Bryan Lao, Tomoya Tamei, Kazushi Ikeda

Understanding the contributions of therapist skill during intervention is essential for improving existing rehabilitation methodologies. This study aims to characterize therapist intervention on an important activity of daily living, the sit-to-stand motion. Using the concept of muscle synergy, we quantify and compare naturally-occurring standing strategies with those induced by a physical therapist. In this paper, we show that natural standing strategies are not shared among healthy subjects. However, each subject retains their own set of strategies. Moreover, the results suggest that a therapist does not introduce new strategies during therapy, but rather modulates the existing strategies of the individuals. Using such a low-dimensional representation of standing behavior allows for development of low-cost tools for wider distribution.

2019年07月, Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference, 2019, 2311 - 2315, 英語, 国際誌

[査読有り]

研究論文（学術雑誌）

Nishanth Koganti, Tomohiro Shibata, Tomoya Tamei, Kazushi Ikeda

2019年, Adv. Robotics, 33 (15-16), 800 - 814

[査読有り]

研究論文（学術雑誌）

Nishanth Koganti, Tomoya Tamei, Kazushi Ikeda, Tomohiro Shibata

2017年, IEEE Trans. Robotics, 33 (4), 916 - 931

[査読有り]

研究論文（学術雑誌）

Felix Orlando Maria Joseph, Laxmidhar Behera, Tomoya Tamei, Tomohiro Shibata, Ashish Dutta, Anupam Saxena

2017年, Robotica, 35 (10), 1992 - 2017

[査読有り]

研究論文（学術雑誌）

Bryan Lao, Tomoya Tamei, Kazushi Ikeda

Understanding effective sit-to-stand (STS) movement is essential for improving rehabilitation strategies and developing services for the rapidly increasing number of elderly people. This study aims at identifying effective STS therapy by analyzing the kinematic synergies of movements induced by therapists of different skill-levels. Three synergies were found to share the same temporal pattern in both joint angles and center-of-mass spaces across all therapists. Effective strategy used by a skilled therapist and strategy flaws of less-experienced therapists were revealed through comparison of spatial patterns.

2016年08月, Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference, 2016, 6282 - 6285, 英語, 国際誌

[査読有り]

研究論文（学術雑誌）

Nishanth Koganti, Jimson Gelbolingo Ngeo, Tomoya Tamei, Kazushi Ikeda, Tomohiro Shibata

2015年, 3464 - 3469

[査読有り]

研究論文（国際会議プロシーディングス）

Jimson Ngeo, Tomoya Tamei, Kazushi Ikeda, Tomohiro Shibata

Accurate proportional myoelectric control of the hand is important in replicating dexterous manipulation in robot prostheses and orthoses. However, this is still difficult to achieve due to the complex and high degree-of-freedom (DOF) nature present in the governing musculoskeletal system. To address this problem, we suggest using a low dimensional encoding based on nonlinear synergies to represent both the high-DOF finger joint kinematics and the coordination of muscle activities taken from surface electromyographic (EMG) signals. Generating smooth multi-finger movements using EMG inputs is then done by using a shared Gaussian Process latent variable model that learns a dynamical model between both the kinematic and EMG data represented in a shared latent space. The experimental results show that the method is able to synthesize continuous movements of a full five-finger hand model, with total dimensions as large as 69 (although highly redundant and correlated). Finally, by comparing the estimation performances when the number of EMG latent dimensions are varied, we show that these synergistic features can capture the variance, shared and specific to the observed kinematics.

