Electromyography (EMG) signal is one of the widely used biological signals for human motor intention prediction, which is an essential element in human-robot collaboration systems. Studies on motor ...intention prediction from EMG signal have been concentrated on classification and regression models, and there are numerous review and survey papers on classification models. However, to the best of our knowledge, there is no review paper on regression models or continuous motion prediction from EMG signal. Therefore, in this paper, we provide a comprehensive review of EMG-based motor intention prediction of continuous human upper limb motion. This review will cover the models and approaches used in continuous motion estimation, the kinematic motion parameters estimated from EMG signal, and the performance metrics utilized for system validation. From the review, we will provide some insights into future research directions on these subjects. We first review the overall structure and components of EMG-based human-robot collaboration systems. We then discuss the state of arts in continuous motion prediction of the human upper limb. Finally, we conclude the paper with a discussion of the current challenges and future research directions.
Display omitted
•Morphological transformation strategy is proposed to harvest irregular wave.•The output performance rises by 114.136 times as the wave changes.•Random wave motion is transfigured ...into bidirectional continuous rotation.•Wave-based TENG can output 39.67 mA and a peak power density of 30.62 W/m3.•The output achieves 0 % attenuation rate after operating for 7 h or within 90 %RH.
Wave is inherently characterized by disorder and randomness, which is a great challenge for the conventional wave-based triboelectric nanogenerator (W-TENG) and necessitates conducting adaptability research on the device. Therefore, we proposed a morphological transformation strategy, that is, W-TENG can actively transform the motion patterns of self-structure to accommodate the variations in waves and achieve power improvement. And a morphological transformation TENG (MT-TENG) with multi-mode operation is developed for harvesting irregular wave energy. Furthermore, the disorder wave motion is transformed into a bidirectional continuous rotation of power generation units, which realizes the continuous waveform output. Experimental results demonstrate that the wave power grows by 9.22 times with frequency increase, and the device's performance increases by 114.136 times utilizing this strategy. MT-TENG can output 39.67 mA through the energy management circuit (EMC) and a peak power density of 30.62 W/m3 under the wave excitation of 1.1 Hz. Finally, the self-powered environmental monitoring system is constructed, which can illuminate ten 30 W LEDs in series and provide a continuous energy supply to the wireless sensor module. This work presents a research paradigm for the design of wave-environment adaptability, holding significant implications for improving performance and constructing self-powered sensing systems.
Display omitted
•Persistent luminescence-activated nanomotors are engineered with integration of phototherapies.•The generated persistent luminescence acts as an internal light source for continuous ...phototherapy.•Persistent heat gradients create thermophoretic force on Janus nanoparticles to drive their motion.•Persistent luminescence-activated motion enhances tumor distribution and cell internalization.•Synergistic and persistent photothermal and photodynamic therapies promote antitumor efficacy.
Cancer photothermal (PTT) and photodynamic therapies (PDT) have aroused tremendous attention with high spatial specificity, but they experience the challenges from the inefficient tumor accumulation and penetration of photosensitizers and dose-dependent side effects. Herein, persistent luminescence (PL)-activated nanomotors are developed with the integration of PL-illuminated PTT and PDT to overcome these limitations. PL nanodots of ZnGa2O4:Cr3+ (ZGC) were deposited on mesoporous silica nanoparticles (NPs), followed by conjugation of silicon phthalocyanine as a photosensitizer and capping with polydopamine (PDA) to fabricate Janus mPL-Pc@PDA NPs. ZGC nanodots on NPs are activated by external illumination to generate PL as an internal light source to excite PDA and phthalocyanine for persistent productions of heat and reactive oxygen species (ROS), avoiding high heat stress and ROS levels in the conventional intermittent phototherapy. In addition, the persistent heat gradients around the Janus NPs create thermophoretic force to drive their motions and enhance their cellular uptake, and the PL-illuminated PDT continuously produces intracellular ROS to damage tumor cells. Light activation of mPL-Pc@PDA obviously promotes accumulation and deep penetration of NPs into tumors and produces mild thermal and ROS levels with well distribution across the tumors. The self-propelled tumor distribution and the combined PDT/PTT treatment led to full inhibition of tumor growth and significant extension of animal survival, and there is no systemic toxicity and function fluctuation of the major organs. Thus, this study demonstrates a concise strategy to generate PL-activated motion for deep penetration and produce PL-illuminated PDT/PTT for synergistic tumor treatment.
