2025
4.
Hyun Jae Lee, Ryuma Niiyama
Bleeding-Mimetic Damage-Detecting and Self-Healing Modular Skin for Inflatable Structures Journal Article
In: Advanced Robotics Research, 2025.
Abstract | BibTeX | タグ: | Links:
@article{Lee2025,
title = {Bleeding-Mimetic Damage-Detecting and Self-Healing Modular Skin for Inflatable Structures},
author = {Hyun Jae Lee, Ryuma Niiyama},
doi = {10.1002/adrr.202500009},
year = {2025},
date = {2025-04-24},
urldate = {2025-04-24},
journal = {Advanced Robotics Research},
abstract = {The extension of the lifespan of soft robots necessitates the establishment of an effective self-healing system accompanied by rapid damage detection. Inspired by the mechanisms of bleeding and blood coagulation, a novel damage-detecting and self-healing modular skin is developed for inflatable structures. This alternative structural material is realized using a liquid conductive polymer composed of an elastomer, conductive particles, and a dispersant. Encapsulated in a thin layer, this conductive polymer is found to be capable of both damage detection through generating an electric current and subsequent self-healing through its solidification in the damaged area. The repeated and reproducible generation of electric current is confirmed both prior to and subsequent to the infliction of damage to the patch. A comparison of conductive polymers with distinct mixing ratios reveals that the changes in electric current following the solidification on the patches are different. The applicability of the modular skins is confirmed by their conduciveness to assembly for various curvatures and larger areas of inflatable structures. The proposed modular skins feature an easy fabrication process, a simple chemical mechanism, and high adaptability to inflatable structures, thus displaying considerable potential for pioneering a new methodology for effective damage detection and self-healing systems in inflatable robots.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The extension of the lifespan of soft robots necessitates the establishment of an effective self-healing system accompanied by rapid damage detection. Inspired by the mechanisms of bleeding and blood coagulation, a novel damage-detecting and self-healing modular skin is developed for inflatable structures. This alternative structural material is realized using a liquid conductive polymer composed of an elastomer, conductive particles, and a dispersant. Encapsulated in a thin layer, this conductive polymer is found to be capable of both damage detection through generating an electric current and subsequent self-healing through its solidification in the damaged area. The repeated and reproducible generation of electric current is confirmed both prior to and subsequent to the infliction of damage to the patch. A comparison of conductive polymers with distinct mixing ratios reveals that the changes in electric current following the solidification on the patches are different. The applicability of the modular skins is confirmed by their conduciveness to assembly for various curvatures and larger areas of inflatable structures. The proposed modular skins feature an easy fabrication process, a simple chemical mechanism, and high adaptability to inflatable structures, thus displaying considerable potential for pioneering a new methodology for effective damage detection and self-healing systems in inflatable robots.
20.
Gangadhara Naga Sai Gubbala, Masato Nagashima, Hiroki Mori, Young Ah Seong, Hiroki Sato, Ryuma Niiyama, Yuki Suga, Tetsuya Ogata
Deformation Analysis and Prediction of Drop-Stitch Reinforced Inflatable Robot Link for 1DOF and 2DOF Motion Proceedings
2025.
Abstract | BibTeX | タグ: | Links:
@proceedings{Gubbala2025_SII,
title = {Deformation Analysis and Prediction of Drop-Stitch Reinforced Inflatable Robot Link for 1DOF and 2DOF Motion},
author = {Gangadhara Naga Sai Gubbala, Masato Nagashima, Hiroki Mori, Young Ah Seong, Hiroki Sato, Ryuma Niiyama, Yuki Suga, Tetsuya Ogata},
doi = {10.1109/SII59315.2025.10871051},
year = {2025},
date = {2025-01-22},
urldate = {2025-01-22},
abstract = {In this study, we observe the dynamic behavior of an inflatable robot arm with an internally reinforced drop-stitch structure. We examine the deformation during motion of 1 and 2 degrees of freedom (DOF) for an inflatable body. The inflatable robot arm has a soft inflatable body as links and rigid servo actuators as joints. We implemented a sinusoidal motion for inflatable links for various payload conditions and analyzed them using a Motion Capture system. To estimate the dynamic deformation of the balloon in motion, we have defined a Deformation Index (DI) metric. Angle, current of the actuator (servo), and DI are used as input to polynomial regression to predict the end effector position. With this analysis, we can understand the complexity of modeling the nonlinear behavior of inflatable links for multi-DOF motion. We observed DI helps improve the prediction of the end effector position by including deformation information. However, the results demonstrate the limitations of polynomial regression analysis of an internally reinforced inflatable robot arm link.},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
In this study, we observe the dynamic behavior of an inflatable robot arm with an internally reinforced drop-stitch structure. We examine the deformation during motion of 1 and 2 degrees of freedom (DOF) for an inflatable body. The inflatable robot arm has a soft inflatable body as links and rigid servo actuators as joints. We implemented a sinusoidal motion for inflatable links for various payload conditions and analyzed them using a Motion Capture system. To estimate the dynamic deformation of the balloon in motion, we have defined a Deformation Index (DI) metric. Angle, current of the actuator (servo), and DI are used as input to polynomial regression to predict the end effector position. With this analysis, we can understand the complexity of modeling the nonlinear behavior of inflatable links for multi-DOF motion. We observed DI helps improve the prediction of the end effector position by including deformation information. However, the results demonstrate the limitations of polynomial regression analysis of an internally reinforced inflatable robot arm link.
21.
Genta Sasaki, Kazuya Kudo, Ryuma Niiyama
Subterranean Locomotion of Half-Inch Diameter Soft Earthworm Robot with Bellows Segments Proceedings
2025.
Abstract | BibTeX | タグ: | Links:
@proceedings{Sasaki2025_SII,
title = {Subterranean Locomotion of Half-Inch Diameter Soft Earthworm Robot with Bellows Segments},
author = {Genta Sasaki, Kazuya Kudo, Ryuma Niiyama},
doi = {10.1109/SII59315.2025.10870989},
year = {2025},
date = {2025-01-22},
urldate = {2025-01-22},
abstract = {Moving through the ground with a soft robot is a difficult task. Soft locomotion can move without damaging the environment, such as tree roots, but even in just a few centimeters of soil, high friction and resistance forces occur. Differences in soil topography and moisture content also affect the motion. We therefore developed a small, bellows-shaped earthworm robot with an outer diameter of 12 mm. The robot consists of silicone rubber and shape memory alloy wire, and the inside of the bellows is filled with air. When electric current is applied to the shape memory alloy wire, the convex part of the bellows contracts and stretches in the axial direction, generating a force for movement. When no current is applied, it is used as an anchoring segment. We have experimented with 16 different patterns of soil topography and moisture content, and succeeded in realizing soft-robotic subterranean locomotion.},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
Moving through the ground with a soft robot is a difficult task. Soft locomotion can move without damaging the environment, such as tree roots, but even in just a few centimeters of soil, high friction and resistance forces occur. Differences in soil topography and moisture content also affect the motion. We therefore developed a small, bellows-shaped earthworm robot with an outer diameter of 12 mm. The robot consists of silicone rubber and shape memory alloy wire, and the inside of the bellows is filled with air. When electric current is applied to the shape memory alloy wire, the convex part of the bellows contracts and stretches in the axial direction, generating a force for movement. When no current is applied, it is used as an anchoring segment. We have experimented with 16 different patterns of soil topography and moisture content, and succeeded in realizing soft-robotic subterranean locomotion.
27.
Keishi Hirade, Ryuma Niiyama
Curriculum Reinforcement Learning for Obstacle Avoidance Postures for a Hyper-Redundant Manipulator Proceedings
2025.
Abstract | BibTeX | タグ: | Links:
@proceedings{Hirade2025_SII,
title = {Curriculum Reinforcement Learning for Obstacle Avoidance Postures for a Hyper-Redundant Manipulator},
author = {Keishi Hirade, Ryuma Niiyama},
doi = {10.1109/SII59315.2025.10871128},
year = {2025},
date = {2025-01-22},
urldate = {2025-01-22},
abstract = {Redundant robots with more degrees of freedom than necessary for given tasks have attracted attention due to their flexibility, but they also increase the complexity of control. Especially for highly redundant robots, accurate motion planning and obstacle avoidance remain challenging. This research aims to develop a redundant robot arm that can perform reaching tasks while avoiding randomly appearing obstacles using reinforcement learning. We adopted the Proximal Policy Optimization (PPO) algorithm and conducted simulations in the Mujoco environment. The learning process consisted of a three-stage curriculum: reaching task, fixed obstacle avoidance, and random obstacle avoidance, gradually increasing difficulty to achieve efficient learning. Experimental results showed that the arm could adapt to complex environments and effectively reach target positions while avoiding obstacles. In particular, the system demonstrated high adaptability to randomly placed obstacles, successfully reaching within a maximum distance of approximately 0.07 m from the target position.},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
Redundant robots with more degrees of freedom than necessary for given tasks have attracted attention due to their flexibility, but they also increase the complexity of control. Especially for highly redundant robots, accurate motion planning and obstacle avoidance remain challenging. This research aims to develop a redundant robot arm that can perform reaching tasks while avoiding randomly appearing obstacles using reinforcement learning. We adopted the Proximal Policy Optimization (PPO) algorithm and conducted simulations in the Mujoco environment. The learning process consisted of a three-stage curriculum: reaching task, fixed obstacle avoidance, and random obstacle avoidance, gradually increasing difficulty to achieve efficient learning. Experimental results showed that the arm could adapt to complex environments and effectively reach target positions while avoiding obstacles. In particular, the system demonstrated high adaptability to randomly placed obstacles, successfully reaching within a maximum distance of approximately 0.07 m from the target position.
32.
Yusuke Kawashima, Ryuma Niiyama
Motion Assistance System for Telesports by Seamlessly Blending Manual and Automatic Throwing Controls Proceedings
2025.
