[17] Ikemoto S, DallaLibera F and Hosoda K (2017), "Noise-modulated Neural Networks as an Application of Stochastic Resonance", Neurocomputing. Vol. In Press
[Abstract] [BibTeX] [DOI]
|
Abstract: Stochastic resonance (SR) is a phenomenon by which the input signal of a nonlinear system, with magnitude too small to affect the output, becomes observable by adding a non-zero level of noise to the system. SR is known to assist biological beings in coping with noisy environments, providing sophisticated information processing and adaptive behaviors. The SR effect can be interpreted as a decrease in the input-output information loss of a nonlinear system by making it stochastically closer to a linear system. This work shows how SR can improve the performance of a system even when the desired input-output relationship is nonlinear, specifically for the case of a neural networks whose hidden layers consist of threshold functions. Universal approximation capability of neural networks exploiting SR is then discussed: although a network consisting of threshold activation functions has been proven to be an universal approximator in the context of the extreme learning machine (ELM), once SR is taken into account, the system can be deemed as a classic three-layer neural network whose universality has been previously proven by simpler proofs. After proving the universal approximation capability for an infinite number of hidden units, the performance achieved with a finite number of hidden units is evaluated using two training algorithms, namely backpropagation and ELM. Results highlight the SR effect occurring in the proposed system, and the relationship among the number of hidden units, noise intensity, and approximation performance.
|
BibTeX:
@article{ikemoto2017noise,
author = {Shuhei Ikemoto and Fabio DallaLibera and Koh Hosoda},
title = {Noise-modulated Neural Networks as an Application of Stochastic Resonance},
journal = {Neurocomputing},
year = {2017},
volume = {In Press},
doi = {10.1016/j.neucom.2016.12.111}
}
|
[16] Shin H, Saito H, Kawakami T, Yamanishi S, Ikemoto S and Hosoda K (2016), "Development of an embedded sensor system as pneumatic artificial muscle proprioceptors", Artificial Life and Robotics. Vol. 21(4), pp. 486-492.
[Abstract] [BibTeX]
|
| Abstract: Spinal reflexes greatly contribute to the control of fast physical interactions (e.g., catching a moving ball) without the influence of higher level control systems involved in human motor control. Therefore, to realize the interactions in robots, it is a useful approach to mimic the nervous system controlling spinal reflexes. To this end, as the starting point for creating spinal reflexes, sensors that measure and encode body movements similar to human proprioceptors are needed to generate signals for the spinal reflexes. In this study, we developed artificial muscle proprioceptors to reproduce spinal reflexes in robots. In particular, we focused on pneumatic artificial muscles and designed an artificial muscle spindle and an artificial Golgi tendon organ, which were integrated with a pneumatic artificial muscle. A compact local measuring system consisting of a microcomputer and amplifiers was developed to easily install and organize the sensors. |
BibTeX:
@article{shin2016development,
author = {Hirofumi Shin and Hajime Saito and Takahiko Kawakami and Satoshi Yamanishi and Shuhei Ikemoto and Koh Hosoda},
title = {Development of an embedded sensor system as pneumatic artificial muscle proprioceptors},
journal = {Artificial Life and Robotics},
year = {2016},
volume = {21},
number = {4},
pages = {486-492}
}
|
[15] Shirafuji S, Ikemoto S and Hosoda K (2016), "Designing Non-circular Pulleys to Realize Target Motion between Two Joints", IEEE/ASME Transactions on Mechatronics., February, 2016. Vol. 22(1), pp. 487-497.
