AIConfPaper
← Search

Hiroki Mori

16 accepted papers

2024

Augmenting Compliance With Motion Generation Through Imitation Learning Using Drop-Stitch Reinforced Inflatable Robot Arm With Rigid Joints

Gangadhara Naga Sai Gubbala, Masato Nagashima, Hiroki Mori, Young Ah Seong, Hiroki Sato, Ryuma Niiyama +2
RA-L 2024

Safe physical human-robot collaboration is possible with soft robots due to their inherent compliance and low inertia. Soft bodies inherently possess passive compliance, providing adaptability in collaborative tasks because of their deformations; however, the same features add complexity to modeling

Cited by 7Source ↗Scholar ↗
2023

Modality Attention for Prediction-Based Robot Motion Generation: Improving Interpretability and Robustness of Using Multi-Modality

Hideyuki Ichiwara, Hiroshi Ito, Kenjiro Yamamoto, Hiroki Mori, Tetsuya Ogata
RA-L 2023

We developed a modality attention motion generation model on the basis of multi-modality prediction. This model provides interpretability about modality usage and demonstrates robustness against disturbances. We used a hierarchical model consisting of low-level recurrent neural networks (RNNs) for p

Cited by 8Source ↗Scholar ↗
2023

Multimodal Time Series Learning of Robots Based on Distributed and Integrated Modalities: Verification with a Simulator and Actual Robots

Hideyuki Ichiwara, Hiroshi Ito, Kenjiro Yamamoto, Hiroki Mori, Tetsuya Ogata
ICRA 2023poster

We have developed an autonomous robot motion generation model based on distributed and integrated multimodal learning. Since each modality used as a robot's senses, such as image, joint angle, and torque, has a different physical meaning and time characteristic, the generation of autonomous motions…

Cited by 8Source ↗Scholar ↗
2023

Visual Spatial Attention and Proprioceptive Data-Driven Reinforcement Learning for Robust Peg-in-Hole Task Under Variable Conditions

André Yuji Yasutomi, Hideyuki Ichiwara, Hiroshi Ito, Hiroki Mori, Tetsuya Ogata
RA-L 2023

Anchor-bolt insertion is a peg-in-hole task performed in the construction field for holes in concrete. Efforts have been made to automate this task, but the variable lighting and hole surface conditions, as well as the requirements for short setup and task execution time make the automation challeng

Cited by 31Source ↗Scholar ↗
2022

Contact-Rich Manipulation of a Flexible Object based on Deep Predictive Learning using Vision and Tactility

Hideyuki Ichiwara, Hiroshi Ito, Kenjiro Yamamoto, Hiroki Mori, Tetsuya Ogata
ICRA 2022poster

We achieved contact-rich flexible object manipulation, which was difficult to control with vision alone. In the unzipping task we chose as a validation task, the gripper grasps the puller, which hides the bag state such as the direction and amount of deformation behind it, making it difficult to obt…

Cited by 31Source ↗Scholar ↗
2022

Deep Active Visual Attention for Real-Time Robot Motion Generation: Emergence of Tool-Body Assimilation and Adaptive Tool-Use

Hyogo Hiruma, Hiroshi Ito, Hiroki Mori, Tetsuya Ogata
RA-L 2022

Sufficiently perceiving the environment is a critical factor in robot motion generation. Although the introduction of deep visual processing models have contributed in extending this ability, existing methods lack in the ability to actively modify what to perceive; humans perform internally during v

Cited by 13Source ↗Scholar ↗
2022

Integrated Learning of Robot Motion and Sentences: Real-Time Prediction of Grasping Motion and Attention based on Language Instructions

Hiroshi Ito, Hideyuki Ichiwara, Kenjiro Yamamoto, Hiroki Mori, Tetsuya Ogata
ICRA 2022poster

We propose a motion generation model that can achieve robust behavior against environmental changes based on language instructions at a low cost. Conventional robots that communicate with humans use a restricted environment and language to build up a mapping between language and motion, and thus nee…