Abstract | BibTeX | タグ: | Links:
@proceedings{Kawashima2025_SII,
title = {Motion Assistance System for Telesports by Seamlessly Blending Manual and Automatic Throwing Controls},
author = {Yusuke Kawashima, Ryuma Niiyama},
doi = {10.1109/SII59315.2025.10871100},
year = {2025},
date = {2025-01-24},
urldate = {2025-01-24},
abstract = {Telesport, which involves playing sports via avatar robots, has the potential to provide people with physical limitations with the chance to participate in sports, as it allows them to replace their bodies with robots. However, the delay in the teleoperation system makes real-time operation difficult, and it is challenging to operate the agile robot as intended. In this study, we focused on overhand throwing and treated the problem of it being difficult to throw the ball in the intended direction and speed using manual control. In order to accurately realise the agile movements that a user intends, we propose an assistance system that intervenes with automatic control based on the estimated future user's intent for manual control. Furthermore, this assistance system blends manual and automatic control seamlessly to prevent the user from feeling disconnected from the robot due to the intervention of automatic control. The assistance system was evaluated by measuring the direction and speed of the ball thrown overhand, and by assessing whether the user's intent was reflected. As a result, by making the assistance system effective, manual and automatic control were seamlessly blended, and it was confirmed that the throwing motion intended by the user was accurately reflected in the robot.},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
Telesport, which involves playing sports via avatar robots, has the potential to provide people with physical limitations with the chance to participate in sports, as it allows them to replace their bodies with robots. However, the delay in the teleoperation system makes real-time operation difficult, and it is challenging to operate the agile robot as intended. In this study, we focused on overhand throwing and treated the problem of it being difficult to throw the ball in the intended direction and speed using manual control. In order to accurately realise the agile movements that a user intends, we propose an assistance system that intervenes with automatic control based on the estimated future user's intent for manual control. Furthermore, this assistance system blends manual and automatic control seamlessly to prevent the user from feeling disconnected from the robot due to the intervention of automatic control. The assistance system was evaluated by measuring the direction and speed of the ball thrown overhand, and by assessing whether the user's intent was reflected. As a result, by making the assistance system effective, manual and automatic control were seamlessly blended, and it was confirmed that the throwing motion intended by the user was accurately reflected in the robot.
2024
2.
Gubbala Gangadhara Naga Sai, Masato Nagashima, Hiroki Mori, Young Ah Seong, Hiroki Sato, Ryuma Niiyama, Yuki Suga, Tetsuya Ogata
Augmenting Compliance with Motion Generation Through Imitation Learning Using Drop-Stitch Reinforced Inflatable Robot Arm with Rigid Joints Journal Article
In: IEEE Robotics and Automation Letters, vol. 9, iss. 10, pp. 8595 - 8602, 2024.
Abstract | BibTeX | タグ: | Links:
@article{Gangadhara2024,
title = {Augmenting Compliance with Motion Generation Through Imitation Learning Using Drop-Stitch Reinforced Inflatable Robot Arm with Rigid Joints},
author = {Gubbala Gangadhara Naga Sai, Masato Nagashima, Hiroki Mori, Young Ah Seong, Hiroki Sato, Ryuma Niiyama, Yuki Suga, Tetsuya Ogata},
doi = {10.1109/LRA.2024.3446270},
year = {2024},
date = {2024-08-20},
urldate = {2024-08-20},
journal = {IEEE Robotics and Automation Letters},
volume = {9},
issue = {10},
pages = {8595 - 8602},
abstract = {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 and dynamic control. We focus on motion generation for a 3 degrees of freedom (3DOF) inflatable robot arm, which consists of soft inflatable body links and rigid joints. This research explores the limitations of relying solely on soft robot compliance for completing contact-based tasks. Our goal is to generate adaptive motion for contact-based tasks by exploiting the compliance of soft links. We compare contact-based tasks involving an inflatable robot with and without a learning model. Improved performance is achieved when soft robot compliance is augmented with imitation learning. The combination of soft robot compliance and the adaptability of the machine learning model demonstrates the potential for collaborative robots to safely interact with humans and their surroundings.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
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 and dynamic control. We focus on motion generation for a 3 degrees of freedom (3DOF) inflatable robot arm, which consists of soft inflatable body links and rigid joints. This research explores the limitations of relying solely on soft robot compliance for completing contact-based tasks. Our goal is to generate adaptive motion for contact-based tasks by exploiting the compliance of soft links. We compare contact-based tasks involving an inflatable robot with and without a learning model. Improved performance is achieved when soft robot compliance is augmented with imitation learning. The combination of soft robot compliance and the adaptability of the machine learning model demonstrates the potential for collaborative robots to safely interact with humans and their surroundings.
13.
Ryuma Niiyama, Honoka Yoshida, Ryogo Kawamata, Katsuki Higo, Sotaro Shimada
Augmented Bodily Self in Performing a Button-Touching Task with Soft Supernumerary Robotic Arms Journal Article
In: Journal of Robotics and Mechatronics, vol. 36, iss. 4, pp. 856-863, 2024.
Abstract | BibTeX | タグ: | Links:
@article{Niiyama2024,
title = {Augmented Bodily Self in Performing a Button-Touching Task with Soft Supernumerary Robotic Arms},
author = {Ryuma Niiyama, Honoka Yoshida, Ryogo Kawamata, Katsuki Higo, Sotaro Shimada},
doi = {10.20965/jrm.2024.p0856},
year = {2024},
date = {2024-08-20},
urldate = {2024-08-20},
journal = {Journal of Robotics and Mechatronics},
volume = {36},
issue = {4},
pages = {856-863},
abstract = {Extra or supernumerary robotic limbs are actively exploited in the field of body augmentation. The science of self-recognition of additional body parts is an interesting subject. Although the field is primarily led by psychological studies in virtual reality, which facilitate flexible experimental designs, we believe that assessments employing real robots are also essential. In this study, we investigated the sense of body ownership and agency of a dual-arm wearable robotic arm using an inexpensive and safe inflatable structure. We report the results of functional near-infrared spectroscopy (fNIRS) analysis of brain activity during the use of the robotic arm. The questionnaire results from the experiment, which involved a button-touching task, revealed that both the sense of ownership and sense of agency were significantly higher in the goal-oriented collaborative experience compared to the non-goal-oriented condition. This indicates that humans feel ownership of and agency toward an autonomous robot or a remote-controlled robotic arm operated by another person. The analysis of the fNIRS data included a two-factor analysis of variance for the learning and trial phases. While there was no main effect for the conditions within each phase, a significant interaction was observed between the two brain regions of the right angular gyrus and right postcentral gyrus.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Extra or supernumerary robotic limbs are actively exploited in the field of body augmentation. The science of self-recognition of additional body parts is an interesting subject. Although the field is primarily led by psychological studies in virtual reality, which facilitate flexible experimental designs, we believe that assessments employing real robots are also essential. In this study, we investigated the sense of body ownership and agency of a dual-arm wearable robotic arm using an inexpensive and safe inflatable structure. We report the results of functional near-infrared spectroscopy (fNIRS) analysis of brain activity during the use of the robotic arm. The questionnaire results from the experiment, which involved a button-touching task, revealed that both the sense of ownership and sense of agency were significantly higher in the goal-oriented collaborative experience compared to the non-goal-oriented condition. This indicates that humans feel ownership of and agency toward an autonomous robot or a remote-controlled robotic arm operated by another person. The analysis of the fNIRS data included a two-factor analysis of variance for the learning and trial phases. While there was no main effect for the conditions within each phase, a significant interaction was observed between the two brain regions of the right angular gyrus and right postcentral gyrus.
17.
Takeru Manome, Ryuma Niiyama
Hybrid RobOstrich Manipulator with Intrinsic and Extrinsic Actuations Journal Article
In: Journal of Robotics and Mechatronics, vol. 36, no. 6, pp. 1448-1457, 2024.
Abstract | BibTeX | タグ: | Links:
@article{Manome2024,
title = {Hybrid RobOstrich Manipulator with Intrinsic and Extrinsic Actuations},
author = {Takeru Manome and Ryuma Niiyama},
doi = {10.20965/jrm.2024.p1448},
year = {2024},
date = {2024-12-20},
urldate = {2024-12-20},
journal = {Journal of Robotics and Mechatronics},
volume = {36},
number = {6},
pages = {1448-1457},
abstract = {Ostrich neck-inspired manipulators have attracted attention in the field of bio-inspired robotics. They achieve unique movements that are difficult for conventional robots, owing to their flexibility. However, it is difficult to mimic the length, mass, and actuation redundancy of ostrich necks. This is because the longer and heavier the robotic arm, the greater is the load on the joints. Furthermore, if a robotic arm exhibits actuation redundancy, its structure and control become more complex. In this study, we developed a hybrid RobOstrich manipulator with both intrinsic and extrinsic actuations. This is the third-generation of the RobOstrich series. The manipulator consists of a servomotor attached to each joint that performs intrinsic actuation and two servomotors on the base that perform extrinsic actuation through wires. We conducted an experiment to reproduce the rolling pattern, which is a unique movement of the ostrich neck, to verify the effect of hybrid actuation. The results indicated that the joint angle error and required torque were reduced by applying hybrid actuation.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Ostrich neck-inspired manipulators have attracted attention in the field of bio-inspired robotics. They achieve unique movements that are difficult for conventional robots, owing to their flexibility. However, it is difficult to mimic the length, mass, and actuation redundancy of ostrich necks. This is because the longer and heavier the robotic arm, the greater is the load on the joints. Furthermore, if a robotic arm exhibits actuation redundancy, its structure and control become more complex. In this study, we developed a hybrid RobOstrich manipulator with both intrinsic and extrinsic actuations. This is the third-generation of the RobOstrich series. The manipulator consists of a servomotor attached to each joint that performs intrinsic actuation and two servomotors on the base that perform extrinsic actuation through wires. We conducted an experiment to reproduce the rolling pattern, which is a unique movement of the ostrich neck, to verify the effect of hybrid actuation. The results indicated that the joint angle error and required torque were reduced by applying hybrid actuation.
24.
Katsu Uchiyama, Masayuki Otsuka, Ryuma Niiyama
Multi-DOF Blower-Powered and Inner Tendon-Driven Soft Inflatable Robotic Arm Proceedings
2024.
