@inproceedings{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},

booktitle = {IEEE/SICE International Symposium on System Integration (SII)},

pages = {88-95 (WedA1T2.7)},

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 = {inproceedings}

}

@inproceedings{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},

booktitle = {IEEE/SICE International Symposium on System Integration (SII)},

pages = {211-215 (WedP1T2.1)},

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 = {inproceedings}

}

@inproceedings{Yamauchi2025_RCAR,

title = {A Snap Mechanism Imitating the Thoracic Joint of a Click Beetle},

author = {Kanta Yamauchi; Takahiro Matsuno; Ryuma Niiyama; Shinichi Hirai},

doi = {10.1109/RCAR65431.2025.11139521},

year  = {2025},

date = {2025-06-01},

urldate = {2025-06-01},

booktitle = {IEEE International Conference on Real-time Computing and Robotics (RCAR)},

pages = {769-774},

abstract = {In this study, we focused on the thoracic joint of a click beetle and proposed a two-link type snap mechanism. This mechanism mimics the click beetle's principle for storing and releasing elastic energy, and is composed of links, springs, motors, viscoelastic peg, etc. This mechanism normally functions as a general active joint, and can generate snap rotational motion at any time. The developed snap mechanism was likened to a click beetle and the relationships between the mechanism's parameter and jumping characteristics were validated. As a result, we confirmed that the size of the mechanism, weight distribution, and hardness of the ground affect the jumping performance.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{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},

booktitle = {IEEE/SICE International Symposium on System Integration (SII)},

pages = {199-204 (WedP1T1.6)},

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 = {inproceedings}

}

@inproceedings{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},

booktitle = {IEEE/SICE International Symposium on System Integrations (SII)},

pages = {1318-1323 (FriP1T2.5)},

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 = {inproceedings}

}

@inproceedings{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},

booktitle = {IEEE/SICE International Symposium on System Integration (SII)},

pages = {42-47 (TueAK2.2)},

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 = {inproceedings}

}

@inproceedings{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 = {11416-11421 (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 = {inproceedings}

}

@inproceedings{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},

booktitle = {IEEE-RAS International Conference on Soft Robotics (RoboSoft)},

pages = {579-585 (TuPo1S.4)},

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 = {inproceedings}

}

@inproceedings{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},

booktitle = {IEEE/SICE International Symposium on System Integration (SII)},

pages = {434-439 (TuAT3.3)},

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 = {inproceedings}

}

@inproceedings{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},

booktitle = {International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines（CLAWAR）},

pages = {107-118 (S8)},

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 = {inproceedings}

}

@inproceedings{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},

booktitle = {IEEE/SICE International Symposium on System Integration (SII) },

pages = {47-52 (MoAT2.2)},

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 = {inproceedings}

}

@inproceedings{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},

booktitle = {IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)},

pages = {649-656 (TuP2T4.4)},

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 = {inproceedings}

}

@inproceedings{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},

booktitle = {IEEE International Conference on Soft Robotics (RoboSoft)},

pages = {141-148},

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 = {inproceedings}

}

@inproceedings{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},

booktitle = {IEEE International Conference on Soft Robotics (RoboSoft)},

pages = {295-301},

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 = {inproceedings}

}

@inproceedings{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},

booktitle = {ACM Proceedings of the CHI Conference on Human Factors in Computing Systems（CHI）},

number = {214},

pages = {1-12 (214)},

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 = {inproceedings}

}

@inproceedings{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},

booktitle = {Conference on Artificial Life（ALIFE）},

volume = {33},

pages = {92-100 (isal 2021; 92)},

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 = {inproceedings}

}