•Rehabilitation motion data of 8 healthy subjects were acquired.•Multiple decomposition feature preserved more complete information of sEMG.•Bidirectional mechanism of BiLSTM alleviated the ...asynchrony of data.
In human-robot interaction systems oriented to rehabilitation training, surface electromyogram (sEMG)-based human motion intention recognition has essential application value. Compared with discrete motion classification, continuous motion estimation is more natural, fast, and accurate. However, due to the non-stability, non-linearity, and strong randomness of sEMG, the effective motion information of sEMG is often lost when extracting the time-domain features of sEMG, and there are also cases where sEMG and joint angle data are not completely synchronized in practical applications, all of which affect the performance of continuous motion estimation. To solve the above problems, this paper firstly proposed a multiple decomposition feature (MDF) representation method based on variational mode decomposition (VMD) and wavelet packet transform (WPT), which can extract more hidden motion information of sEMG from multiple frequency scales; then introduced a bi-directional long short-term memory (BiLSTM) network to establish the regression model between sEMG and joint angle to deal with the incomplete synchronization problem between the input and output data. The experimental results showed that the multiple decomposition feature and the BiLSTM network regression model used in this paper could significantly improve the estimation performance in continuous motion estimation.
Presently, there is a dearth of professional climbers to carry out coconut harvesting because it involves considerable risk posed by the tree height and uneven trunk surface. Numerous ...coconut-tree-climbing devices have been developed to overcome this issue, but human effort is still required. Hence, it is imperative to develop a wheel-driven mechanism in the structure with a continuous motion to harvest coconuts. By featuring an anti-falling capability, the climber can be stable in static and dynamic conditions. This feature can be achieved by attaching springs in the supporting frame during vertical climbing on the trunk surface. This paper presents a 3D modeling and the static and dynamic analysis of a climbing machine. The climbing field trials of the climbing model were carried out on a coconut tree trunk, and the best climbing rate that was achieved was 0.3 m in 1.6 seconds. Control of the climber maneuverability was tested with an embedded processor board. The maturity identification of coconuts in a complex background was successfully achieved with a detection score of 99% on real-time images by using deep learning techniques. This study can be extended to identify the cutting point of the coconut bunches for harvesting.
(1) Background: Three-dimensional (3-D) hand position is one of the kinematic parameters that can be inferred from Electromyography (EMG) signals. The inferred parameter is used as a communication ...channel in human-robot collaboration applications. Although its application from the perspective of rehabilitation and assistive technologies are widely studied, there are few papers on its application involving healthy subjects such as intelligent manufacturing and skill transfer. In this regard, for tasks associated with complex hand trajectories without the consideration of the degree of freedom (DOF), the prediction of 3-D hand position from EMG signal alone has not been addressed. (2) Objective: The primary aim of this study is to propose a model to predict human motor intention that can be used as information from human to robot. Therefore, the prediction of a 3-D hand position directly from the EMG signal for complex trajectories of hand movement, without the direct consideration of joint movements, is studied. In addition, the effects of slow and fast motions on the accuracy of the prediction model are analyzed. (3) Methods: This study used the EMG signal that is collected from the upper limb of healthy subjects, and the position signal of the hand while the subjects manipulate complex trajectories. We considered and analyzed two types of tasks with complex trajectories, each with quick and slow motions. A recurrent fuzzy neural network (RFNN) model was constructed to predict the 3-D position of the hand from the features of EMG signals alone. We used the Pearson correlation coefficient (CC) and normalized root mean square error (NRMSE) as performance metrics. (4) Results: We found that 3-D hand positions of the complex movement can be predicted with the mean performance of CC = 0.85 and NRMSE = 0.105. The 3-D hand position can be predicted well within a future time of 250 ms, from the EMG signal alone. Even though tasks performed under quick motion had a better prediction performance; the statistical difference in the accuracy of prediction between quick and slow motion was insignificant. Concerning the prediction model, we found that RFNN has a good performance in decoding for the time-varying system. (5) Conclusions: In this paper, irrespective of the speed of the motion, the 3-D hand position is predicted from the EMG signal alone. The proposed approach can be used in human-robot collaboration applications to enhance the natural interaction between a human and a robot.