Abstract | BibTeX | タグ: | Links:
@proceedings{Uchiyama2024_SII,
title = {Multi-DOF Blower-Powered and Inner Tendon-Driven Soft Inflatable Robotic Arm},
author = {Katsu Uchiyama, Masayuki Otsuka, Ryuma Niiyama},
doi = {10.1109/SII58957.2024.10417544},
year = {2024},
date = {2024-01-08},
urldate = {2024-01-08},
abstract = {We propose a soft inflatable robotic arm as a type of inflatable robot that is light and can be made larger. This robotic arm is based on a soft inflatable joint, which is actuated by an internal tendon and constantly supplied with air by a blower. The tendon drive method was unknown, so it was difficult to make the arm articulated. To achieve multiple degrees of freedom, a guide was fabricated to prevent tendon interference and to guide the tendons. This guide was made of a thin plate so that the flexibility and light weight of the inflatable robot would not be compromised. Guide was provided at the joints to derive the relationship between joint angle and amount of wire pulling. It was used to maintain the relationship between the tendon wire intersections and the anchor points between the joints. The function of the guide was fully confirmed through motion experiments on a robot arm using these guides. Based on this, a robot arm over 1-meter long was created, and it was verified that various postures were possible. These results will contribute to expanding the design space for low-pressure, large inflatable robots.},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
We propose a soft inflatable robotic arm as a type of inflatable robot that is light and can be made larger. This robotic arm is based on a soft inflatable joint, which is actuated by an internal tendon and constantly supplied with air by a blower. The tendon drive method was unknown, so it was difficult to make the arm articulated. To achieve multiple degrees of freedom, a guide was fabricated to prevent tendon interference and to guide the tendons. This guide was made of a thin plate so that the flexibility and light weight of the inflatable robot would not be compromised. Guide was provided at the joints to derive the relationship between joint angle and amount of wire pulling. It was used to maintain the relationship between the tendon wire intersections and the anchor points between the joints. The function of the guide was fully confirmed through motion experiments on a robot arm using these guides. Based on this, a robot arm over 1-meter long was created, and it was verified that various postures were possible. These results will contribute to expanding the design space for low-pressure, large inflatable robots.
25.
Katsu Uchiyama, Ryuma Niiyama
Pneumatic Bladder Links with Wide Range of Motion Joints for Articulated Inflatable Robots Proceedings
2024.
Abstract | BibTeX | タグ: | Links:
@proceedings{Uchiyama2024_IROS,
title = {Pneumatic Bladder Links with Wide Range of Motion Joints for Articulated Inflatable Robots},
author = {Katsu Uchiyama, Ryuma Niiyama},
doi = {10.1109/IROS58592.2024.10802836},
year = {2024},
date = {2024-10-18},
urldate = {2024-10-18},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
pages = {FrPI6T2.13},
abstract = {Exploration of various applications is the frontier of research on inflatable robots. We proposed an articulated robots consisting of multiple pneumatic bladder links connected by rolling contact joints called Hillberry joints. The bladder link is made of a double-layered structure of tarpaulin sheet and polyurethane sheet, which is both airtight and flexible in shape. The integration of the Hilberry joint into an inflatable robot is also a new approach. The rolling contact joint allows wide range of motion of ±150°, the largest among the conventional inflatable joints. Using the proposed mechanism for inflatable robots, we demonstrated moving a 500 g payload with a 3-DoF arm and lifting 3.4 kg and 5 kg payloads with 2-DoF and 1-DoF arms, respectively. We also experimented with a single 3-DoF inflatable leg attached to a dolly to show that the proposed structure worked for legged locomotion.},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
Exploration of various applications is the frontier of research on inflatable robots. We proposed an articulated robots consisting of multiple pneumatic bladder links connected by rolling contact joints called Hillberry joints. The bladder link is made of a double-layered structure of tarpaulin sheet and polyurethane sheet, which is both airtight and flexible in shape. The integration of the Hilberry joint into an inflatable robot is also a new approach. The rolling contact joint allows wide range of motion of ±150°, the largest among the conventional inflatable joints. Using the proposed mechanism for inflatable robots, we demonstrated moving a 500 g payload with a 3-DoF arm and lifting 3.4 kg and 5 kg payloads with 2-DoF and 1-DoF arms, respectively. We also experimented with a single 3-DoF inflatable leg attached to a dolly to show that the proposed structure worked for legged locomotion.
28.
Koichi Tezuka, Ryuma Niiyama
Real-to-real motor learning of tendon-driven soft caterpillar locomotion with world model Proceedings
2024.
Abstract | BibTeX | タグ: | Links:
@proceedings{Tezuka2024_Robosoft,
title = {Real-to-real motor learning of tendon-driven soft caterpillar locomotion with world model},
author = {Koichi Tezuka, Ryuma Niiyama},
doi = {10.1109/RoboSoft60065.2024.10521932},
year = {2024},
date = {2024-04-16},
urldate = {2024-04-16},
abstract = {Controlling soft mobile robots that perform limb-less locomotion is costly to develop due to the need to consider friction and the complexity of movement mechanics. There are methods using reinforcement learning (RL) to create controllers for complex soft caterpillar robots. However, these often involve learning through simulation, and model inaccuracies can lead to reduced controller performance upon deployment. In this paper, we created a soft caterpillar robot driven by tendons with two motors and trained a controller using RL. By training with real soft robots without using simulations, we created a learning model that works effectively even with soft robots' complex dynamics, without performance degradation upon deployment. Using a model-based learning algorithm enabled quick policy learning, even with real robots that typically require time-consuming sampling. The learning model we developed could achieve locomotion in forward tasks after about one hour of training. After training, the actual robot was capable of moving at approximately 36.7 mm/s. To the best of our knowledge, this is the first instance of learning locomotion for a soft mobile robot's crawling using only a real robot.},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
Controlling soft mobile robots that perform limb-less locomotion is costly to develop due to the need to consider friction and the complexity of movement mechanics. There are methods using reinforcement learning (RL) to create controllers for complex soft caterpillar robots. However, these often involve learning through simulation, and model inaccuracies can lead to reduced controller performance upon deployment. In this paper, we created a soft caterpillar robot driven by tendons with two motors and trained a controller using RL. By training with real soft robots without using simulations, we created a learning model that works effectively even with soft robots' complex dynamics, without performance degradation upon deployment. Using a model-based learning algorithm enabled quick policy learning, even with real robots that typically require time-consuming sampling. The learning model we developed could achieve locomotion in forward tasks after about one hour of training. After training, the actual robot was capable of moving at approximately 36.7 mm/s. To the best of our knowledge, this is the first instance of learning locomotion for a soft mobile robot's crawling using only a real robot.
2023
5.
Kazashi Nakano, Megu Gunji, Masahiro Ikeda, Keung Or, Mitsuhito Ando, Katsuma Inoue, Hiromi Mochiyama, Kohei Nakajima, Ryuma Niiyama, Yasuo Kuniyoshi
RobOstrich Manipulator: A Novel Mechanical Design and Control Based on the Anatomy and Behavior of an Ostrich Neck Journal Article
In: IEEE Robotics and Automation Letters, vol. 8, no. 5, pp. 3062–3069, 2023.
Abstract | BibTeX | タグ: | Links:
@article{Nakano2023,
title = {RobOstrich Manipulator: A Novel Mechanical Design and Control Based on the Anatomy and Behavior of an Ostrich Neck},
author = {Kazashi Nakano, Megu Gunji, Masahiro Ikeda, Keung Or, Mitsuhito Ando, Katsuma Inoue, Hiromi Mochiyama, Kohei Nakajima, Ryuma Niiyama, Yasuo Kuniyoshi},
doi = {10.1109/LRA.2023.3265301},
year = {2023},
date = {2023-04-06},
urldate = {2023-04-06},
journal = {IEEE Robotics and Automation Letters},
volume = {8},
number = {5},
pages = {3062–3069},
abstract = {Flexible manipulators have high degrees of freedom and deformability, enabling dexterous movements and allowing for unexpected contacts with the environment. Underactuated tendon-drive mechanisms are the most widely adopted because of their simplicity and effectiveness. However, they suffer from difficulty in modeling and in achieving dexterity and structural stability. In this letter, we focus on ostriches, which can dexterously and swiftly move their flexible necks. We carried out a detailed dissection of ostrich necks and identified a specific musculo-tendon-skeletal structure. Based on the findings related to the structure, we came up with a novel mechanical design and control method manifested as a “RobOstrich” manipulator. Our actual robot experiments confirm that it exhibits similar movement patterns as an ostrich neck. It is also flexible yet structurally stable, enabling dexterous reaching movements. This work also contributes to biology by providing constructive understanding of the functionality of the morphology of an ostrich neck.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Flexible manipulators have high degrees of freedom and deformability, enabling dexterous movements and allowing for unexpected contacts with the environment. Underactuated tendon-drive mechanisms are the most widely adopted because of their simplicity and effectiveness. However, they suffer from difficulty in modeling and in achieving dexterity and structural stability. In this letter, we focus on ostriches, which can dexterously and swiftly move their flexible necks. We carried out a detailed dissection of ostrich necks and identified a specific musculo-tendon-skeletal structure. Based on the findings related to the structure, we came up with a novel mechanical design and control method manifested as a “RobOstrich” manipulator. Our actual robot experiments confirm that it exhibits similar movement patterns as an ostrich neck. It is also flexible yet structurally stable, enabling dexterous reaching movements. This work also contributes to biology by providing constructive understanding of the functionality of the morphology of an ostrich neck.
9.
Keung Or, Kehua Wu, Kazashi Nakano, Masahiro Ikeda,Mitsuhito Ando, Yasuo Kuniyoshi, Ryuma Niiyama
Curriculum-reinforcement learning on simulation platform of tendon-driven high-degree of freedom underactuated manipulator Journal Article
In: Frontiers in Robotics and AI, vol. 10, pp. 1-15, 2023.