[Abstract] [BibTeX] [DOI]
|
| Abstract: Many mechanisms reduce the number of inputs for their target motions by restricting the motions of pairs of joints. This study designs a novel constraint mechanism using a pair of noncircular pulleys and a wire. The wire restricts the motion of the joints to the target motion while enabling a compact structure. We analytically derive the shape of the noncircular pulleys using the desired relation between the joints and the lengths of their moment arms. The usability of the proposed mechanism is evaluated on a robotic leg, which maintains the height and posture of its upper body under the constraints. |
BibTeX:
@article{shirafuji2016designing,
author = {Shouhei Shirafuji and Shuhei Ikemoto and Koh Hosoda},
title = {Designing Non-circular Pulleys to Realize Target Motion between Two Joints},
journal = {IEEE/ASME Transactions on Mechatronics},
year = {2016},
volume = {22},
number = {1},
pages = {487-497}
}
|
[14] Ikemoto S, Kimoto Y and Hosoda K (2015), "Shoulder complex linkage mechanism for humanlike musculoskeletal robot arms", Bioinspiration & Biomimetics. Vol. In Press
[Abstract] [BibTeX]
|
| Abstract: The shoulder complex in the human body consists of the scapula, clavicle, humerus, and thorax and bears the load imposed by arm movements while at the same time realizing a wide range of motions. To mimic and exploit its role, several musculoskeletal robot arms with shoulder complex mechanisms have been developed. However, although many research groups have tried to design the structures using links and joints that faithfully correspond to the bones and joints in the human shoulder complex, its function has not been successfully reproduced because biologically plausible designs seriously compromise engineering plausibility. In this paper, we propose a linkage mechanism that can reproduce complex three-dimensional scapulo movements and considers the trade-off between biological and engineering plausibilities. Subsequently, the design was validated by driving the mechanism using pneumatic artificial muscles placed similarly to muscles in humans. Further, we present experiments in which the robot was controlled by surface electromyographic signals from a human. We show that the proposed design, due to its kinematic similarity with human musculoskeletal systems, eases the conversion between the surface electromyogram signals and the pneumatic artificial muscles (PAM) control inputs. |
BibTeX:
@article{Ikemoto2015shoulder,
author = {Shuhei Ikemoto and Yuya Kimoto and Koh Hosoda},
title = {Shoulder complex linkage mechanism for humanlike musculoskeletal robot arms},
journal = {Bioinspiration & Biomimetics},
year = {2015},
volume = {In Press}
}
|
[13] Koyama N, Ikemoto S and Hosoda K (2015), "Parameter Tuning in the Application of Stochastic Resonance to Redundant Sensor Systems", Journal of robotics and mechatoronics. Vol. 27(3), pp. 251-258.
[Abstract] [BibTeX]
|
| Abstract: Stochastic resonance (SR) is a phenomenon by which the addition of random noise improves the detection of weak signals. Thus far, this phenomenon has been extensively studied with the aim of improving sensor sensitivity in various fields of engineering research. However, the possibility of actual application of SR has not been explored because the target signal has to be known in order to confirm the occurrence of SR. In this paper, we propose an optimization method for making SR usable in engineering applications. The underlying mechanism of the proposed method is investigated using information theory and numerical simulation. We developed a tactile sensing system based on the simulation results. The proposed method is applied to this system in order to optimize its parameters for exploiting SR. Results of the experiment show that the developed tactile sensing system successfully achieved higher sensitivity than a conventional system. |
BibTeX:
@article{koyama2015parameter,
author = {Nagisa Koyama and Shuhei Ikemoto and Koh Hosoda},
title = {Parameter Tuning in the Application of Stochastic Resonance to Redundant Sensor Systems},
journal = {Journal of robotics and mechatoronics},
year = {2015},
volume = {27},
number = {3},
pages = {251-258}
}
|
[12] Ito K, Hosoda K, Shimizu M, Ikemoto S, Kume S, Nagura T, Imanishi N, Aiso S, Jinzaki M and Ogihara N (2015), "Direct assessment of 3D foot bone kinematics using biplanar X-ray fluoroscopy and an automatic model registration method", Journal of foot and ankle research., 12, 2015. Vol. 8(1), pp. 21.
[Abstract] [BibTeX] [DOI]
|
| Abstract: Quantifying detailed 3-dimensional (3D) kinematics of the foot in contact with the ground during locomotion is crucial for understanding the biomechanical functions of the complex musculoskeletal structure of the foot. Biplanar X-ray fluoroscopic systems and model-based registration techniques have recently been employed to capture and visualise 3D foot bone movements in vivo, but such techniques have generally been performed manually. In the present study, we developed an automatic model-registration method with biplanar fluoroscopy for accurate measurement of 3D movements of the skeletal foot. |
BibTeX:
@article{Ito2015direct,
author = {Kohta Ito and Koh Hosoda and Masahiro Shimizu and Shuhei Ikemoto and Shinnosuke Kume and Takeo Nagura and Nobuaki Imanishi and Sadakazu Aiso and Masahiro Jinzaki and Naomichi Ogihara},
title = {Direct assessment of 3D foot bone kinematics using biplanar X-ray fluoroscopy and an automatic model registration method},
journal = {Journal of foot and ankle research},
year = {2015},
volume = {8},
number = {1},
pages = {21},
doi = {10.1186/s13047-015-0079-4}
}
|
[11] Shimizu T, Saegusa R, Ikemoto S, Ishiguro H and Metta G (2014), "Robust Sensorimotor Representation to Physical Interaction Changes in Humanoid Motion Learning", IEEE Transactions on Neural Networks and Learning Systems., 4, 2014. Vol. 26(5), pp. 1035-1047.
