Muscle Synergy-Based Control of Human-Manipulator Interactions

This article attempts to review papers on power assist rehabilitation robots, human motion intention, control laws, and estimation of power assist rehabilitation robots based on human motion intention in recent years. This paper presents the various ways in which human motion intention in rehabilitation can be estimated. This paper also elaborates on the control laws for the estimation of motion intention of the power assist rehabilitation robot. From the review, it has been found that the motion intention estimation method includes: Artificial Intelligence-based motion intention and Model-based motion intention estimation. The controllers include hybrid force/position control, EMG control, and adaptive control. Furthermore, Artificial Intelligence based motion intention estimation can be subdivided into Electromyography (EMG), Surface Electromyography (SEMG), Extreme Learning Machine (ELM), and Electromyography-based Admittance Control (EAC). Also, Model-based motion intention estimation can be subdivided into Impedance and Admittance control interaction. Having reviewed several papers, EAC and ELM are proposed for efficient motion intention estimation under artificial-based motion intention. In future works, Impedance and Admittance control methods are suggested under model-based motion intention for efficient estimation of motion intention of power assist rehabilitation robot. In addition, hybrid force/position control and adaptive control are suggested for the selection of control laws. The findings of this review paper can be used for developing an efficient power assist rehabilitation robot with motion intention to aid people with lower or upper limb impairment.

A human motion intent estimation algorithm based on laser ranger finder and force sensors is designed for a walking-aid robot. By applying the proposed algorithm to the robot, the user can operate the walking-aid robot more fluently, comfortably and safely. A walking-aid or rehabilitation robot normally estimates the user's motion intention by measuring the interactive forces between human and robot. Whereas, the human motion should be represented as a coordination between the arms and the legs movements. This study therefore proposes a human motion intent estimation algorithm by fusing the motion intentions detected by the force sensors and the laser ranger finder, which are used to monitor the movements of arms and legs respectively. A special arrangement of push-pull force sensors is implemented for estimating the human motion intention I from user's operations on the handles. Meanwhile the human motion intention II is extracted by a laser ranger finder observing the user's movement of legs. A multi-sensor fusion algorithm is employed to fuse these two estimates. Experimental results are presented to show the validity of the proposed human motion intent estimation algorithm.

Estimation of human impedance and motion intention for constrained human–robot interaction

EEG signal is one of the biological signals that can be useful to control wearable robotic devices, according to the human motion intention. However, the real-time estimation of the user's motion intention from EEG signals is cumbersome. The user's motion intention might not be estimated when the user does not concentrate on the control of the robot, distracted by other things or disturbed by the outside interferences. In this paper, a neural network based real-time estimation method is proposed to detect human motion intention in terms of intended task, using EEG signals. The inputs of bandpower time series signals let the neural network identify the dynamic nature of the tasks performed. Experimental details, methodology and the prediction results are presented.

The objective of this research is to explore whether a two-dimensional BCI can be achieved by reliably decoding single-trial magneto-encephalography (MEG) signal associated with sustaining or ceasing right and left hand movements. Seven naïve subjects participated in the study. Signals were recorded from 275-channel MEG and synthetic aperture magnetometry (SAM) was employed. The multi-class classification for four-directional control was evaluated offline from 10-fold cross-validation using direct-decision tree classifier and genetic algorithm based Mahalanobis linear distance. Beta band (15-30Hz) event-related desynchronization and event related synchronization were observed in right and left hand movement related motor areas for physical movements as well as motor imagery. The cross-validation accuracy for the proposed four-direction classification from SAM- filtered MEG signal was as high as 95-97% for physical movements and 86-87% for motor imagery. The high classification accuracy suggests that a reliable high performance two-dimensional BCI can be achieved from single trial detection of human natural movement intentions from SAM-filtered MEG signals, where user may not need extensive training.

