Mitsuhiro Hayashibe

Prof. Dr. Mitsuhiro Hayashibe

orcid

Research Focus & Metrics

Academic Career Length

25Years (2002-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 October 2021 in IEEE Sensors Journal
Verified
Journal Article
Open access
YHYonatan Hutabarat
Yonatan Hutabarat
Dai OwakiDai Owaki
Dai Owaki
MHMitsuhiro Hayashibe
Mitsuhiro Hayashibe
The current gold standard for gait analysis involves performing the gait experiments in a laboratory environment with a constrained space. However, there is growing interest in using flexible, efficient, and inexpensive wearable sensors as tools to perform gait analysis. This review aimed to identify and summarize the current advances in wearable sensors for various aspects of gait analysis, such as the application of wearable gait analysis systems, sensor systems and their attachment locations, and the algorithms used for the analysis. The PRISMA guideline was adopted to find relevant studies from the period 2011 to 2020 from several scientific databases. A total of 76 articles were selected based on the inclusion and exclusion criteria. A wearable inertial measurement unit (IMU) attached to the lower limb region was found to be the most common approach for gait analysis. Temporal, spatial, and spatiotemporal features were the most common quantitative gait features extracted from the wearable sensors. The proposed frameworks showed varying performances, and an increased number of sensors did not necessarily improve the estimation performance metrics. A few studies have integrated various machine learning techniques for classification problems, correction algorithms, crosschecking functions, and scoring functions. Finally, this review paper discusses the challenges and future direction of the research on quantitative gait analysis.

20 July 2022 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Open access
WZWei Zhu
Wei Zhu
MHMitsuhiro Hayashibe
Mitsuhiro Hayashibe
We present a hierarchical deep reinforcement learning (DRL) framework with prominent sampling efficiency and sim-to-real transfer ability for fast and safe navigation: the low-level DRL policy enables the robot to move toward the target position and keep a safe distance to obstacles simultaneously; the high-level DRL policy is supplemented to further enhance the navigation safety. We select a waypoint located on the path from the robot to the ultimate goal as the subgoal to reduce the state space and avoid sparse reward. Moreover, the path is generated based on either a local or a global map, which can significantly improve the sampling efficiency, safety, and generalization ability of the proposed DRL framework. Additionally, a target-directed representation for the action space can be derived based on the subgoal to improve the motion efficiency and reduce the action space. In order to demonstrate the eminent sampling efficiency, motion performance, obstacle avoidance, and generalization ability of the proposed framework, we implement sufficient comparisons with the nonlearning navigation methods and DRL-based baselines, with videos, data, code, and other supplemental material shown on our website.

29 September 2021 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
WZWei Zhu
Wei Zhu
XGXian Guo
Xian Guo
DODai Owaki
Dai Owaki
KKKyo Kutsuzawa
Kyo Kutsuzawa
MHMitsuhiro Hayashibe
Mitsuhiro Hayashibe
The state-of-the-art reinforcement learning (RL) techniques have made innumerable advancements in robot control, especially in combination with deep neural networks (DNNs), known as deep reinforcement learning (DRL). In this article, instead of reviewing the theoretical studies on RL, which were almost fully completed several decades ago, we summarize some state-of-the-art techniques added to commonly used RL frameworks for robot control. We mainly review bioinspired robots (BIRs) because they can learn to locomote or produce natural behaviors similar to animals and humans. With the ultimate goal of practical applications in real world, we further narrow our review scope to techniques that could aid in sim-to-real transfer. We categorized these techniques into four groups: 1) use of accurate simulators; 2) use of kinematic and dynamic models; 3) use of hierarchical and distributed controllers; and 4) use of demonstrations. The purposes of these four groups of techniques are to supply general and accurate environments for RL training, improve sampling efficiency, divide and conquer complex motion tasks and redundant robot structures, and acquire natural skills. We found that, by synthetically using these techniques, it is possible to deploy RL on physical BIRs in actuality.