[Abstract] [BibTeX] [DOI]
|
| Abstract: This paper proposes a learning from demonstration system based on a motion feature, called phase transfer sequence. The system aims to synthesize the knowledge on humanoid whole body motions learned during teacher-supported interactions, and apply this knowledge during different physical interactions between a robot and its surroundings. The phase transfer sequence represents the temporal order of the changing points in multiple time sequences. It encodes the dynamical aspects of the sequences so as to absorb the gaps in timing and amplitude derived from interaction changes. The phase transfer sequence was evaluated in reinforcement learning of sitting-up and walking motions conducted by a real humanoid robot and compatible simulator. In both tasks, the robotic motions were less dependent on physical interactions when learned by the proposed feature than by conventional similarity measurements. Phase transfer sequence also enhanced the convergence speed of motion learning. Our proposed feature is original primarily because it absorbs the gaps caused by changes of the originally acquired physical interactions, thereby enhancing the learning speed in subsequent interactions. |
BibTeX:
@article{shimizu2014robust,
author = {Toshihiko Shimizu and Ryo Saegusa and Shuhei Ikemoto and Hiroshi Ishiguro and Giorgio Metta},
title = {Robust Sensorimotor Representation to Physical Interaction Changes in Humanoid Motion Learning},
journal = {IEEE Transactions on Neural Networks and Learning Systems},
year = {2014},
volume = {26},
number = {5},
pages = {1035-1047},
doi = {10.1109/TNNLS.2014.2333092}
}
|
[10] Ikemoto S, DallaLibera F, Hosoda K and Ishiguro H (2014), "Spurious Correlation as an Approximation of the Mutual Information between Redundant Outputs and an Unknown Input", Communications in Nonlinear Science and Numerical Simulation., October, 2014. Vol. 19(10), pp. 3611-3616.
[Abstract] [BibTeX] [DOI]
|
| Abstract: Stochastic resonance (SR) is a counterintuitive phenomenon, observed in a wide variety of nonlinear systems, for which the addition of noise of opportune magnitude can improve signal detection. Tuning the noise for maximizing the SR effect is important both for artificial and biological systems. In the case of artificial systems, full exploitation of the SR effect opens the possibility of measuring otherwise unmeasurable signals. In biology, identification of possible SR maximization mechanisms is of great interest for explaining the low-energy high-sensitivity perception capabilities often observed in animals. SR maximization approaches presented in literature use knowledge on the input signal (or stimulus, in the case of living beings), and maximize the mutual information between the input and the output signal. The input signal, however, is unknown in many practical settings. To cope with this problem, this paper introduces an approximation of the input-output mutual information based on the spurious correlation among a set of redundant units. A proof of the approximation, as well as numerical examples of its application are given. |
BibTeX:
@article{ikemoto2014spurious,
author = {Shuhei Ikemoto and Fabio DallaLibera and Koh Hosoda and Hiroshi Ishiguro},
title = {Spurious Correlation as an Approximation of the Mutual Information between Redundant Outputs and an Unknown Input},
journal = {Communications in Nonlinear Science and Numerical Simulation},
year = {2014},
volume = {19},
number = {10},
pages = {3611-3616},
doi = {10.1016/j.cnsns.2014.03.021}
}
|
[9] Shirafuji S, Ikemoto S and Hosoda K (2014), "Development of a tendon-driven robotic finger for an anthropomorphic robotic hand", The International Journal of Robotics Research. Vol. 33, pp. 677-693.