A neural network-based model for lower limb continuous estimation against the disturbance of uncertainty

In this paper, a novel inverse model is designed for multivariable disturbance observer-based (MDOB) control system. A new interaction measure, generalized relative input disturbance gain (GRIDG), is proposed to quantify the disturbance rejection capabilities of different inverse model structures. Consequently, an inverse model with partially coupled structure can be determined for better disturbance rejection performance. Besides, by defining a relative input disturbance gain array (RIDGA), the values of GRIDG under different input-output pairings and structures can be derived in an intuitive manner, which greatly facilitates the structure selection of the inverse model. And then, to overcome the difficulty of implementing the partially coupled inverse model, a V canonical structure is used without introducing model approximations. It also has the advantage of simple calculation and being easy to generalize to high-dimensional systems. Finally, simulation examples of several multivariable industrial processes are given to illustrate the design procedure and demonstrate the effectiveness of the proposed strategy.

As one of the research hotspots in the field of rehabilitation robotics, the upper limb exoskeleton robot has been widely used in the field of rehabilitation. However, the existing methods cannot comprehensively and accurately reflect the motion state of patients, which may lead to overtraining and secondary injury of patients in the process of rehabilitation training. In this paper, an upper limb exoskeleton control method based on mixed perception model of motion intention and intensity is proposed, which is based on the 6 degree-of-freedom upper limb rehabilitation exoskeleton in the laboratory. First, the kinematic information and heart rate information in the rehabilitation process of patients are collected, corresponding to patients’ motion intention and motion intensity, and fused to obtain the mixed perception vector. Second, the motion perception model based on long short-term memory neural network is established to realize the prediction of upper limb motion trajectory of patients and compared with back-propagation neural network to prove its effectiveness. Finally, the control system is built, and both offline and online test of the control method proposed are implemented. The experimental results show that the method can achieve comprehensive motion state perception of patients, realize real-time and accurate prediction trajectory according to human motion intention and intensity. The average prediction accuracy is 95.3%, and predicted joint angle error is less than 5 degrees. Therefore, the control method based on mixed perception model has good robustness and universality, which provides a new method for the active control of upper limb exoskeleton.

In this paper, the EEG (electroencephalograph) signal acquisition equipment is used to collect the EEG signal of human lower limb movement intention. This paper firstly analyzes α waveform and β waveform, which can most reveal the intentions of human body movement. Then, wavelet transform is used for noise removal, filter and feature extraction. This paper also has described the theory of Support Vector Machine (SVM), and one-to-one SVM method is used for the classification of EEG of six different movement patterns. Finally through the experimental verification, the validity of the proposed research method is demonstrated. The experiment has shown a better judging result, in which the average recognition rate is 78.9%.

Myoelectric control systems as the emerging control strategies for upper limb wearable robots have shown their efficacy and applicability to effectively provide motion assistance and/or restore motor functions in people with impairment or disabilities, as well as augment physical performance in able-bodied individuals. In myoelectric control, electromyographic (EMG) signals from muscles are utilized, improving adaptability and human-robot interactions during various motion tasks. Machine learning has been widely applied in myoelectric control systems due to its advantages in detecting and classifying various human motions and motion intentions. This chapter illustrates the challenges and trends in recent machine learning algorithms implemented on myoelectric control systems designed for upper limb wearable robots, and highlights the key focus areas for future research directions. Different modalities of recent machine learning-based myoelectric control systems are described in detail, and their advantages and disadvantages are summarized. Furthermore, key design aspects and the type of experiments conducted to validate the efficacy of the proposed myoelectric controllers are explained. Finally, the challenges and limitations of current myoelectric control systems using machine learning algorithms are analyzed, from which future research directions are suggested.