Cited by 13Source ↗Scholar ↗
2021

Compensation for Undefined Behaviors During Robot Task Execution by Switching Controllers Depending on Embedded Dynamics in RNN

Kanata Suzuki, Hiroki Mori, Tetsuya Ogata
RA-L 2021

Robotic applications require both correct task performance and compensation for undefined behaviors. Although deep learning is a promising approach to perform complex tasks, the response to undefined behaviors that are not reflected in the training dataset remains challenging. In a human-robot colla

Cited by 16Source ↗Scholar ↗
2021

Embodying Pre-Trained Word Embeddings Through Robot Actions

Minori Toyoda, Kanata Suzuki, Hiroki Mori, Yoshihiko Hayashi, Tetsuya Ogata
RA-L 2021

We propose a promising neural network model with which to acquire a grounded representation of robot actions and the linguistic descriptions thereof. Properly responding to various linguistic expressions, including polysemous words, is an important ability for robots that interact with people via li

Cited by 14Source ↗Scholar ↗
2021

How to Select and Use Tools? : Active Perception of Target Objects Using Multimodal Deep Learning

Namiko Saito, Tetsuya Ogata, Satoshi Funabashi, Hiroki Mori, Shigeki Sugano
RA-L 2021

Selection of appropriate tools and use of them when performing daily tasks is a critical function for introducing robots for domestic applications. In previous studies, however, adaptability to target objects was limited, making it difficult to accordingly change tools and adjust actions. To manipul

Cited by 51Source ↗Scholar ↗
2021

In-air Knotting of Rope using Dual-Arm Robot based on Deep Learning

Kanata Suzuki, Momomi Kanamura, Yuki Suga, Hiroki Mori, Tetsuya Ogata
IROS 2021poster

In this study, we report the successful execution of in-air knotting of rope using a dual-arm two-finger robot based on deep learning. Owing to its flexibility, the state of the rope was in constant flux during the operation of the robot. This required the robot control system to dynamically corresp…

Cited by 32Source ↗Scholar ↗
2020

Wiping 3D-objects using Deep Learning Model based on Image/Force/Joint Information

Namiko Saito, Danyang Wang, Tetsuya Ogata, Hiroki Mori, Shigeki Sugano
IROS 2020poster

We propose a deep learning model for a robot to wipe 3D-objects. Wiping of 3D-objects requires recognizing the shapes of objects and planning the motor angle adjustments for tracing the objects. Unlike previous research, our learning model does not require pre-designed computational models of target…

Cited by 16Source ↗Scholar ↗
2019

Learning Multiple Sensorimotor Units to Complete Compound Tasks using an RNN with Multiple Attractors

Kei Kase, Ryoichi Nakajo, Hiroki Mori, Tetsuya Ogata
IROS 2019poster

As the complexity of the robot's tasks increases, we can consider many general tasks in a compound form that consists of shorter tasks. Therefore, for robots to generate various tasks, they need to be able to execute shorter tasks in succession, appropriately to the situation. With the design princi…

Cited by 12Source ↗Scholar ↗
2018

Motion Switching With Sensory and Instruction Signals by Designing Dynamical Systems Using Deep Neural Network

Kanata Suzuki, Hiroki Mori, Tetsuya Ogata
RA-L 2018

To ensure that a robot is able to accomplish an extensive range of tasks, it is necessary to achieve a flexible combination of multiple behaviors. This is because the design of task motions suited to each situation would become increasingly difficult as the number of situations and the types of task

Cited by 20Source ↗Scholar ↗
2018

Put-in-Box Task Generated from Multiple Discrete Tasks by aHumanoid Robot Using Deep Learning

Kei Kase, Kanata Suzuki, Pin-Chu Yang, Hiroki Mori, Tetsuya Ogata
ICRA 2018poster

For robots to have a wide range of applications, they must be able to execute numerous tasks. However, recent studies into robot manipulation using deep neural networks (DNN) have primarily focused on single tasks. Therefore, we investigate a robot manipulation model that uses DNNs and can execute l…

Cited by 41Source ↗Scholar ↗