Abstract | BibTeX | タグ: | Links:
@article{Or2023,
title = {Curriculum-reinforcement learning on simulation platform of tendon-driven high-degree of freedom underactuated manipulator},
author = {Keung Or, Kehua Wu, Kazashi Nakano, Masahiro Ikeda,Mitsuhito Ando, Yasuo Kuniyoshi, Ryuma Niiyama},
doi = {10.3389/frobt.2023.1066518},
year = {2023},
date = {2023-07-12},
urldate = {2023-07-12},
journal = {Frontiers in Robotics and AI},
volume = {10},
pages = {1-15},
abstract = {A high degree of freedom (DOF) benefits manipulators by presenting various postures when reaching a target. Using a tendon-driven system with an underactuated structure can provide flexibility and weight reduction to such manipulators. The design and control of such a composite system are challenging owing to its complicated architecture and modeling difficulties. In our previous study, we developed a tendon-driven, high-DOF underactuated manipulator inspired from an ostrich neck referred to as the Robostrich arm. This study particularly focused on the control problems and simulation development of such a tendon-driven high-DOF underactuated manipulator. We proposed a curriculum-based reinforcement-learning approach. Inspired by human learning, progressing from simple to complex tasks, the Robostrich arm can obtain manipulation abilities by step-by-step reinforcement learning ranging from simple position control tasks to practical application tasks. In addition, an approach was developed to simulate tendon-driven manipulation with a complicated structure. The results show that the Robostrich arm can continuously reach various targets and simultaneously maintain its tip at the desired orientation while mounted on a mobile platform in the presence of perturbation. These results show that our system can achieve flexible manipulation ability even if vibrations are presented by locomotion.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
A high degree of freedom (DOF) benefits manipulators by presenting various postures when reaching a target. Using a tendon-driven system with an underactuated structure can provide flexibility and weight reduction to such manipulators. The design and control of such a composite system are challenging owing to its complicated architecture and modeling difficulties. In our previous study, we developed a tendon-driven, high-DOF underactuated manipulator inspired from an ostrich neck referred to as the Robostrich arm. This study particularly focused on the control problems and simulation development of such a tendon-driven high-DOF underactuated manipulator. We proposed a curriculum-based reinforcement-learning approach. Inspired by human learning, progressing from simple to complex tasks, the Robostrich arm can obtain manipulation abilities by step-by-step reinforcement learning ranging from simple position control tasks to practical application tasks. In addition, an approach was developed to simulate tendon-driven manipulation with a complicated structure. The results show that the Robostrich arm can continuously reach various targets and simultaneously maintain its tip at the desired orientation while mounted on a mobile platform in the presence of perturbation. These results show that our system can achieve flexible manipulation ability even if vibrations are presented by locomotion.
15.
Ryuma Niiyama, Masahiro Ikeda, Young Ah Seong
Inflatable Humanoid Cybernetic Avatar for Physical Human–Robot Interaction Journal Article
In: International Journal of Automation Technology (IJAT), vol. 17, no. 3, pp. 277–283, 2023.
Abstract | BibTeX | タグ: | Links:
@article{Niiyama2023,
title = {Inflatable Humanoid Cybernetic Avatar for Physical Human–Robot Interaction},
author = {Ryuma Niiyama, Masahiro Ikeda, Young Ah Seong},
doi = {10.20965/ijat.2023.p0277},
year = {2023},
date = {2023-05-05},
urldate = {2023-05-05},
journal = {International Journal of Automation Technology (IJAT)},
volume = {17},
number = {3},
pages = {277–283},
abstract = {In a digital twin, a humanoid robot can be the counterpart of a simulated agent in the real world. In addition, a human, virtual avatar, and avatar robot might constitute digital triplets. We propose an inflatable cybernetic avatar (CA) with a humanoid upper body using an inflatable structure that can represent gestures. This inflatable CA is much lighter, safer, and cheaper than conventional humanoid robots and can be folded when deflated. These properties are ideal for physical human–robot interaction (pHRI) and allow real-time collection of human behavior through interaction. In the experiment, basic movements such as nodding and raising arms were measured using motion capture systems. This paper demonstrates the proposed inflatable CA in a hybrid event. We also conducted an experiment to measure the touch interactions using tactile sensors attached to the fabric of the inflatable part. A psychologically secure inflatable humanoid CA is a promising platform for physical interaction experiments.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In a digital twin, a humanoid robot can be the counterpart of a simulated agent in the real world. In addition, a human, virtual avatar, and avatar robot might constitute digital triplets. We propose an inflatable cybernetic avatar (CA) with a humanoid upper body using an inflatable structure that can represent gestures. This inflatable CA is much lighter, safer, and cheaper than conventional humanoid robots and can be folded when deflated. These properties are ideal for physical human–robot interaction (pHRI) and allow real-time collection of human behavior through interaction. In the experiment, basic movements such as nodding and raising arms were measured using motion capture systems. This paper demonstrates the proposed inflatable CA in a hybrid event. We also conducted an experiment to measure the touch interactions using tactile sensors attached to the fabric of the inflatable part. A psychologically secure inflatable humanoid CA is a promising platform for physical interaction experiments.
2022
1.
Atsuhiko Niikura, Hiroyuki Nabae, Gen Endo, Megu Gunji, Kent Mori, Ryuma Niiyama, Koichi Suzumori
Giraffe Neck Robot: First Step Toward a Powerful and Flexible Robot Prototyping Based on Giraffe Anatomy Journal Article
In: IEEE Robotics and Automation Letters, vol. 7, no. 2, pp. 3539–3546, 2022.
Abstract | BibTeX | タグ: | Links:
@article{Niikura2022,
title = {Giraffe Neck Robot: First Step Toward a Powerful and Flexible Robot Prototyping Based on Giraffe Anatomy},
author = {Atsuhiko Niikura, Hiroyuki Nabae, Gen Endo, Megu Gunji, Kent Mori, Ryuma Niiyama, Koichi Suzumori},
doi = {10.1109/LRA.2022.3146611},
year = {2022},
date = {2022-01-27},
urldate = {2022-01-27},
journal = {IEEE Robotics and Automation Letters},
volume = {7},
number = {2},
pages = {3539–3546},
abstract = {The neck of a giraffe has excellent characteristics that can serve as a good alternative for designing a large robotic mechanism. For example, the neck can rapidly move when performing necking, a motion where the giraffes strike each other’s necks. Furthermore, the neck of a giraffe helps prevent impacts and adapts to the shape and hardness of the opponent’s neck during necking. In contrast, a conventional robotic mechanism is limited in its capability to achieve such powerfulness and flexibility characteristics; that is, being powerful while having robustness against impacts and kinematic and dynamic adaptability to the opponent. This study focuses on applying those excellent characteristics of a giraffe neck to develop robotic mechanisms. Specifically, roboticists and animal anatomists have combined efforts to develop a powerful and flexible long musculoskeletal robot based on the anatomy of a giraffe neck. The musculoskeletal robot prototype is actuated using thin McKibben pneumatic artificial muscles that bend easily. The results confirm the coordination between the muscles and ligaments and the shape adaptability to an external force.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The neck of a giraffe has excellent characteristics that can serve as a good alternative for designing a large robotic mechanism. For example, the neck can rapidly move when performing necking, a motion where the giraffes strike each other’s necks. Furthermore, the neck of a giraffe helps prevent impacts and adapts to the shape and hardness of the opponent’s neck during necking. In contrast, a conventional robotic mechanism is limited in its capability to achieve such powerfulness and flexibility characteristics; that is, being powerful while having robustness against impacts and kinematic and dynamic adaptability to the opponent. This study focuses on applying those excellent characteristics of a giraffe neck to develop robotic mechanisms. Specifically, roboticists and animal anatomists have combined efforts to develop a powerful and flexible long musculoskeletal robot based on the anatomy of a giraffe neck. The musculoskeletal robot prototype is actuated using thin McKibben pneumatic artificial muscles that bend easily. The results confirm the coordination between the muscles and ligaments and the shape adaptability to an external force.
3.
Hiromi Mochiyama, Megu Gunji, Ryuma Niiyama
Ostrich-Inspired Soft Robotics: A Flexible Bipedal Manipulator for Aggressive Physical Interaction Journal Article
In: Journal of Robotics and Mechatronics, vol. 34, no. 2, pp. 212–218, 2022.
Abstract | BibTeX | タグ: | Links:
@article{Mochiyama2022,
title = {Ostrich-Inspired Soft Robotics: A Flexible Bipedal Manipulator for Aggressive Physical Interaction},
author = {Hiromi Mochiyama, Megu Gunji, Ryuma Niiyama},
doi = {10.20965/jrm.2022.p0212},
year = {2022},
date = {2022-04-20},
urldate = {2022-04-20},
journal = {Journal of Robotics and Mechatronics},
volume = {34},
number = {2},
pages = {212–218},
abstract = {In this letter, ostrich-inspired soft robotics, an approach to intelligent robots that can achieve dexterous manipulation and locomotion without hesitating to collide with the surrounding environment, is proposed. The rationale behind the approach is described from the history of bio-inspired mechanisms, biology, and the theory of robot control. This letter focuses on the manipulator. The first prototype of an ostrich-inspired manipulator was developed to investigate its feasibility. This prototype is a serial chain of 18 rigid links connected with rotation joints moving in a vertical plane and driven through two asymmetric antagonistic wire systems connected to two levers that are directly operated by a human operator playing the role of the controller. Therefore, this manipulator is a highly underactuated mechanism that is flexible against external forces. The experimental results show that a human operator can control this manipulator so that its tip (i.e., the head) can reach several positions, including an upper position against gravity, indicating the potential of ostrich-inspired manipulators.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In this letter, ostrich-inspired soft robotics, an approach to intelligent robots that can achieve dexterous manipulation and locomotion without hesitating to collide with the surrounding environment, is proposed. The rationale behind the approach is described from the history of bio-inspired mechanisms, biology, and the theory of robot control. This letter focuses on the manipulator. The first prototype of an ostrich-inspired manipulator was developed to investigate its feasibility. This prototype is a serial chain of 18 rigid links connected with rotation joints moving in a vertical plane and driven through two asymmetric antagonistic wire systems connected to two levers that are directly operated by a human operator playing the role of the controller. Therefore, this manipulator is a highly underactuated mechanism that is flexible against external forces. The experimental results show that a human operator can control this manipulator so that its tip (i.e., the head) can reach several positions, including an upper position against gravity, indicating the potential of ostrich-inspired manipulators.
8.
Kenji Misu, Masahiro Ikeda, Keung Or, Mitsuhito Ando, Megu Gunji, Hiromi Mochiyama, Ryuma Niiyama
Robostrich Arm: Wire-Driven High-DOF Underactuated Manipulator Journal Article
In: Journal of Robotics and Mechatronics, vol. 34, no. 2, pp. 328–338, 2022.