[Abstract] [BibTeX] [DOI]
|
| Abstract: Our paper proposes a tendon-driven robotic finger based on an anatomical model of a human finger and a suitable method for its analysis. Our study aims to realize an anthropomorphic robotic hand that has the same characteristics and dexterity as that of a human hand, and it also aims to identify the advantages of the human musculoskeletal structure for application to the design and control of robot manipulators. When designing an anthropomorphic robotic hand, several devices are required to apply the human finger structure to a tendon-driven robotic finger. Reasons for this include that one of the human finger muscles, namely, the lumbrical muscle, is situated between tendons, which is an unfavorable configuration for the tendon-driven mechanism. Second, unlike a standard pulley used in a tendon-driven mechanism, some moment arms of the human finger change nonlinearly according to the joint angle. In our robotic finger design, we address these difficulties by rearranging its tendons and develop a mechanism to change the moment arm. We also propose a method to analyze and control this robotic fingers coordinating joints using non-stretch branching tendons based on the human extensor mechanism with a virtual tendon Jacobian matrix and the advantage is that this constraint virtually reduces the degrees-of-freedom (DOF) of the mechanism. Further, we build a prototype to confirm its motion using this method. In addition, we show that the state with the reduced DOF can be lost by external forces acting on the mechanism, and this condition can be changed manually by adjusting the tendon forces. This makes it possible to control the virtual DOFs to satisfy the requirements of the task. Finally, we discuss the benefits from anthropomorphic structures including the tendon arrangement, which mimic the human lumbrical muscle, and the above mentioned mechanism with non-linear moment arms from the perspective that there are two states of DOFs. These insights may provide new perspectives in the design of robotic hands. |
BibTeX:
@article{shirafuji2014development,
author = {Shouhei Shirafuji and Shuhei Ikemoto and Koh Hosoda},
title = {Development of a tendon-driven robotic finger for an anthropomorphic robotic hand},
journal = {The International Journal of Robotics Research},
year = {2014},
volume = {33},
pages = {677-693},
doi = {10.1177/0278364913518357}
}
|
[8] Ikemoto S, DallaLibera F, Hosoda K and Ishiguro H (2012), "Minimalistic Behavioral Rule derived from Bacterial Chemotaxis in a Stochastic Resonance Setup", Physical Review E: Statistical, Nonlinear, and Soft Matter Physics., February, 2012. Vol. 85(2), pp. 021905.
[Abstract] [BibTeX] [DOI]
|
| Abstract: Animals are able to cope with the noise, uncertainties, and complexity of the real world. Often even elementary living beings, equipped with very limited sensory organs, are able to reach regions favorable to their existence, using simple stochastic policies. In this paper we discuss a minimalistic stochastic behavioral rule, inspired from bacteria chemotaxis, which is able to increase the value of a specified evaluation function in a similar manner. In particular, we prove that, under opportune assumptions, the direction that is taken with maximum probability by an agent that follows this rule corresponds to the optimal direction. The rule does not require a specific agent dynamics, needs no memory for storing observed states, and works in generic n-dimensional spaces. It thus reveals itself interesting for the control of simple sensing robots as well. |
BibTeX:
@article{ikemoto2012minimalistic,
author = {Shuhei Ikemoto and Fabio DallaLibera and Koh Hosoda and Hiroshi Ishiguro},
title = {Minimalistic Behavioral Rule derived from Bacterial Chemotaxis in a Stochastic Resonance Setup},
journal = {Physical Review E: Statistical, Nonlinear, and Soft Matter Physics},
year = {2012},
volume = {85},
number = {2},
pages = {021905},
doi = {10.1103/PhysRevE.85.021905}
}
|
[7] Ikemoto S, Amor HB, Minato T and Ishiguro H (2012), "Mutual Learning and Adaptation in Physical Human-Robot Interaction", IEEE Robotics & Automation Magazine., December, 2012. Vol. 19(4), pp. 24-35.