2015年, Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference, 2015, 2095 - 8, 英語, 国際誌

[査読有り]

研究論文（学術雑誌）

Jimson G Ngeo, Tomoya Tamei, Tomohiro Shibata

BACKGROUND: Surface electromyography (EMG) signals are often used in many robot and rehabilitation applications because these reflect motor intentions of users very well. However, very few studies have focused on the accurate and proportional control of the human hand using EMG signals. Many have focused on discrete gesture classification and some have encountered inherent problems such as electro-mechanical delays (EMD). Here, we present a new method for estimating simultaneous and multiple finger kinematics from multi-channel surface EMG signals. METHOD: In this study, surface EMG signals from the forearm and finger kinematic data were extracted from ten able-bodied subjects while they were tasked to do individual and simultaneous multiple finger flexion and extension movements in free space. Instead of using traditional time-domain features of EMG, an EMG-to-Muscle Activation model that parameterizes EMD was used and shown to give better estimation performance. A fast feed forward artificial neural network (ANN) and a nonparametric Gaussian Process (GP) regressor were both used and evaluated to estimate complex finger kinematics, with the latter rarely used in the other related literature. RESULTS: The estimation accuracies, in terms of mean correlation coefficient, were 0.85 ± 0.07, 0.78 ± 0.06 and 0.73 ± 0.04 for the metacarpophalangeal (MCP), proximal interphalangeal (PIP) and the distal interphalangeal (DIP) finger joint DOFs, respectively. The mean root-mean-square error in each individual DOF ranged from 5 to 15%. We show that estimation improved using the proposed muscle activation inputs compared to other features, and that using GP regression gave better estimation results when using fewer training samples. CONCLUSION: The proposed method provides a viable means of capturing the general trend of finger movements and shows a good way of estimating finger joint kinematics using a muscle activation model that parameterizes EMD. The results from this study demonstrates a potential control strategy based on EMG that can be applied for simultaneous and continuous control of multiple DOF(s) devices such as robotic hand/finger prostheses or exoskeletons.

2014年08月14日, Journal of neuroengineering and rehabilitation, 11, 122 - 122, 英語, 国際誌

[査読有り]

研究論文（学術雑誌）

Chihiro Obayashi, Tomoya Tamei, Tomohiro Shibata

This paper proposes a novel robotic trainer for motor skill learning. It is user-adaptive inspired by the assist-as-needed principle well known in the field of physical therapy. Most previous studies in the field of the robotic assistance of motor skill learning have used predetermined desired trajectories, and it has not been examined intensively whether these trajectories were optimal for each user. Furthermore, the guidance hypothesis states that humans tend to rely too much on external assistive feedback, resulting in interference with the internal feedback necessary for motor skill learning. A few studies have proposed a system that adjusts its assistive strength according to the user's performance in order to prevent the user from relying too much on the robotic assistance. There are, however, problems in these studies, in that a physical model of the user's motor system is required, which is inherently difficult to construct. In this paper, we propose a framework for a robotic trainer that is user-adaptive and that neither requires a specific desired trajectory nor a physical model of the user's motor system, and we achieve this using model-free reinforcement learning. We chose dart-throwing as an example motor-learning task as it is one of the simplest throwing tasks, and its performance can easily be and quantitatively measured. Training experiments with novices, aiming at maximizing the score with the darts and minimizing the physical robotic assistance, demonstrate the feasibility and plausibility of the proposed framework.

2014年05月, Neural networks : the official journal of the International Neural Network Society, 53, 52 - 60, 英語, 国際誌

[査読有り]

研究論文（学術雑誌）

Nishanth Koganti, Tomoya Tamei, Takamitsu Matsubara, Tomohiro Shibata

2014年, 124 - 129

[査読有り]

研究論文（国際会議プロシーディングス）

Jimson Ngeo, Tomoya Tamei, Tomohiro Shibata

Surface electromyographic (EMG) signals have often been used in estimating upper and lower limb dynamics and kinematics for the purpose of controlling robotic devices such as robot prosthesis and finger exoskeletons. However, in estimating multiple and a high number of degrees-of-freedom (DOF) kinematics from EMG, output DOFs are usually estimated independently. In this study, we estimate finger joint kinematics from EMG signals using a multi-output convolved Gaussian Process (Multi-output Full GP) that considers dependencies between outputs. We show that estimation of finger joints from muscle activation inputs can be improved by using a regression model that considers inherent coupling or correlation within the hand and finger joints. We also provide a comparison of estimation performance between different regression methods, such as Artificial Neural Networks (ANN) which is used by many of the related studies. We show that using a multi-output GP gives improved estimation compared to multi-output ANN and even dedicated or independent regression models.