1 October 2011 in IEEE/ASME Transactions on Mechatronics
Verified
Journal Article
Closed access
QZQin Zhang
Qin Zhang
MHMitsuhiro Hayashibe
Mitsuhiro Hayashibe
PFPhilippe Fraisse
Philippe Fraisse
DGDavid Guiraud
David Guiraud
This paper investigates a torque estimation method for muscle fatigue tracking, using stimulus evoked electromyography (eEMG) in the context of a functional electrical stimulation (FES) rehabilitation system. Although FES is able to effectively restore motor function in spinal cord injured (SCI) individuals, its application is inevitably restricted by muscle fatigue. In addition, the sensory feedback indicating fatigue is missing in such patients. Therefore, torque estimation is essential to provide feedback or feedforward signal for adaptive FES control. In this paper, a fatigue-inducing protocol is conducted on five SCI subjects via transcutaneous electrodes under isometric condition, and eEMG signals are collected by surface electrodes. A myoelectrical mechanical muscle model based on the Hammerstein structure with eEMG as model input is employed to capture muscle contraction dynamics. It is demonstrated that the correlation between eEMG and torque is time varying during muscle fatigue. Compared to conventional fixed-parameter models, the adapted-parameter model shows better torque prediction performance in fatiguing muscles. It motivates us to use a Kalman filter with forgetting factor for estimating the time-varying parameters and for tracking muscle fatigue. The assessment with experimental data reveals that the identified eEMG-to-torque model properly predicts fatiguing muscle behavior. Furthermore, the performance of the time-varying parameter estimation is efficient, suggesting that real-time tracking is feasible with a Kalman filter and driven by eEMG sensing in the application of FES.

10 April 2014 in IEEE Computational Intelligence Magazine
Verified
Journal Article
Closed access
ZLZhan Li
Zhan Li
MHMitsuhiro Hayashibe
Mitsuhiro Hayashibe
CFCharles Fattal
Charles Fattal
DGDavid Guiraud
David Guiraud
One of the challenging issues in computational rehabilitation is that there is a large variety of patient situations depending on the type of neurological disorder. Human characteristics are basically subject specific and time variant; for instance, neuromuscular dynamics may vary due to muscle fatigue. To tackle such patient specificity and time-varying characteristics, a robust bio-signal processing and a precise model-based control which can manage the nonlinearity and time variance of the system, would bring break-through and new modality toward computational intelligence (CI) based rehabilitation technology and personalized neuroprosthetics. Functional electrical stimulation (FES) is a useful technique to assist restoring motor capability of spinal cord injured (SCI) patients by delivering electrical pulses to paralyzed muscles. However, muscle fatigue constraints the application of FES as it results in the time-variant muscle response. To perform adaptive closedloop FES control with actual muscle response feedback taken into account, muscular torque is essential to be estimated accurately. However, inadequacy of the implantable torque sensor limits the direct measurement of the time-variant torque at the joint. This motivates the development of methods to estimate muscle torque from bio-signals that can be measured. Evoked electromyogram (eEMG) has been found to be highly correlated with FES-induced torque under various muscle conditions, indicating that it can be used for torque/force prediction. A nonlinear ARX (NARX) type model is preferred to track the relationship between eEMG and stimulated muscular torque. This paper presents a NARX recurrent neural network (NARX-RNN) model for identification/prediction of FES-induced muscular dynamics with eEMG. The NARX-RNN model may possess novelty of robust prediction performance. Due to the difficulty of choosing a proper forgetting factor of Kalman filter for predicting time-variant torque with eEMG, the presented NARX-RNN could be considered as an alternative muscular torque predictor. Data collected from five SCI patients is used to evaluate the proposed NARX-RNN model, and the results show promising estimation performances. In addition, the general importance regarding CI-based motor function modeling is introduced along with its potential impact in the rehabilitation domain. The issue toward personalized neuroprosthetics is discussed in detail with the potential role of CI-based identification and the benefit for motor-impaired patient community.

1 August 2013 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Closed access
QZQin Zhang
Qin Zhang
MHMitsuhiro Hayashibe
Mitsuhiro Hayashibe
CAChristine Azevedo-Coste
Christine Azevedo-Coste
This paper proposed a closed-loop torque control strategy of functional electrical stimulation (FES) with the aim of obtaining an accurate, safe, and robust FES system. Generally, FES control systems are faced with the challenge of how to deal with time-variant muscle dynamics due to physiological and biochemical factors (such as fatigue). The degraded muscle force needs to be compensated in order to ensure the accuracy of the motion restored by FES. Another challenge concerns the fact that implantable sensors are unavailable to feedback torque information for FES in humans. As FES-evoked electromyography (EMG) represents the activity of stimulated muscles, and also enables joint torque prediction as presented in our previous studies, here we propose an EMG-feedback predictive controller of FES to control joint torque adaptively. EMG feedback contributes to taking the activated muscle state in the FES torque control system into account. The nature of the predictive controller facilitates prediction of the muscle mechanical response and the system can therefore control joint torque from EMG feedback and also respond to time-variant muscle state changes. The control performance, fatigue compensation and aggressive control suppression capabilities of the proposed controller were evaluated and discussed through experimental and simulation studies.