[Abstract] [BibTeX] [DOI]
|
| Abstract: Close physical interaction between robots and humans is a particularly challenging aspect of robot development. For successful interaction and cooperation, the robot must have the ability to adapt its behavior to the human counterpart. Based on our earlier work, we present and evaluate a computationally efficient machine learning algorithm that is well suited for such close-contact interaction scenarios. We show that this algorithm helps to improve the quality of the interaction between a robot and a human caregiver. To this end, we present two human-in-the-loop learning scenarios that are inspired by human parenting behavior, namely, an assisted standing-up task and an assisted walking task. |
BibTeX:
@article{ikemoto2012mutual,
author = {Shuhei Ikemoto and Heni Ben Amor and Takashi Minato and Hiroshi Ishiguro},
title = {Mutual Learning and Adaptation in Physical Human-Robot Interaction},
journal = {IEEE Robotics & Automation Magazine},
year = {2012},
volume = {19},
number = {4},
pages = {24-35},
doi = {10.1109/MRA.2011.2181676}
}
|
[6] DallaLibera F, Ikemoto S, Ishiguro H and Hosoda K (2012), "Control of real-world complex robots using a biologically inspired algorithm", Artificial Life and Robotics., October, 2012. Vol. 17(1), pp. 42-46.
[Abstract] [BibTeX] [DOI]
|
| Abstract: Elementary living beings, like bacteria, are able to reach food sources using only limited and very noisy sensory information. In this paper, we describe a very simple algorithm inspired from bacteria chemotaxis. We present a Markov chain model for studying the effect of noise on the behavior of an agent that moves according to this algorithm, and we show that, counterintuitively, the application of noise can increase the expected average performance over a fixed available time. After this theoretical analysis, experiments on real-world application of this algorithm are introduced. In particular, we show that the algorithm is able to control a complex robot arm, actuated by 17 McKibben pneumatic artificial muscles, without the need of any model of the robot or of its environment. |
BibTeX:
@article{dallalibera2012control,
author = {Fabio DallaLibera and Shuhei Ikemoto and Hiroshi Ishiguro and Koh Hosoda},
title = {Control of real-world complex robots using a biologically inspired algorithm},
journal = {Artificial Life and Robotics},
year = {2012},
volume = {17},
number = {1},
pages = {42-46},
doi = {10.1007/s10015-012-0034-4}
}
|
[5] Hosoda K, Sekimoto S, Nishigori Y, Takamuku S and Ikemoto S (2012), "Anthropomorphic Muscular-Skeletal Robotic Upper Limb For Understanding Embodied Intelligence", Advanced Robotics., April, 2012. Vol. 26(7), pp. 729-744.
[Abstract] [BibTeX] [DOI]
|
| Abstract: In this paper, we describe an anthropomorphic muscular skeletal robotic upper limb and focus on its soft interaction with the environment. Two experiments are conducted to demonstrate the ability of the system: object recognition by dynamic touch and adaptive door opening. The first experiment shows that the compliant robot is advantageous for categorizing an object by shaking and the second experiment shows that the human-comparable compliant robot can open a door without precise control. The robot is expected to have comparable anisotropic compliance to that of a human, which can be utilized for realization of human-like adaptive behavior. |
BibTeX:
@article{hosoda2012anthropomorphic,
author = {Koh Hosoda and Shunsuke Sekimoto and Yoichi Nishigori and Shinya Takamuku and Shuhei Ikemoto},
title = {Anthropomorphic Muscular-Skeletal Robotic Upper Limb For Understanding Embodied Intelligence},
journal = {Advanced Robotics},
year = {2012},
volume = {26},
number = {7},
pages = {729-744},
doi = {10.1163/156855312X625371}
}
|
[4] Ikemoto S, Nishigori Y and Hosoda K (2012), "Advantages of flexible musculoskeletal robot structure in sensory acquisition", Artificial Life and Robotics., October, 2012. Vol. 17(1), pp. 63-69.
[Abstract] [BibTeX] [DOI]
|
| Abstract: Morphological computation is the concept for which a well-designed hardware can bear part of the computational cost required for robot・ｽfs control and perception. So far, many musculoskeletal robots have been developed by taking inspiration from human・ｽfs one and shown superior motion performances. The use of pneumatic artificial muscles (PAMs) has been the key to realize these high performance. Additionally, PAMs have the possibility of being used as sensors for environmental information because they are flexible and backdrivable. In this research, we focus on clarifying how PAMs can contribute to morphological computation of robots driven by these actuators. In particular, we propose an analysis method based on transfer entropy and apply this method to the experimental data acquired by a musculoskeletal robot that opens a door. |
BibTeX:
@article{ikemoto2012advantages,
author = {Shuhei Ikemoto and Yoichi Nishigori and Koh Hosoda},
title = {Advantages of flexible musculoskeletal robot structure in sensory acquisition},
journal = {Artificial Life and Robotics},
year = {2012},
volume = {17},
number = {1},
pages = {63-69},
doi = {10.1007/s10015-012-0017-5}
}
|
[3] Shimizu T, Saegusa R, Ikemoto S, Ishiguro H and Metta G (2012), "Self-protective whole body motion for humanoid robots based on synergy of global reaction and local reflex", Neural Networks. Vol. 32, pp. 109-118.
