industrial robots programmed from demonstrations. However, variable stiffness learning studies have focused on task performance rather than safet
Externí odkaz:
http://arxiv.org/abs/2307.15345
This study explores the problem of Multi-Agent Path Finding with continuous and stochastic travel times whose probability distribution is unknown. Our purpose is to manage a group of automated robots that provide package delivery services in a buildi
Externí odkaz:
http://arxiv.org/abs/2302.01489
In this study, a novel self-supervised learning (SSL) method is proposed, which considers SSL in terms of variational inference to learn not only representation but also representation uncertainties. SSL is a method of learning representations withou
Externí odkaz:
http://arxiv.org/abs/2203.11437
In this paper, we propose Multi-View Dreaming, a novel reinforcement learning agent for integrated recognition and control from multi-view observations by extending Dreaming. Most current reinforcement learning method assumes a single-view observatio
Externí odkaz:
http://arxiv.org/abs/2203.11024
Autor:
Okada, Masashi, Taniguchi, Tadahiro
The present paper proposes a novel reinforcement learning method with world models, DreamingV2, a collaborative extension of DreamerV2 and Dreaming. DreamerV2 is a cutting-edge model-based reinforcement learning from pixels that uses discrete world m
Externí odkaz:
http://arxiv.org/abs/2203.00494
Autor:
Orlov, Anton, Jägermeyr, Jonas, Müller, Christoph, Daloz, Anne Sophie, Zabel, Florian, Minoli, Sara, Liu, Wenfeng, Lin, Tzu-Shun, Jain, Atul K., Folberth, Christian, Okada, Masashi, Poschlod, Benjamin, Smerald, Andrew, Schneider, Julia M., Sillmann, Jana
Publikováno v:
In One Earth 19 July 2024 7(7):1250-1265
Annual recruitment data of new graduates are manually analyzed by human resources specialists (HR) in industries, which signifies the need to evaluate the recruitment strategy of HR specialists. Every year, different applicants send in job applicatio
Externí odkaz:
http://arxiv.org/abs/2008.10039
Autor:
Okada, Masashi, Taniguchi, Tadahiro
In the present paper, we propose a decoder-free extension of Dreamer, a leading model-based reinforcement learning (MBRL) method from pixels. Dreamer is a sample- and cost-efficient solution to robot learning, as it is used to train latent state-spac
Externí odkaz:
http://arxiv.org/abs/2007.14535