Abstract | BibTeX | タグ: | Links:
@article{Misu2022,
title = {Robostrich Arm: Wire-Driven High-DOF Underactuated Manipulator},
author = {Kenji Misu, Masahiro Ikeda, Keung Or, Mitsuhito Ando, Megu Gunji, Hiromi Mochiyama, Ryuma Niiyama},
doi = {10.20965/jrm.2022.p0328},
year = {2022},
date = {2022-04-20},
urldate = {2022-04-20},
journal = {Journal of Robotics and Mechatronics},
volume = {34},
number = {2},
pages = {328–338},
abstract = {We propose a wire-driven robotic arm inspired by the ostrich neck. It can pick up a small piece of feed from the ground while colliding with it. This arm is named robostrich arm (shortened form of robotic ostrich arm). It consists of a serial chain of 18 rigid bodies connected by free rotational joints that are designed to have angle limitations similar to the bones of a real ostrich. It moves in a vertical plane and is driven by two DC motors through antagonistic wires. The task considered in this study was to lift the arm tip (the “head” of the robostrich arm). The experimental results indicate that the tensioner balance and timing between the two wires are important for achieving the head-up task. This paper indicates the contribution of antagonist muscles to the performance of head-up tasks by high-degree-of-freedom underactuated manipulators in robotics and ostrich necks in biological studies.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
We propose a wire-driven robotic arm inspired by the ostrich neck. It can pick up a small piece of feed from the ground while colliding with it. This arm is named robostrich arm (shortened form of robotic ostrich arm). It consists of a serial chain of 18 rigid bodies connected by free rotational joints that are designed to have angle limitations similar to the bones of a real ostrich. It moves in a vertical plane and is driven by two DC motors through antagonistic wires. The task considered in this study was to lift the arm tip (the “head” of the robostrich arm). The experimental results indicate that the tensioner balance and timing between the two wires are important for achieving the head-up task. This paper indicates the contribution of antagonist muscles to the performance of head-up tasks by high-degree-of-freedom underactuated manipulators in robotics and ostrich necks in biological studies.
11.
Masahiro Ikeda, Ryuma Niiyama, Yasuo Kuniyoshi
Proposal of Manufacturing Method for New Passive Elastic Joint and Prototype of Human Phantom Journal Article
In: Journal of Robotics and Mechatronics, vol. 34, no. 2, pp. 402–412, 2022.
Abstract | BibTeX | タグ: | Links:
@article{Ikeda2022,
title = {Proposal of Manufacturing Method for New Passive Elastic Joint and Prototype of Human Phantom},
author = {Masahiro Ikeda, Ryuma Niiyama, Yasuo Kuniyoshi},
doi = {10.20965/jrm.2022.p0402},
year = {2022},
date = {2022-04-20},
urldate = {2022-04-20},
journal = {Journal of Robotics and Mechatronics},
volume = {34},
number = {2},
pages = {402–412},
abstract = {Fabricating a soft robot using conventional molding methods is difficult and time-consuming. Moreover, the types of materials used in the process are limited, and the elasticity cannot be changed incrementally. In this paper, we explain the detailed process of manufacturing molds for silicone joints. We construct a prototype molded silicone joint. We measure the elastic modulus of this joint and confirm that the elastic modulus and anisotropy change depending on the density, size, and arrangement of the surface grooves in the mold. We also develop a prototype human phantom using the proposed joint. We aim to contribute to the medical field by applying new techniques made possible by soft robotics.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Fabricating a soft robot using conventional molding methods is difficult and time-consuming. Moreover, the types of materials used in the process are limited, and the elasticity cannot be changed incrementally. In this paper, we explain the detailed process of manufacturing molds for silicone joints. We construct a prototype molded silicone joint. We measure the elastic modulus of this joint and confirm that the elastic modulus and anisotropy change depending on the density, size, and arrangement of the surface grooves in the mold. We also develop a prototype human phantom using the proposed joint. We aim to contribute to the medical field by applying new techniques made possible by soft robotics.
12.
Ryuma Niiyama
Soft Actuation and Compliant Mechanisms in Humanoid Robots Journal Article
In: Current Robotics Reports, vol. 3, pp. 111-117, 2022.
Abstract | BibTeX | タグ: | Links:
@article{Niiyama2022,
title = {Soft Actuation and Compliant Mechanisms in Humanoid Robots},
author = {Ryuma Niiyama},
doi = {10.1007/s43154-022-00084-7},
year = {2022},
date = {2022-07-21},
urldate = {2022-07-21},
journal = {Current Robotics Reports},
volume = {3},
pages = {111-117},
abstract = {Purpose of Review
We aimed to reveal the impact of soft robotics, which has developed in the last decade, on humanoid robotics research. Although humanoid robots are usually classified as hard robotics, softness should be integrated because soft materials and mechanisms are used extensively in the human body.
Recent Findings
In recent years, new soft actuators based on hybrid approaches, such as the combination of electricity and fluid, have emerged. Physically compliant robotic systems that are safe and robust are needed to take on higher-risk tasks and to tolerate large numbers of trials in the process of machine learning.
Summary
Emerging soft actuators are enabling humanoid robots to achieve rapid movements with physical impacts. Efforts to integrate soft robotics and humanoid robots are still on their way. A potential direction for humanoid robots is their application to physical human-robot interaction, where further exploitation of softness is expected.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Purpose of Review
We aimed to reveal the impact of soft robotics, which has developed in the last decade, on humanoid robotics research. Although humanoid robots are usually classified as hard robotics, softness should be integrated because soft materials and mechanisms are used extensively in the human body.
Recent Findings
In recent years, new soft actuators based on hybrid approaches, such as the combination of electricity and fluid, have emerged. Physically compliant robotic systems that are safe and robust are needed to take on higher-risk tasks and to tolerate large numbers of trials in the process of machine learning.
Summary
Emerging soft actuators are enabling humanoid robots to achieve rapid movements with physical impacts. Efforts to integrate soft robotics and humanoid robots are still on their way. A potential direction for humanoid robots is their application to physical human-robot interaction, where further exploitation of softness is expected.
We aimed to reveal the impact of soft robotics, which has developed in the last decade, on humanoid robotics research. Although humanoid robots are usually classified as hard robotics, softness should be integrated because soft materials and mechanisms are used extensively in the human body.
Recent Findings
In recent years, new soft actuators based on hybrid approaches, such as the combination of electricity and fluid, have emerged. Physically compliant robotic systems that are safe and robust are needed to take on higher-risk tasks and to tolerate large numbers of trials in the process of machine learning.
Summary
Emerging soft actuators are enabling humanoid robots to achieve rapid movements with physical impacts. Efforts to integrate soft robotics and humanoid robots are still on their way. A potential direction for humanoid robots is their application to physical human-robot interaction, where further exploitation of softness is expected.
14.
Ryuma Niiyama, Kazuma Matsushita, Masahiro Ikeda, Keung Or, Yasuo Kuniyoshi
A 3D Printed Hydrostatic Skeleton for Earthworm-inspired Soft Burrowing Robot Journal Article
In: Soft Matter, vol. 18, iss. 41, pp. 7990–7997, 2022.
Abstract | BibTeX | タグ: | Links:
@article{Niiyama2022,
title = {A 3D Printed Hydrostatic Skeleton for Earthworm-inspired Soft Burrowing Robot},
author = {Ryuma Niiyama, Kazuma Matsushita, Masahiro Ikeda, Keung Or, Yasuo Kuniyoshi},
doi = {10.1039/D2SM00882C},
year = {2022},
date = {2022-10-11},
urldate = {2022-10-11},
journal = {Soft Matter},
volume = {18},
issue = {41},
pages = {7990–7997},
abstract = {Moving through soil is challenging for robots, particularly for soft robots. Herein, we propose a support structure, based on the hydrostatic skeleton of earthworms, to overcome this problem. To create extremely flexible, thin-walled, worm-sized deformed segments, a specialized 3D printer for low-hardness rubber was utilized. To obtain large radial deformation, we investigated the properties of the soft materials for 3D printing and the geometry of the segments. Notably, segments are deformed with multiply-wound shape memory alloy wires. We constructed an earthworm robot by connecting shape memory alloy-driven segments in series and experimentally demonstrated that this robot could propel in the soil. The proposed robot is unique in that it has a small diameter of 10 mm and exhibits a peristaltic motion in soil.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Moving through soil is challenging for robots, particularly for soft robots. Herein, we propose a support structure, based on the hydrostatic skeleton of earthworms, to overcome this problem. To create extremely flexible, thin-walled, worm-sized deformed segments, a specialized 3D printer for low-hardness rubber was utilized. To obtain large radial deformation, we investigated the properties of the soft materials for 3D printing and the geometry of the segments. Notably, segments are deformed with multiply-wound shape memory alloy wires. We constructed an earthworm robot by connecting shape memory alloy-driven segments in series and experimentally demonstrated that this robot could propel in the soil. The proposed robot is unique in that it has a small diameter of 10 mm and exhibits a peristaltic motion in soil.
18.
新山 龍馬, 池田 昌弘, ソン ヨンア
社会的相互作用の拡張のためのヒト型インフレータブル・サイバネティック・アバター Journal Article
In: 日本バーチャルリアリティ学会論文誌, vol. 27, no. 4, pp. 381–384, 2022.
Abstract | BibTeX | タグ: | Links:
@article{新山2022,
title = {社会的相互作用の拡張のためのヒト型インフレータブル・サイバネティック・アバター},
author = {新山 龍馬, 池田 昌弘, ソン ヨンア},
doi = {10.18974/tvrsj.27.4_381},
year = {2022},
date = {2022-12-28},
urldate = {2022-12-28},
journal = {日本バーチャルリアリティ学会論文誌},
volume = {27},
number = {4},
pages = {381–384},
abstract = {This paper proposes a humanoid cybernetic avatar (CA) that can replicate and extend human presence inexpensively and create social interactions that are difficult to simulate among humans. Standard life-size humanoid robots are expensive and have the disadvantage of being difficult to customize and use multiple units. Therefore, we constructed a humanoid robot with an inflatable structure, omitting work and walking abilities and focusing only on appearance and gestures. Humanoid inflatable CAs are lightweight, contact-safe, foldable when deflated, and can be customized in shape and texture at low cost. The social interactions enabled by such robots are discussed and categorized.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This paper proposes a humanoid cybernetic avatar (CA) that can replicate and extend human presence inexpensively and create social interactions that are difficult to simulate among humans. Standard life-size humanoid robots are expensive and have the disadvantage of being difficult to customize and use multiple units. Therefore, we constructed a humanoid robot with an inflatable structure, omitting work and walking abilities and focusing only on appearance and gestures. Humanoid inflatable CAs are lightweight, contact-safe, foldable when deflated, and can be customized in shape and texture at low cost. The social interactions enabled by such robots are discussed and categorized.