[Abstract] [BibTeX] [DOI]
|
| Abstract: This paper describes a self-protective whole body motor controller to enable life-long learning of humanoid robots. In order to reduce the damages on robots caused by physical interaction such as obstacle collision, we introduce self-protective behaviors based on the adaptive coordination of full-body global reactions and local limb reflexes. Global reactions aim at adaptive whole-body movements to prepare for harmful situations. The system incrementally learns a more effective association of the states and global reactions. Local reflexes based on a force-torque sensing function to reduce the impact load on the limbs independently of high-level motor intention. We examined the proposed method with a robot simulator in various conditions. We then applied the systems on a real humanoid robot. |
BibTeX:
@article{shimizu2012self,
author = {Toshihiko Shimizu and Ryo Saegusa and Shuhei Ikemoto and Hiroshi Ishiguro and Giorgio Metta},
title = {Self-protective whole body motion for humanoid robots based on synergy of global reaction and local reflex},
journal = {Neural Networks},
year = {2012},
volume = {32},
pages = {109-118},
doi = {10.1016/j.neunet.2012.02.011}
}
|
[2] Ikemoto S, DallaLibera F and Ishiguro H (2011), "Stochastic Resonance Emergence from a Minimalistic Behavioral Rule", Journal of Theoretical Biology., March, 2011. Vol. 273(1), pp. 179-187.
[Abstract] [BibTeX] [DOI]
|
| Abstract: Stochastic resonance (SR) is a phenomenon occurring in nonlinear systems by which the ability to process information, for instance the detection of weak signals is statistically enhanced by a non-zero level of noise. SR effects have been observed in a great variety of systems, comprising electronic circuits, optical devices, chemical reactions and neurons. In this paper we report the SR phenomena occurring in the execution of an extremely simple behavioral rule inspired from bacteria chemotaxis. The phenomena are quantitatively analyzed by using Markov chain models and Monte Carlo simulations. |
BibTeX:
@article{ikemoto2011stochastic,
author = {Shuhei Ikemoto and Fabio DallaLibera and Hiroshi Ishiguro},
title = {Stochastic Resonance Emergence from a Minimalistic Behavioral Rule},
journal = {Journal of Theoretical Biology},
year = {2011},
volume = {273},
number = {1},
pages = {179-187},
doi = {10.1016/j.jtbi.2011.01.002}
}
|
[1] Ikemoto S, Minato T and Ishiguro H (2008), "Analysis of Physical Human-Robot Interaction for Motor Learning with Physical Help", Applied Bionics and Biomechanics., March, 2008. Vol. 5(4), pp. 213-223.
[Abstract] [BibTeX] [DOI]
|
| Abstract: In this paper, we investigate physical human robot interaction (PHRI) as an important extension of traditional HRI research. The aim of this research is to develop a motor learning system that uses physical help from a human helper. We first propose a new control system that takes advantage of inherent joint flexibility. This control system is applied on a new humanoid robot called CB2. In order to clarify the difference between successful and unsuccessful interaction, we conduct an experiment where a human subject has to help the CB2 robot in its rising-up motion. We then develop a new measure that demonstrates the difference between smooth and non-smooth physical interactions. An analysis of the experiment's data, based on the introduced measure, shows significant differences between experts and beginners in human robot interaction. |
BibTeX:
@article{ikemoto2008analysis,
author = {Shuhei Ikemoto and Takashi Minato and Hiroshi Ishiguro},
title = {Analysis of Physical Human-Robot Interaction for Motor Learning with Physical Help},
journal = {Applied Bionics and Biomechanics},
year = {2008},
volume = {5},
number = {4},
pages = {213-223},
doi = {10.1080/11762320902808143}
}
|