Continuous motion estimation of human limb plays a vital role in human-robot interaction (HRI) and collaboration (HRC), which can facilitate more natural and active HRI. However, the prediction ...accuracy of continuous motion estimation needs to be improved, moreover, the noise interference in motion estimation should be suppressed in practical applications. In this paper, the sEMG-based closed-loop model combining the noise-tolerant zeroing neural network (NTZNN) and the long short-term memory (LSTM) network (termed as the L-NTZNN closed-loop model) is proposed for continuous motion estimation in different noise-polluted conditions. On the basis of the LSTM model, the zeroing neural network-based (L-ZNN) and the gradient neural network-based (L-GNN) models are presented for comparison. The advantage of this work is that the L-NTZNN closed-loop model has higher prediction accuracy and stronger anti-noise performance in noise-polluted condition compared with the L-ZNN, the L-GNN, the LSTM and the Gaussian process regression (GPR) models. The root mean squared error (RMSE) and the coefficient of determination (R2) of the L-NTZNN in continuous motion estimation prove its superiority in different noise-polluted conditions (R2: 0.9881, 0.9812, 0.9858, 0.9775; RMSE: 0.0793, 0.1069, 0.0949, 0.1271). The Kruskal-Wallis test reports that the L-NTZNN closed-loop model has significantly ascendancy over the other models in respect of prediction accuracy and noise-tolerant property (p<0.05). In addition, the stability and generalization ability of the proposed L-NTZNN closed-loop model for different subjects are verified.
This work investigates a new sensing technology for use in robotic human-machine interface (HMI) applications. The proposed method uses near E-field sensing to measure small changes in the limb ...surface topography due to muscle actuation over time. The sensors introduced in this work provide a non-contact, low-computational-cost, and low-noise method for sensing muscle activity. By evaluating the key sensor characteristics, such as accuracy, hysteresis, and resolution, the performance of this sensor is validated. Then, to understand the potential performance in intention detection, the unmodified digital output of the sensor is analysed against movements of the hand and fingers. This is done to demonstrate the worst-case scenario and to show that the sensor provides highly targeted and relevant data on muscle activation before any further processing. Finally, a convolutional neural network is used to perform joint angle prediction over nine degrees of freedom, achieving high-level regression performance with an RMSE value of less than six degrees for thumb and wrist movements and 11 degrees for finger movements. This work demonstrates the promising performance of this novel approach to sensing for use in human-machine interfaces.
In this paper, we present a simultaneous and continuous kinematics estimation method for multiple DoFs across shoulder and elbow joint. Although simultaneous and continuous kinematics estimation from ...surface electromyography (EMG) is a feasible way to achieve natural and intuitive human-machine interaction, few works investigated multi-DoF estimation across the significant joints of upper limb, shoulder and elbow joints. This paper evaluates the feasibility to estimate 4-DoF kinematics at shoulder and elbow during coordinated arm movements. Considering the potential applications of this method in exoskeleton, prosthetics and other arm rehabilitation techniques, the estimation performance is presented with different muscle activity decomposition and learning strategies. Principle component analysis (PCA) and independent component analysis (ICA) are respectively employed for EMG mode decomposition with artificial neural network (ANN) for learning the electromechanical association. Four joint angles across shoulder and elbow are simultaneously and continuously estimated from EMG in four coordinated arm movements. By using ICA (PCA) and single ANN, the average estimation accuracy 91.12% (90.23%) is obtained in 70-s intra-cross validation and 87.00% (86.30%) is obtained in 2-min inter-cross validation. This result suggests it is feasible and effective to use ICA (PCA) with single ANN for multi-joint kinematics estimation in variant application conditions.