19.
Fumiya Nakano, Ryuma Niiyama, Shunji Yamanaka
Flexible Sliding-teeth-array Mechanism for Hollow Joint Module with Smooth Outline Proceedings
2022.
Abstract | BibTeX | タグ: | Links:
@proceedings{Nakano2022_SII,
title = {Flexible Sliding-teeth-array Mechanism for Hollow Joint Module with Smooth Outline},
author = {Fumiya Nakano, Ryuma Niiyama, Shunji Yamanaka},
doi = {10.1109/SII52469.2022.9708806},
year = {2022},
date = {2022-01-11},
urldate = {2022-01-11},
abstract = {This study proposes a flex-hollow mechanism that maintains a smooth silhouette while it stretches and bends. In general, robots with moving mechanisms are either of a combination of rigid parts or a mechanism covered with passively deforming soft material. Thus, it is challenging to make robots inherently flexible and smooth. The key feature of our mechanism is an array of longitudinally extending teeth that bend by sliding along each other. This array also functions as a structural load-bearing exterior. Our smooth, hollow sliding-teeth-array is a simple active module that can contain other robot components. In this paper, we first provide an overview of this mechanism and a simple theoretical model. Then, we display the physical characteristics of the model utilizing a 3D printed prototype composed of flexible parts.},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
This study proposes a flex-hollow mechanism that maintains a smooth silhouette while it stretches and bends. In general, robots with moving mechanisms are either of a combination of rigid parts or a mechanism covered with passively deforming soft material. Thus, it is challenging to make robots inherently flexible and smooth. The key feature of our mechanism is an array of longitudinally extending teeth that bend by sliding along each other. This array also functions as a structural load-bearing exterior. Our smooth, hollow sliding-teeth-array is a simple active module that can contain other robot components. In this paper, we first provide an overview of this mechanism and a simple theoretical model. Then, we display the physical characteristics of the model utilizing a 3D printed prototype composed of flexible parts.
23.
Hiroki Tomioka, Masahiro Ikeda, Keung Or, Ryuma Niiyama, Yasuo Kuniyoshi
Autonomous Wheeled Locomotion on Irregular Terrain with Tactile Sensing Proceedings
2022.
Abstract | BibTeX | タグ: | Links:
@proceedings{Tomioka2022_CLAWAR,
title = {Autonomous Wheeled Locomotion on Irregular Terrain with Tactile Sensing},
author = {Hiroki Tomioka, Masahiro Ikeda, Keung Or, Ryuma Niiyama, Yasuo Kuniyoshi},
doi = {10.1007/978-3-031-15226-9_13},
year = {2022},
date = {2022-09-13},
urldate = {2022-09-13},
abstract = {Adopting the concept of the tactile wheel, which considers the interaction between the wheel and the ground, this paper simulates reinforcement learning to show the usefulness of tactile sensing for autonomous wheeled robots on irregular terrain and to clarify the characteristics of the information to be acquired. A wheeled robot model with a wheel-on-leg structure is created and tested on two types of irregular terrain. The tactile information from each wheel is used as part of the reinforcement learning state. The average return and sample efficiency respectively increase by factors of 1.18 and 2.21 on uneven terrain. On fractal terrain, they increase by factors of 1.31 and 2.51 times, respectively, confirming the usefulness of tactile information. Tactile wheels using analog tactile information perform better in terms of adaptability to unknown terrain.},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
Adopting the concept of the tactile wheel, which considers the interaction between the wheel and the ground, this paper simulates reinforcement learning to show the usefulness of tactile sensing for autonomous wheeled robots on irregular terrain and to clarify the characteristics of the information to be acquired. A wheeled robot model with a wheel-on-leg structure is created and tested on two types of irregular terrain. The tactile information from each wheel is used as part of the reinforcement learning state. The average return and sample efficiency respectively increase by factors of 1.18 and 2.21 on uneven terrain. On fractal terrain, they increase by factors of 1.31 and 2.51 times, respectively, confirming the usefulness of tactile information. Tactile wheels using analog tactile information perform better in terms of adaptability to unknown terrain.
26.
Kazuma Matsushita, Masahiro Ikeda, Keung Or, Ryuma Niiyama, Yasuo Kuniyoshi
An Actuation System Using a Hydrostatic Skeleton and a Shape Memory Alloy for Earthworm-like Soft Robots Proceedings
2022.
Abstract | BibTeX | タグ: | Links:
@proceedings{Matsushita2022_SII,
title = {An Actuation System Using a Hydrostatic Skeleton and a Shape Memory Alloy for Earthworm-like Soft Robots},
author = {Kazuma Matsushita, Masahiro Ikeda, Keung Or, Ryuma Niiyama, Yasuo Kuniyoshi},
doi = {10.1109/SII52469.2022.9708807},
year = {2022},
date = {2022-01-10},
urldate = {2022-01-10},
abstract = {Numerous soft robots that mimic living organisms have been proposed. Earthworm robots are a type of robots that imitate the peristaltic locomotion of earthworms. Engineering reproduction of the burrowing motion of earthworms is useful for soil investigation and stirring of the particles in the soil. In this study, a novel compact actuation system that can be mounted on small earthworm-like robots was developed. The system can output axial extension force and is suitable for enabling earthworm-like robots to drive peristaltic locomotion in soil. The actuation system for an earthworm robot was fabricated by reproducing the hydrostatic skeleton and circumferential muscle arrangement of the earthworm using a water-filled rubber-like resin and shape memory alloy (SMA). We confirmed that the proposed system can output the axial extension force by applying an electric current to the SMA of the actuation system. Thus, the fabricated actuation system is useful for earthworm-like robots that dig holes. This system can be extensively used in earthworm-like as well as small soft robots to easily obtain the extension force.},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
Numerous soft robots that mimic living organisms have been proposed. Earthworm robots are a type of robots that imitate the peristaltic locomotion of earthworms. Engineering reproduction of the burrowing motion of earthworms is useful for soil investigation and stirring of the particles in the soil. In this study, a novel compact actuation system that can be mounted on small earthworm-like robots was developed. The system can output axial extension force and is suitable for enabling earthworm-like robots to drive peristaltic locomotion in soil. The actuation system for an earthworm robot was fabricated by reproducing the hydrostatic skeleton and circumferential muscle arrangement of the earthworm using a water-filled rubber-like resin and shape memory alloy (SMA). We confirmed that the proposed system can output the axial extension force by applying an electric current to the SMA of the actuation system. Thus, the fabricated actuation system is useful for earthworm-like robots that dig holes. This system can be extensively used in earthworm-like as well as small soft robots to easily obtain the extension force.
2021
6.
Kazutoshi Tanaka, Satoshi Nishikawa, Ryuma Niiyama, Yasuo Kuniyoshi
Immediate generation of jump-and-hit motions by a pneumatic humanoid robot using a lookup table of learned dynamics Journal Article
In: IEEE Robotics and Automation Letters, vol. 6, no. 3, pp. 5557–5564, 2021.
Abstract | BibTeX | タグ: | Links:
@article{Tanaka2021,
title = {Immediate generation of jump-and-hit motions by a pneumatic humanoid robot using a lookup table of learned dynamics},
author = {Kazutoshi Tanaka, Satoshi Nishikawa, Ryuma Niiyama, Yasuo Kuniyoshi},
doi = {10.1109/LRA.2021.3076959},
year = {2021},
date = {2021-04-30},
urldate = {2021-04-30},
journal = {IEEE Robotics and Automation Letters},
volume = {6},
number = {3},
pages = {5557–5564},
abstract = {This letter focuses on the jump-and-hit motion of a humanoid robot, wherein a robot instantaneously jumps forward and hits a flying ball in the air, similar to how human players behave in volleyball games. We propose a Immediate Motion generation using a Lookup table of learned dynamics (IMoLo) for generating the motions of a pneumatic humanoid robot. To test this method, we developed a humanoid robot called “Liberobot” with eight joints applying structure-integrated pneumatic cable cylinders. Using simulations, the prediction errors of the robot hand positions during the jump-and-hit motions measured via nonlinear interpolation when using IMoLo was smaller than without it in cases having a small number of training trials. In the experiments, the robot jumped and hit the flying ball 16 times out of 20 trials using the proposed motion generation method. The results indicate that a pneumatic humanoid robot using IMoLo can instantaneously perform dynamic whole-body motions, such as jump-and-hit motions, with a changing target within a specified time. Our humanoid robot is the first pneumatic humanoid robot capable of executing such dynamic motions.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This letter focuses on the jump-and-hit motion of a humanoid robot, wherein a robot instantaneously jumps forward and hits a flying ball in the air, similar to how human players behave in volleyball games. We propose a Immediate Motion generation using a Lookup table of learned dynamics (IMoLo) for generating the motions of a pneumatic humanoid robot. To test this method, we developed a humanoid robot called “Liberobot” with eight joints applying structure-integrated pneumatic cable cylinders. Using simulations, the prediction errors of the robot hand positions during the jump-and-hit motions measured via nonlinear interpolation when using IMoLo was smaller than without it in cases having a small number of training trials. In the experiments, the robot jumped and hit the flying ball 16 times out of 20 trials using the proposed motion generation method. The results indicate that a pneumatic humanoid robot using IMoLo can instantaneously perform dynamic whole-body motions, such as jump-and-hit motions, with a changing target within a specified time. Our humanoid robot is the first pneumatic humanoid robot capable of executing such dynamic motions.
7.