An electromyography signals-based human-robot collaboration system for human motion intention recognition and realization

Future emerging technologies in upper limb neuroprosthetic devices will require decoding and executing the user's intended movement. Previous studies, using invasive and non-invasive brain signals, have shown promising results in decoding movement directions during movement execution. Intracortical recordings also allow for decoding of target directions before the actual movement in a reaction task. This thesis contributes to the exciting endeavor of designing practical upper limb neuroprosthetics by investigating the potential of using brain signals recorded non-invasively for detecting the intention to move and decoding directions of a self-paced reaching task before movement initiation. This work has the potential towards a more intuitive and coupled neuro-motor rehabilitation tools. The thesis provides three major contributions: (i) it proposes the use of data-driven and machine learning methods for localizing the regions of interests from scalp surface signals, (ii) it reports on successful detection of movement intention before a self-paced reaching task using amplitudes of on-going slow cortical potentials (SCPs) which is consistent across healthy subjects and chronic stroke patients and (ii) it proposes the use of amplitudes and phase of on-going SCPs for decoding movement directions before the reaching task. First, we reported a method for single trial detection of movement intention before a self-paced reaching task using signal processing and machine learning techniques. We used the movement-related potentials (MRPs) in a narrow frequency range between 0.1 to 1Hz for early detection of movement intention in the first study with 8 healthy subjects using scalp EEG. Movement intention can be detected on average 460ms before the actual onset. The average maximum true positive rates across subjects was 76% peaking at time 167ms before onset. These findings are coherent with the next study on stroke patients and control subjects. In the second study, movement intention can be detected as early as 600ms before the actual onset. More interestingly, the true positive rate reached above 80% for one of the stroke patients (both the paretic and healthy arm) and healthy control subjects. The low false positive rate before the detection of movement intention suggested that the method is promising for future online implementation using appropriate tasks (i.e. goal-oriented reaching). Second, we proposed a method for decoding reaching movement directions before onset using feature selection method called canonical variants analysis (CVA). Across all the subjects, the best selected features are mostly from the frontoparietal regions, which is consistent with previous neurophysiological studies on arm reaching tasks. The results of single trial decoding of movement directions are also promising, with a decoding accuracy before the onset for one of the control healthy subjects was of 71% using the amplitude of on-going SCPs. In addition, at 250ms before onset, the decoding accuracy peaks at 65% with the use of instantaneous phase features. The decoding accuracy for the stroke patients was 40-50% with their paretic arms. Thus, we observe that using phase features has two advantages: (i) the possibility to decode directions earlier and (ii) higher decoding accuracy. The thesis also validates the findings from scalp EEG with the invasive intra-cranial local field potentials recorded from an epileptic patient. We report that movement intention can be detected as early as 2000ms before the onset of movement with accuracy above 90%. The use of electrodes implanted in the supplementary motor area (SMA) for detecting intention with near perfection single trial classification has strengthen the theory that movement preparation starts as early as 1500ms before execution. As for movement directions, the decoding capability is rather low. It should be noticed that there are no electrode implanted in the parietal region that, as we have found in the two EEG studies and has been previously reported, are key for decoding reaching directions. In summary, the work in this thesis suggests that it is possible to recognize above chance level both the intention and direction of a self-paced reaching movement. In particular, movement intention detection can be used for the purpose of early activation of neuro-motor prosthetic devices that could enhance the recovery of stroke patients. In addition, future work derived from this thesis can harness the full potential of early intention detection from human voluntary movement for BCI and neuroprosthetics.

