Abstract-Robot-assisted rehabilitation offers benefits such as repetitive, intensive and task specific training as compared to traditional manual manipulation performed by physiotherapists. In this paper, a robust iterative feedback tuning (IFT) technique for repetitive training control of a compliant parallel ankle rehabilitation robot is presented. The robot employs four parallel intrinsically compliant pneumatic muscle actuators that mimic skeletal muscles for ankle's motion training. A multiple degreesof-freedom normalised IFT technique is proposed to increase the controller robustness by obtaining an optimal value for the weighting factor and offering a method with learning capacity to achieve an optimum of the controller parameters. Experiments with human participants were conducted to investigate the robustness as well as to validate the performance of the proposed IFT technique. Results show that the normalised IFT scheme will achieve a better and better tracking performance during the robot repetitive control and provides more robustness to the system by adapting to various situations in robotic rehabilitation.

Objective. A motor-imagery-based brain-computer interface (MI-BCI) provides an alternative way for people to interface with the outside world. However, the classification accuracy of MI signals remains challenging, especially with an increased number of classes and the presence of high variations with data from multiple individual people. This work investigates electroencephalogram (EEG) signal processing techniques, aiming to enhance the classification performance of multiple MI tasks in terms of tackling the challenges caused by the vast variety of subjects. Approach. This work introduces a novel method to extract discriminative features by combining the features of functional brain networks with two other feature extraction algorithms: common spatial pattern (CSP) and local characteristic-scale decomposition (LCD). After functional brain networks are established from the MI EEG signals of the subjects, the measures of degree in the binary networks are extracted as additional features and fused with features in the frequency and spatial domains extracted by the CSP and LCD algorithms. A real-time BCI robot control system is designed and implemented with the proposed method. Subjects can control the movement of the robot through four classes of MI tasks. Both the BCI competition IV dataset 2a and real-time data acquired in our designed system are used to validate the performance of the proposed method. Main results. As for the offline data experiment results, the average classification accuracy of the proposed method reaches 79.7%, outperforming the majority of popular algorithms. Experimental results with real-time data also prove the proposed method to be highly promising in its real-time performance. Significance. The experimental results show that our proposed method is robust in extracting discriminative brain activity features when performing different MI tasks, hence improving the classification accuracy in four-class MI tasks. The high classification accuracy and low computational demand show a considerable practicality for real-time rehabilitation systems.

Pneumatic artificial muscles (PAMs) have been widely used in actuation of medical devices due to their intrinsic compliance and high power to weight ratio features. However, the nonlinearity and time-varying nature of PAMs makes it challenging to maintain highperformance tracking control. In this paper, a High-Order Pseudo-Partial Derivative based Model-Free Adaptive Iterative Learning Controller (HOPPD-MFAILC) is proposed to achieve fast convergence speed. The dynamics of PAM is converted into a dynamic linearization model during iterations, meanwhile, a high-order estimation algorithm is designed to estimate the pseudo-partial derivative component of the linearization model by only utilizing the input and output data in previous iterations. The stability and convergence performance of the controller is verified through theoretical analysis. Simulation and experimental results on PAM demonstrate that the proposed HOPPD-MFA ILC can track the desired trajectory with improved convergence and tracking performance. Index Terms-Pneumatic artificial muscle, model-free adaptive control, iterative learning control, convergence. I. INTRODUCTION NEUMATIC artificial muscle (PAM) is a tube-like actuator that largely mimics biological human muscle functions [1]. Compared to traditional electrical motors and hydraulic actuators, the lightweight, high compliance and high power-to-weight ratio of PAMs [2] have fueled their popularity among assistive exoskeletons and rehabilitation robots, such as the upper limb exoskeleton series RUPERT [3] and the lower limb orthotics KAFO [4]. However, unlike the conventional actuators adopted in Lokomat [5] and ArmeoPower [6], the nonlinear and time-varying nature of PAMs may cause Manuscript

Since surface electromyograghic (sEMG) signals are non-invasive and capable of reflecting humans' motion intention, they have been widely used for the motion recognition of upper limbs. However, limited research has been conducted for lower limbs, because the sEMGs of lower limbs are easily affected by body gravity and muscle jitter. In this paper, sEMG signals and accelerometer signals are acquired and fused to recognize the motion patterns of lower limbs. A curve fitting method based on median filtering is proposed to remove accelerometer noise. As for movement onset detection, an sEMG power spectral correlation coefficient method is used to detect the start and end points of active signals. Then, the time-domain features and wavelet coefficients of sEMG signals are extracted, and a dynamic time warping (DTW) distance is used for feature extraction of acceleration signals. At last, five lower limbs' motions are classified and recognized by using Gaussian kernel-based linear discriminant analysis (LDA) and support vector machine (SVM) respectively. The results prove that the fused feature-based classification outperforms the classification with only sEMG signals or accelerometer signals, and the fused feature can achieve 95% or higher recognition accuracy, demonstrating the validity of the proposed method.

A rehabilitation robot plays an important role in relieving the therapists’ burden and helping patients with ankle injuries to perform more accurate and effective rehabilitation training. However, a majority of current ankle rehabilitation robots are rigid and have drawbacks in terms of complex structure, poor flexibility and lack of safety. Taking advantages of pneumatic muscles’ good flexibility and light weight, we developed a novel two degrees of freedom (2-DOF) parallel compliant ankle rehabilitation robot actuated by pneumatic muscles (PMs). To solve the PM’s nonlinear characteristics during operation and to tackle the human-robot uncertainties in rehabilitation, an adaptive backstepping sliding mode control (ABS-SMC) method is proposed in this paper. The human-robot external disturbance can be estimated by an observer, who is then used to adjust the robot output to accommodate external changes. The system stability is guaranteed by the Lyapunov stability theorem. Experimental results on the compliant ankle rehabilitation robot show that the proposed ABS-SMC is able to estimate the external disturbance online and adjust the control output in real time during operation, resulting in a higher trajectory tracking accuracy and better response performance especially in dynamic conditions.