Kazuya Saito, Hiroto Nagai, Kai Suto, Naoki Ogawa, Young ah Seong, Tomohiro Tachi, Ryuma Niiyama, Yoshihiro Kawahara
Insect wing 3D printing Journal Article
In: Scientific reports, vol. 11, no. 1, pp. 1–8 (18631), 2021.
Abstract | BibTeX | タグ: | Links:
@article{Saito2022,
title = {Insect wing 3D printing},
author = {Kazuya Saito, Hiroto Nagai, Kai Suto, Naoki Ogawa, Young ah Seong, Tomohiro Tachi, Ryuma Niiyama, Yoshihiro Kawahara},
doi = {10.1038/s41598-021-98242-y},
year = {2021},
date = {2021-10-14},
urldate = {2021-10-14},
journal = {Scientific reports},
volume = {11},
number = {1},
pages = {1–8 (18631)},
abstract = {Insects have acquired various types of wings over their course of evolution and have become the most successful terrestrial animals. Consequently, the essence of their excellent environmental adaptability and locomotive ability should be clarified; a simple and versatile method to artificially reproduce the complex structure and various functions of these innumerable types of wings is necessary. This study presents a simple integral forming method for an insect-wing-type composite structure by 3D printing wing frames directly onto thin films. The artificial venation generation algorithm based on the centroidal Voronoi diagram, which can be observed in the wings of dragonflies, was used to design the complex mechanical properties of artificial wings. Furthermore, we implemented two representative functions found in actual insect wings: folding and coupling. The proposed crease pattern design software developed based on a beetle hindwing enables the 3D printing of foldable wings of any shape. In coupling-type wings, the forewing and hindwing are connected to form a single large wing during flight; these wings can be stored compactly by disconnecting and stacking them like cicada wings.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Insects have acquired various types of wings over their course of evolution and have become the most successful terrestrial animals. Consequently, the essence of their excellent environmental adaptability and locomotive ability should be clarified; a simple and versatile method to artificially reproduce the complex structure and various functions of these innumerable types of wings is necessary. This study presents a simple integral forming method for an insect-wing-type composite structure by 3D printing wing frames directly onto thin films. The artificial venation generation algorithm based on the centroidal Voronoi diagram, which can be observed in the wings of dragonflies, was used to design the complex mechanical properties of artificial wings. Furthermore, we implemented two representative functions found in actual insect wings: folding and coupling. The proposed crease pattern design software developed based on a beetle hindwing enables the 3D printing of foldable wings of any shape. In coupling-type wings, the forewing and hindwing are connected to form a single large wing during flight; these wings can be stored compactly by disconnecting and stacking them like cicada wings.
10.
Lai Chen, Takuya Sasatani, Keung Or, Satoshi Nishikawa, Yoshihiro Kawahara, Ryuma Niiyama, Yasuo Kuniyoshi
Wireless powered dielectric elastomer actuator Journal Article
In: IEEE Robotics and Automation Letters, vol. 6, no. 4, pp. 7278–7274, 2021.
Abstract | BibTeX | タグ: | Links:
@article{Chen2021,
title = {Wireless powered dielectric elastomer actuator},
author = {Lai Chen, Takuya Sasatani, Keung Or, Satoshi Nishikawa, Yoshihiro Kawahara, Ryuma Niiyama, Yasuo Kuniyoshi},
doi = {10.1109/LRA.2021.3097271},
year = {2021},
date = {2021-07-14},
urldate = {2021-07-14},
journal = {IEEE Robotics and Automation Letters},
volume = {6},
number = {4},
pages = {7278–7274},
abstract = {The need for cable connection with soft robotic systems suppresses the benefits granted by their softness and flexibility. Such systems can be untethered by equipping batteries or by relying on non-electrical actuation mechanisms. However, these approaches cannot simultaneously support long-term and intelligent operations. This research examines a proposed wireless soft actuator based on wireless power transfer (WPT) and dielectric elastomer actuator (DEA) technology, thereby realizing soft robomore diversified application and long-term locomotion. A compact conical DEA fabrication process is presented with 6 mm periodic linear output and design of a lightweight WPT receiver that weighs only 13 g integrated with a driver circuit. Evaluation results show that this system remotely powers the DEA and the intelligent peripheral circuits for system control. Furthermore, our design seamlessly bridges the WPT system, power-efficient in low-voltage output conditions, and the DEA, which requires high-voltage input (kV) for deformation, by leveraging high-voltage boost-converters. Experimentally obtained results demonstrate untethered DEA operation at 170 mm from the transmitter. Also, we demonstrated applying this DEA as a wireless pump.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The need for cable connection with soft robotic systems suppresses the benefits granted by their softness and flexibility. Such systems can be untethered by equipping batteries or by relying on non-electrical actuation mechanisms. However, these approaches cannot simultaneously support long-term and intelligent operations. This research examines a proposed wireless soft actuator based on wireless power transfer (WPT) and dielectric elastomer actuator (DEA) technology, thereby realizing soft robomore diversified application and long-term locomotion. A compact conical DEA fabrication process is presented with 6 mm periodic linear output and design of a lightweight WPT receiver that weighs only 13 g integrated with a driver circuit. Evaluation results show that this system remotely powers the DEA and the intelligent peripheral circuits for system control. Furthermore, our design seamlessly bridges the WPT system, power-efficient in low-voltage output conditions, and the DEA, which requires high-voltage input (kV) for deformation, by leveraging high-voltage boost-converters. Experimentally obtained results demonstrate untethered DEA operation at 170 mm from the transmitter. Also, we demonstrated applying this DEA as a wireless pump.
16.
Ryuma Niiyama, Young Ah Seong, Yoshihiro Kawahara, Yasuo Kuniyoshi
Blower-powered Soft Inflatable Joints for Physical Human-Robot Interaction Journal Article
In: Frontiers in Robotics and AI, vol. 8, pp. 1–12 (720683), 2021.
Abstract | BibTeX | タグ: | Links:
@article{Niiyama2021_InflatableRobot,
title = {Blower-powered Soft Inflatable Joints for Physical Human-Robot Interaction},
author = {Ryuma Niiyama, Young Ah Seong, Yoshihiro Kawahara, Yasuo Kuniyoshi},
doi = {10.3389/frobt.2021.720683},
year = {2021},
date = {2021-08-24},
urldate = {2021-08-24},
journal = {Frontiers in Robotics and AI},
volume = {8},
pages = {1–12 (720683)},
abstract = { Inflatables are safe and lightweight structures even at the human scale. Inflatable robots are expected to be applied to physical human-robot interaction (pHRI). Although active joint mechanisms are essential for developing inflatable robots, the existing mechanisms are complex in structure and it is difficult to integrate actuators, which diminish the advantages of inflatables. This study proposes blower-powered soft inflatable joints that are easy to fabricate and contain enough space for an actuation inside. The joints are driven by tendon wires pulled by linear actuators. We derived a theoretical model for both unilateral and bilateral joints and demonstrated a hugging robot with multiple joints as an application of the proposed joint mechanism. The novelty of the proposed joint mechanism and the inflatable robot is that rigid parts have been thoroughly eliminated and the tendons for actuation have been successfully hidden inside. Moreover, the active control of the internal pressure makes inflatables resistant to punctures. We expect that the contact safety of inflatable robots will facilitate advancement of the pHRI field},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Inflatables are safe and lightweight structures even at the human scale. Inflatable robots are expected to be applied to physical human-robot interaction (pHRI). Although active joint mechanisms are essential for developing inflatable robots, the existing mechanisms are complex in structure and it is difficult to integrate actuators, which diminish the advantages of inflatables. This study proposes blower-powered soft inflatable joints that are easy to fabricate and contain enough space for an actuation inside. The joints are driven by tendon wires pulled by linear actuators. We derived a theoretical model for both unilateral and bilateral joints and demonstrated a hugging robot with multiple joints as an application of the proposed joint mechanism. The novelty of the proposed joint mechanism and the inflatable robot is that rigid parts have been thoroughly eliminated and the tendons for actuation have been successfully hidden inside. Moreover, the active control of the internal pressure makes inflatables resistant to punctures. We expect that the contact safety of inflatable robots will facilitate advancement of the pHRI field
22.
Hiroki Noda, Satoshi Nishikawa, Ryuma Niiyama, Yasuo Kuniyoshi
Competitive Physical Interaction by Reinforcement Learning Agents Using Intention Estimation Proceedings
2021.
Abstract | BibTeX | タグ: | Links:
@proceedings{Noda2021_RO-MAN,
title = {Competitive Physical Interaction by Reinforcement Learning Agents Using Intention Estimation},
author = {Hiroki Noda, Satoshi Nishikawa, Ryuma Niiyama, Yasuo Kuniyoshi},
doi = {10.1109/RO-MAN50785.2021.9515411},
year = {2021},
date = {2021-08-10},
urldate = {2021-08-10},
abstract = {The physical human–robot interaction (pHRI) research field is expected to contribute to competitive and cooperative human–robot tasks that involve force interactions. However, compared with human–human interactions, current pHRI approaches lack tactical considerations. Current approaches do not estimate intentions from human behavior and do not select policies that are appropriate for the opponent’s changing policy. For this reason, we propose a reinforcement learning model that estimates the opponent’s changing policy using time-series observations and expresses the agent’s policy in a common latent space, referring to descriptions of tactics in open-skill sports. We verify the performance of the reinforcement learning agent using two novel physical and competitive environments, push-hand game and air-hockey. From this, we confirm that the latent space works properly for policy information because each latent variable that represents the machine agent’s own policy and that of the opponent affects the behavior of the agent. Two latent variables can clearly express how the agent estimates the opponent’s policy and decides its own policy.},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
The physical human–robot interaction (pHRI) research field is expected to contribute to competitive and cooperative human–robot tasks that involve force interactions. However, compared with human–human interactions, current pHRI approaches lack tactical considerations. Current approaches do not estimate intentions from human behavior and do not select policies that are appropriate for the opponent’s changing policy. For this reason, we propose a reinforcement learning model that estimates the opponent’s changing policy using time-series observations and expresses the agent’s policy in a common latent space, referring to descriptions of tactics in open-skill sports. We verify the performance of the reinforcement learning agent using two novel physical and competitive environments, push-hand game and air-hockey. From this, we confirm that the latent space works properly for policy information because each latent variable that represents the machine agent’s own policy and that of the opponent affects the behavior of the agent. Two latent variables can clearly express how the agent estimates the opponent’s policy and decides its own policy.