2014年, Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference, 2014, 3537 - 40, 英語, 国際誌

[査読有り]

研究論文（学術雑誌）

Jimson Ngeo, Tomoya Tamei, Tomohiro Shibata, M F Felix Orlando, Laxmidhar Behera, Anupam Saxena, Ashish Dutta

Patients suffering from loss of hand functions caused by stroke and other spinal cord injuries have driven a surge in the development of wearable assistive devices in recent years. In this paper, we present a system made up of a low-profile, optimally designed finger exoskeleton continuously controlled by a user's surface electromyographic (sEMG) signals. The mechanical design is based on an optimal four-bar linkage that can model the finger's irregular trajectory due to the finger's varying lengths and changing instantaneous center. The desired joint angle positions are given by the predictive output of an artificial neural network with an EMG-to-Muscle Activation model that parameterizes electromechanical delay (EMD). After confirming good prediction accuracy of multiple finger joint angles we evaluated an index finger exoskeleton by obtaining a subject's EMG signals from the left forearm and using the signal to actuate a finger on the right hand with the exoskeleton. Our results show that our sEMG-based control strategy worked well in controlling the exoskeleton, obtaining the intended positions of the device, and that the subject felt the appropriate motion support from the device.

2013年, Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference, 2013, 338 - 41, 英語, 国際誌

[査読有り]

研究論文（学術雑誌）

Nishanth Koganti, Tomoya Tamei, Takamitsu Matsubara, Tomohiro Shibata

2013年, 36 - 6

[査読有り]

研究論文（国際会議プロシーディングス）

Felix Orlando Maria Joseph, Ashish Dutta, Anupam Saxena, Laxmidhar Behera, Tomoya Tamei, Tomohiro Shibata

2013年, Robotica, 31 (5), 797 - 809

[査読有り]

研究論文（学術雑誌）

Jimson Ngeo, Tomoya Tamei, Tomohiro Shibata

Prediction of dynamic hand finger movements has many clinical and engineering applications in the control of human interface devices such as those used in virtual reality control, robot prosthesis and rehabilitation aids. Surface electromyography (sEMG) signals have often been used in the mentioned applications because these reflect the motor intention of users very well. In this study, we present a method to estimate the finger joint angles of a hand from sEMG signals that considers electromechanical delay (EMD), which is inherent when EMG signals are captured alongside motion data. We use the muscle activation obtained from the sEMG signals as input to a neural network. In this muscle activation model, the EMD is parameterized and automatically obtained through optimization. With this method, we can predict the finger joint angles with sEMG signals in both periodic and nonperiodic free movements of the flexion and extension movement of the fingers. Our results show correlation as high as 0.92 between the actual and predicted metacarpophalangeal (MCP) joint angles for periodic finger flexion movements, and as high as 0.85 for nonperiodic movements, which are more dynamic and natural.

2012年, Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference, 2012, 2756 - 9, 英語, 国際誌

[査読有り]

研究論文（学術雑誌）

Tomoya Tamei, Chihiro Obayashi, Tomohiro Shibata

Acquiring the skillful movements of experts is a difficult task in many fields. If we find quantitative indices of skillful movement, we can develop an adaptive training system using the indices. We focused on throwing darts in our previous study. It was found that optimization criteria of sum of squared joint torque changes over time was negatively correlated with subject's scores, suggesting that the experts optimally controlled the shoulder elevations and rotation around the elbow joint in terms of dynamics. In this study, we investigate the relationship between the skill level of subjects and their utilization joint torque components such as the muscular torque, interaction torque and gravity torque. It is shown found that the sum of squared joint torque components of the subjects correlates with their scores, suggesting that the subjects who can take higher scores utilize the interaction torque of the elbow joint without shoulder displacement.

