Robot-assisted rehabilitation, which can provide repetitive, intensive and high-precision physics training, has a positive influence on motor function recovery of stroke patients. Current robots need to be more intelligent and more reliable in clinical practice. Machine learning algorithms (MLAs) are able to learn from data and predict future unknown conditions, which is of benefit to improve the effectiveness of robot-assisted rehabilitation. In this paper, we conduct a focused review on machine learning-based methods for robot-assisted upper limb rehabilitation. Firstly, the current status of upper rehabilitation robots is presented. Then, we outline and analyze the designs and applications of MLAs for upper limb movement intention recognition, human-robot interaction control and quantitative assessment of motor function. Meanwhile, we discuss the future directions of MLAs-based robotic rehabilitation. This review article provides a summary of MLAs for robotic upper limb rehabilitation and contributes to the design and development of future advanced intelligent medical devices.

Disassembly is a core procedure in remanufacturing. Disassembly is currently carried out mainly by human operators. It is important to reduce the labor content of disassembly through automation, to make remanufacturing more economically attractive. Threaded fastener removal is one of the most difficult disassembly tasks to be fully automated. This article presents a new method developed for automating the unfastening of screws. An electric nutrunner spindle with a geared offset adapter was fitted to the end of a collaborative robot. The position of a hexagonal headed screw in a fitted stage was known only approximately, and its orientation in the hole was unknown. The robot was programed to perform a spiral search motion to engage the tool onto the screw. A control strategy combining torque and position monitoring with active compliance was implemented. An existing robot cell was modified and utilized to demonstrate the concept and to assess the feasibility of the solution using a turbocharger as a disassembly case study. Note to Practitioners-Remanufacturing is known to generate substantial economic, social, and environmental benefits. Disassembly is the first operation in a remanufacturing process chain. Unfastening threaded parts (“unscrewing”) is a common disassembly task accounting for approximately 40% of all disassembly activity. Like other disassembly tasks, often, unscrewing has to be carried out manually in remanufacturing due to difficulties caused by the variable and unpredictable condition of the end-of-life (EoL) products to be remanufactured. Automating unscrewing operations should reduce the labor content of disassembly, thus lowering remanufacturing costs and promoting the adoption of remanufacturing. This article proposes the use of a collaborative robot to perform autonomous unfastening of hexagonal headed screws. Collaborative robots have built-in force sensors and can be programed to carry out operations involving not only position but also active force and compliance control. They can work safely alongside human operators, enabling the latter to focus on jobs requiring high cognitive or manipulation abilities. The article presents a novel spiral search technique developed to improve the rate of successful engagement between the robot end effector and the screw heads despite uncertainties in the location of the screws. The technique was successfully demonstrated on the dismantling of a turbocharger but can readily be applied to other EoL products with hexagonal headed screws. It can also be used with other kinds of screws (e.g., Phillips screws and slotted-head screws) simply by changing the tool and tuning the robot control parameters. A limitation of the proposed technique is that it can only deal reliably with undamaged screws. In our future research, we will consider screws that are in imperfect conditions through usage and develop appropriate solutions for their removal by robots.

Motor Imagery (MI) electroencephalography (EEG) is widely studied for its non-invasiveness, easy availability, portability, and high temporal resolution. As for MI EEG signal processing, the high dimensions of features represent a research challenge. It is necessary to eliminate redundant features, which not only create an additional overhead of managing the space complexity, but also might include outliers, thereby reducing classification accuracy. The firefly algorithm (FA) can adaptively select the best subset of features, and improve classification accuracy. However, the FA is easily entrapped in a local optimum. To solve this problem, this paper proposes a method of combining the firefly algorithm and learning automata (LA) to optimize feature selection for motor imagery EEG. We employed a method of combining common spatial pattern (CSP) and local characteristic-scale decomposition (LCD) algorithms to obtain a high dimensional feature set, and classified it by using the spectral regression discriminant analysis (SRDA) classifier. Both the fourth brain–computer interface competition data and real-time data acquired in our designed experiments were used to verify the validation of the proposed method. Compared with genetic and adaptive weight particle swarm optimization algorithms, the experimental results show that our proposed method effectively eliminates redundant features, and improves the classification accuracy of MI EEG signals. In addition, a real-time brain–computer interface system was implemented to verify the feasibility of our proposed methods being applied in practical brain–computer interface systems.

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.