29.
Ryota Morimoto, Satoshi Nishikawa, Ryuma Niiyama, Yasuo Kuniyoshi
Model-Free Reinforcement Learning with Ensemble for a Soft Continuum Robot Arm Proceedings
2021.
Abstract | BibTeX | タグ: | Links:
@proceedings{Morimoto2021_Robosoft,
title = {Model-Free Reinforcement Learning with Ensemble for a Soft Continuum Robot Arm},
author = {Ryota Morimoto, Satoshi Nishikawa, Ryuma Niiyama, Yasuo Kuniyoshi},
doi = {10.1109/RoboSoft51838.2021.9479340},
year = {2021},
date = {2021-04-14},
urldate = {2021-04-14},
abstract = {Soft robots have more passive degrees of freedom (DoFs) than rigid-body robots, which makes controller design difficult. Model-free reinforcement learning (RL) is a promising tool to resolve control problems in soft robotics alongside detailed and elaborate modeling. However, the adaptation of RL to soft robots requires consideration of the unique nature of soft bodies. In this work, a continuum robot arm is used as an example of a soft robot, and we propose an Ensembled Light-weight model-Free reinforcement learning Network (ELFNet), which is an RL framework with a computationally light ensemble. We demonstrated that the proposed system could learn control policies for a continuum robot arm to reach target positions using its tip not only in simulations but also in the real world. We used a pneumatically controlled continuum robot arm that operates with nine flexible rubber artificial muscles. Each artificial muscle can be controlled independently by pressure control valves, demonstrating that the policy can be learned using a real robot alone. We found that our method is more suitable for compliant robots than other RL methods because the sample efficiency is better than that of the other methods, and there is a significant difference in the performance when the number of passive DoFs is large. This study is expected to lead to the development of model-free RL in future soft robot control.},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
Soft robots have more passive degrees of freedom (DoFs) than rigid-body robots, which makes controller design difficult. Model-free reinforcement learning (RL) is a promising tool to resolve control problems in soft robotics alongside detailed and elaborate modeling. However, the adaptation of RL to soft robots requires consideration of the unique nature of soft bodies. In this work, a continuum robot arm is used as an example of a soft robot, and we propose an Ensembled Light-weight model-Free reinforcement learning Network (ELFNet), which is an RL framework with a computationally light ensemble. We demonstrated that the proposed system could learn control policies for a continuum robot arm to reach target positions using its tip not only in simulations but also in the real world. We used a pneumatically controlled continuum robot arm that operates with nine flexible rubber artificial muscles. Each artificial muscle can be controlled independently by pressure control valves, demonstrating that the policy can be learned using a real robot alone. We found that our method is more suitable for compliant robots than other RL methods because the sample efficiency is better than that of the other methods, and there is a significant difference in the performance when the number of passive DoFs is large. This study is expected to lead to the development of model-free RL in future soft robot control.
30.
Tomoya Kimura, Ryuma Niiyama, Yasuo Kuniyoshi
Modularized genotype combination to design multiobjective soft-bodied robots Proceedings
2021.
Abstract | BibTeX | タグ: | Links:
@proceedings{Kimura2021_Robosoft,
title = {Modularized genotype combination to design multiobjective soft-bodied robots},
author = {Tomoya Kimura, Ryuma Niiyama, Yasuo Kuniyoshi},
doi = {10.1109/RoboSoft51838.2021.9479428},
year = {2021},
date = {2021-04-14},
urldate = {2021-04-14},
abstract = {The evolutionary method is an approach to the difficulties of designing soft-bodied robots. One of the prominent methods is compositional pattern producing network with neuroevolution of augmenting topologies (CPPN-NEAT). How-ever, previous research has focused on single-function robots, and the design of multi-functional robots is still unsolved. This study provides a method for generating multi-functional robots by combining the genotype networks of single-functional robots in a modular manner. The proposed method includes the addition of a weight layer during network combination and the selection of populations with a fitness estimator. We conducted experiments to design voxel-based creatures that can perform two types of tasks in the simulation. Target tasks include terrestrial and aquatic locomotion. The results show that the proposed method was able to search for a form that satisfied the two tasks simultaneously faster than the existing methods. Observations of the generated populations indicated that the proposed method enables the efficient exploration of body morphology. Further, a modularized combination helps focus the exploration in a feasible morphology space. Finally, we fabricated evolved soft creatures in the real world as soft-bodied robots by limiting the arrangement of actuation voxels. We believe that the proposed method of designing a multi-functional robot while utilizing existing single-functional robots will contribute to the automatic design of multi-functional soft robots.},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
The evolutionary method is an approach to the difficulties of designing soft-bodied robots. One of the prominent methods is compositional pattern producing network with neuroevolution of augmenting topologies (CPPN-NEAT). How-ever, previous research has focused on single-function robots, and the design of multi-functional robots is still unsolved. This study provides a method for generating multi-functional robots by combining the genotype networks of single-functional robots in a modular manner. The proposed method includes the addition of a weight layer during network combination and the selection of populations with a fitness estimator. We conducted experiments to design voxel-based creatures that can perform two types of tasks in the simulation. Target tasks include terrestrial and aquatic locomotion. The results show that the proposed method was able to search for a form that satisfied the two tasks simultaneously faster than the existing methods. Observations of the generated populations indicated that the proposed method enables the efficient exploration of body morphology. Further, a modularized combination helps focus the exploration in a feasible morphology space. Finally, we fabricated evolved soft creatures in the real world as soft-bodied robots by limiting the arrangement of actuation voxels. We believe that the proposed method of designing a multi-functional robot while utilizing existing single-functional robots will contribute to the automatic design of multi-functional soft robots.
31.
Yuhu Liu, Satoshi Nishikawa, Young ah Seong, Ryuma Niiyama, Yasuo Kuniyoshi
ThermoCaress: A Wearable Haptic Device with Illusory Moving Thermal Stimulation Proceedings
2021.
Abstract | BibTeX | タグ: | Links:
@proceedings{Liu2021_CHI,
title = {ThermoCaress: A Wearable Haptic Device with Illusory Moving Thermal Stimulation},
author = {Yuhu Liu, Satoshi Nishikawa, Young ah Seong, Ryuma Niiyama, Yasuo Kuniyoshi},
doi = {10.1145/3411764.3445777},
year = {2021},
date = {2021-05-10},
urldate = {2021-05-10},
abstract = {We propose ThermoCaress, a haptic device to create a stroking sensation on the forearm using pressure force and present thermal feedback simultaneously. In our method, based on the phenomenon of thermal referral, by overlapping a stroke of pressure force, users feel as if the thermal stimulation moves although the position of temperature source is static. We designed the device to be compact and soft, using microblowers and inflatable pouches for presenting pressure force and water for presenting thermal feedback. Our user study showed that the device succeeded in generating thermal referrals and creating a moving thermal illusion. The results also suggested that cold temperature enhance the pleasantness of stroking. Our findings contribute to expanding the potential of thermal haptic devices.},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
We propose ThermoCaress, a haptic device to create a stroking sensation on the forearm using pressure force and present thermal feedback simultaneously. In our method, based on the phenomenon of thermal referral, by overlapping a stroke of pressure force, users feel as if the thermal stimulation moves although the position of temperature source is static. We designed the device to be compact and soft, using microblowers and inflatable pouches for presenting pressure force and water for presenting thermal feedback. Our user study showed that the device succeeded in generating thermal referrals and creating a moving thermal illusion. The results also suggested that cold temperature enhance the pleasantness of stroking. Our findings contribute to expanding the potential of thermal haptic devices.
33.
Yuta Horii, Katsuma Inoue, Satoshi Nishikawa, Kohei Nakajima, Ryuma Niiyama, Yasuo Kuniyoshi
Physical reservoir computing in a soft swimming robot Proceedings
2021.
Abstract | BibTeX | タグ: | Links:
@proceedings{Horii2021_ALIFE,
title = {Physical reservoir computing in a soft swimming robot},
author = {Yuta Horii, Katsuma Inoue, Satoshi Nishikawa, Kohei Nakajima, Ryuma Niiyama, Yasuo Kuniyoshi},
doi = {10.1162/isal_a_00426},
year = {2021},
date = {2021-07-19},
urldate = {2021-07-19},
abstract = {In recent years, swimming robots have been developed to achieve efficient propulsion and high maneuverability that are possessed naturally by fish. Previous studies have attempted to achieve swimming similar to fish by control based on physical models and top-down architectures, but have encountered problems due to the high complexity of the underwater environment. Several research works have tried to overcome these problems by exploiting embodiment—that is, by mimicking the physical properties of fish. To achieve more intelligent swimming from the perspective of the embodiment, we focused on a framework called physical reservoir computing (PRC). This framework allows us to utilize physical dynamics as a computational resource. In this study, we propose a soft sheet-like swimming robot and a PRC-based architecture that can be used to emulate swimming motions by exploiting its own body dynamics for closed-loop control. Through experiments, we demonstrated that our system satisfies the properties required for learning swimming motion through supervised learning. We also succeeded in robust motion generation and environmental state estimation, opening up future prospects for more intelligent robot control and sensing.},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
In recent years, swimming robots have been developed to achieve efficient propulsion and high maneuverability that are possessed naturally by fish. Previous studies have attempted to achieve swimming similar to fish by control based on physical models and top-down architectures, but have encountered problems due to the high complexity of the underwater environment. Several research works have tried to overcome these problems by exploiting embodiment—that is, by mimicking the physical properties of fish. To achieve more intelligent swimming from the perspective of the embodiment, we focused on a framework called physical reservoir computing (PRC). This framework allows us to utilize physical dynamics as a computational resource. In this study, we propose a soft sheet-like swimming robot and a PRC-based architecture that can be used to emulate swimming motions by exploiting its own body dynamics for closed-loop control. Through experiments, we demonstrated that our system satisfies the properties required for learning swimming motion through supervised learning. We also succeeded in robust motion generation and environmental state estimation, opening up future prospects for more intelligent robot control and sensing.