Electroencephalography (EEG) is considered the output of a brain and it is a bioelectrical signal with multiscale and nonlinear properties. Motor Imagery EEG (MI-EEG) not only has a close correlation with the human imagination and movement intention but also contains a large amount of physiological or disease information. As a result, it has been fully studied in the field of rehabilitation. To correctly interpret and accurately extract the features of MI-EEG signals, many nonlinear dynamic methods based on entropy, such as Approximate Entropy (ApEn), Sample Entropy (SampEn), Fuzzy Entropy (FE), and Permutation Entropy (PE), have been proposed and exploited continuously in recent years. However, these entropy-based methods can only measure the complexity of MI-EEG based on a single scale and therefore fail to account for the multiscale property inherent in MI-EEG. To solve this problem, Multiscale Sample Entropy (MSE), Multiscale Permutation Entropy (MPE), and Multiscale Fuzzy Entropy (MFE) are developed by introducing scale factor. However, MFE has not been widely used in analysis of MI-EEG, and the same parameter values are employed when the MFE method is used to calculate the fuzzy entropy values on multiple scales. Actually, each coarse-grained MI-EEG carries the characteristic information of the original signal on different scale factors. It is necessary to optimize MFE parameters to discover more feature information. In this paper, the parameters of MFE are optimized independently for each scale factor, and the improved MFE (IMFE) is applied to the feature extraction of MI-EEG. Based on the event-related desynchronization (ERD)/event-related synchronization (ERS) phenomenon, IMFE features from multi channels are fused organically to construct the feature vector. Experiments are conducted on a public dataset by using Support Vector Machine (SVM) as a classifier. The experiment results of 10-fold cross-validation show that the proposed method yields relatively high classification accuracy compared with other entropy-based and classical time–frequency–space feature extraction methods. The t-test is used to prove the correctness of the improved MFE.

The interval type-2 fuzzy Proportional-Integral (PI) controller (IT2-FPI) might be able to handle high levels of uncertainties to produce a satisfactory control performance, which could be potentially due to the robust performance as a result of the smoother control surface around the steady state. However, the transient state and disturbance rejection performance of the IT2-FPI may degrade in comparison with the type-1 fuzzy PI (T1-FPI) counterpart. This drawback can be resolved via general type-2 fuzzy PI controllers which can provide a tradeoff between the robust control performance of the IT2-FPI and the acceptable transient and disturbance rejection performance of the type-1 PI controllers. In this paper, we will present a zSlices-based general type-2 fuzzy PI controller (zT2-FPI), where the secondary membership functions (SMFs) of the antecedent general type-2 fuzzy sets are adjusted in an online manner. We will examine the effect of the SMF on the closed-system control performance to investigate their induced performance improvements. This paper will focus on the case followed in conventional or self-tuning fuzzy controller design strategies, where the aim is to decrease the integral action sufficiently around the steady state to have robust system performance against noises and parameter variations. The zSlices approach will give the opportunity to construct the zT2-FPI controller as a collection of IT2-FPI and T1-FPI controllers. We will present a new way to design a zT2-FPI controller based on a single tuning parameter where the features of T1-FPI (speed) and IT2-FPI (robustness) are combined without increasing the computational complexity much when compared with the IT2-FPI structure. This will allow the proposed zT2-FPI controller to achieve the desired transient state response and provide an efficient disturbance rejection and robust control performance. We will present several simulation studies on benchmark systems, in addition to real-world experiments that were performed using the PIONEER 3-DX mobile robot that will act as a platform to evaluate the proposed systems. The results will show that the control performance of the self-tuning zT2-FPI control structure enhances both the transient state and disturbance rejection performances when compared with the type-1 and IT2-FPI counterparts. In addition, the self-tuning zT2-FPI is more robust to disturbances, noise, and uncertainties when compared with the type-1 and interval type-2 fuzzy counterparts.

Human motion intention recognition is a key to achieve perfect human-machine coordination and wearing comfort of wearable robots. Surface electromyography (sEMG), as a bioelectrical signal, generates prior to the corresponding motion and reflects the human motion intention directly. Thus, a better human-machine interaction can be achieved by using sEMG based motion intention recognition. In this paper, we review and discuss the state of the art of the sEMG based motion intention recognition that is mainly used in detail. According to the method adopted, motion intention recognition is divided into two groups: sEMG-driven musculoskeletal (MS) model based motion intention recognition and machine learning (ML) model based motion intention recognition. The specific models and recognition effects of each study are analyzed and systematically compared. Finally, a discussion of the existing problems in the current studies, major advances, and future challenges is presented.