activity
20202023
most citedMulti-View Dreaming: Multi-View World Model with Contrastive Learning

3 citations · 6 across the 5 of their papers we have counts for

collaborators

6 papers

cs.RO2023★ 1 cited

World-Model-Based Control for Industrial box-packing of Multiple Objects using NewtonianVAE

Yusuke Kato, Ryo Okumura, Tadahiro Taniguchi

The process of industrial box-packing, which involves the accurate placement of multiple objects, requires high-accuracy positioning and sequential actions. When a robot is tasked…

cs.RO2023★ 1 cited

Learning Compliant Stiffness by Impedance Control-Aware Task Segmentation and Multi-objective Bayesian Optimization with Priors

Masashi Okada, Mayumi Komatsu, Ryo Okumura +1

Rather than traditional position control, impedance control is preferred to ensure the safe operation of industrial robots programmed from demonstrations. However, variable stiffne…

cs.CV2022★ 1 cited

Patch-based Object-centric Transformers for Efficient Video Generation

Wilson Yan, Ryo Okumura, Stephen James +1

In this work, we present Patch-based Object-centric Video Transformer (POVT), a novel region-based video generation architecture that leverages object-centric information to effici…

cs.AI2022★ 3 cited

Multi-View Dreaming: Multi-View World Model with Contrastive Learning

Akira Kinose, Masashi Okada, Ryo Okumura +1

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…

cs.RO2022

Tactile-Sensitive NewtonianVAE for High-Accuracy Industrial Connector Insertion

Ryo Okumura, Nobuki Nishio, Tadahiro Taniguchi

An industrial connector insertion task requires submillimeter positioning and grasp pose compensation for a plug. Thus, highly accurate estimation of the relative pose between a pl…

cs.LG2020

Domain-Adversarial and Conditional State Space Model for Imitation Learning

Ryo Okumura, Masashi Okada, Tadahiro Taniguchi

State representation learning (SRL) in partially observable Markov decision processes has been studied to learn abstract features of data useful for robot control tasks. For SRL, a…