2011年, Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference, 2011, 1283 - 6, 英語, 国際誌

[査読有り]

研究論文（学術雑誌）

Chihiro Obayashi, Tomoya Tamei, Akira Imai, Tomohiro Shibata

Acquiring skillful movements of experts is a difficult task in many fields. Since non-experts often fail to find out how to improve their skill, it is desirable to find quantitative indices of skillful movements that clarify the difference between experts and non-experts. If we find quantitative indices, we can develop an adaptive training system using the indices. In this study, we quantitatively compare dart-throwing movements between experts and non-experts based on their scores, motions, and EMG signals. First, we show that the variance of upper-limb motion trajectories of the experts is significantly smaller than that of the non-experts. Then, we show that the displacement and the variance of the shoulder of the experts are also significantly smaller than those of the non-experts. The final result is the highlight of this study. We investigated their upper-limb motions from the viewpoint of trajectory optimization. In this study, we focus on two popular optimization criteria, i.e., sum of squared jerk over a trajectory and sum of squared joint-torque change over a trajectory. We present that the sum of squared joint torques of the subjects was negatively correlated with their scores (p < 0.05), whereas the other criteria were not.

2009年, Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference, 2009, 2647 - 50, 英語, 国際誌

[査読有り]

研究論文（学術雑誌）

手塚 雄大, 王 立華, 林 卓也, Kim Sangwook, 為井 智也, 大森 敏明, 小澤 誠一

データのプライバシーへの懸念が膨大なデータの利活用を妨げている．プライバシーを保護した上でデータ解析を行う技術は重要である．本研究では，Ring-LWEベースの準同型暗号を用いて三層ニューラルネットの内積演算を効率よく行えるプライバシー保護機械学習モデルを提案する．提案モデルは，入力データを暗号化して，その識別結果を受け取るクライアント，学習済モデルを用いて暗号化された入力に対する識別結果を計算するサーバで構成される．これにより，クライアントはデータのプライバシーを漏らすことなく，モデル製作者はモデルを公開することなくデータの解析を行うことができる．提案手法では，一つのクラスの推論処理に対して，10.549 [ms]の時間を要する．また，Sigmoid関数やReLU関数の場合に近い精度で推論処理を行える．

一般社団法人 人工知能学会, 2019年, 人工知能学会全国大会論文集, 2019 (0), 2G3OS2a03 - 2G3OS2a03, 日本語

為井 智也, 石井 信, 柴田 智広

ユーザーの生体情報をリアルタイムでロボットに通信することにより,センサーを持たないロボットに仮想的な力覚・触覚を持たせる新しい知能ロボットの設計アプローチを提案する.本アプローチは制御対象に依存しないため,幅広いロボット・機械に適用することができる.本アプローチの有用性を検証するために,センサーを持たない産業用ロボットマニピュレータ,表面筋電(EMG)計測装置,モーションキャプチャーシステムからなるシステムを構築して実験を行った.ユーザーの手首に関するEMGと姿勢情報をリアルタイムでロボット側に通信することでロボットに力覚/触覚を持たせ,直感的かつ動的なインタラクションを実現した.更に,応用例としてユーザーとロボットが協調して重量物の持ち上げ・下げ作業を行うタスクも実施した.それらの実験結果を示すと共に,本アプローチの利点についても議論する.

一般社団法人電子情報通信学会, 2007年05月14日, 電子情報通信学会技術研究報告. NC, ニューロコンピューティング, 107 (50), 9 - 14, 日本語

為井 智也, 柴田 智広, 石井 信

ピアノ演奏で重要と言われる「脱力した」奏法と「力んだ」奏法の比較を, 示指の3関節を用いた打鍵動作を対象に行う.本目的のため, 示指の関節角度, 筋電位, 鍵盤の変位を同時に記録することの出来る計測システムを開発した.予備的な実験の結果, 脱力した場合と力んだ場合では筋電のパターンに違いが認められ, その結果として鍵盤の挙動にも違いが現れることを示す.特に指が離鍵する際の伸筋の活性度と離鍵速度に強い相関が見られた.得られた結果から, 今回開発した計測システムを用いることによって演奏者の熟達度を評価する手法となり得ることが期待される.

一般社団法人情報処理学会, 2005年08月04日, 情報処理学会研究報告, 2005 (82), 47 - 52, 日本語