Muscle force estimation from lower limb EMG signals using novel optimised machine learning techniques

The main objective of this work is to establish a framework for processing and evaluating the lower limb electromyography (EMG) signals ready to be fed to a rehabilitation robot. We design and build a knee rehabilitation robot that works with surface EMG (sEMG) signals. In our device, the muscle forces are estimated from sEMG signals using several machine learning techniques, i.e. support vector machine (SVM), support vector regression (SVR) and random forest (RF). In order to improve the estimation accuracy, we devise genetic algorithm (GA) for parameter optimisation and feature extraction within the proposed methods. At the same time, a load cell and a wearable inertial measurement unit (IMU) are mounted on the robot to measure the muscle force and knee joint angle, respectively. Various performance measures have been employed to assess the performance of the proposed system. Our extensive experiments and comparison with related works revealed a high estimation accuracy of 98.67% for lower limb muscles. The main advantage of the proposed techniques is high estimation accuracy leading to improved performance of the therapy while muscle models become especially sensitive to the tendon stiffness and the slack length.

Global Trends and Hotspots in Research on Rehabilitation Robots: A Bibliometric Analysis From 2010 to 2020

Background: In recent years, with the development of medical science and artificial intelligence, research on rehabilitation robots has gained more and more attention, for nearly 10 years in the Web of Science database by journal of rehabilitation robot-related research literature analysis, to parse and track rehabilitation robot research hotspot and front, and provide some guidance for future research.Methods: This study employed computer retrieval of rehabilitation robot-related research published in the core data collection of the Web of Science database from 2010 to 2020, using CiteSpace 5.7 visualization software. The hotspots and frontiers of rehabilitation robot research are analyzed from the aspects of high-influence countries or regions, institutions, authors, high-frequency keywords, and emergent words.Results: A total of 3,194 articles were included. In recent years, the research on rehabilitation robots has been continuously hot, and the annual publication of relevant literature has shown a trend of steady growth. The United States ranked first with 819 papers, and China ranked second with 603 papers. Northwestern University ranked first with 161 publications. R. Riener, a professor at the University of Zurich, Switzerland, ranked as the first author with 48 articles. The Journal of Neural Engineering and Rehabilitation has the most published research, with 211 publications. In the past 10 years, research has focused on intelligent control, task analysis, and the learning, performance, and reliability of rehabilitation robots to realize the natural and precise interaction between humans and machines. Research on neural rehabilitation robots, brain–computer interface, virtual reality, flexible wearables, task analysis, and exoskeletons has attracted more and more attention.Conclusions: At present, the brain–computer interface, virtual reality, flexible wearables, task analysis, and exoskeleton rehabilitation robots are the research trends and hotspots. Future research should focus on the application of machine learning (ML), dimensionality reduction, and feature engineering technologies in the research and development of rehabilitation robots to improve the speed and accuracy of algorithms. To achieve wide application and commercialization, future rehabilitation robots should also develop toward mass production and low cost. We should pay attention to the functional needs of patients, strengthen multidisciplinary communication and cooperation, and promote rehabilitation robots to better serve the rehabilitation medical field.

Effects of a Brain-Computer Interface-Operated Lower Limb Rehabilitation Robot on Motor Function Recovery in Patients with Stroke

Purpose. To observe the effect of a brain-computer interface-operated lower limb rehabilitation robot (BCI-LLRR) on functional recovery from stroke and to explore mechanisms. Methods. Subacute-phase stroke patients were randomly divided into two groups. In addition to the routine intervention, patients in the treatment group trained on the BCI-LLRR and underwent the lower limb pedal training in the control group, both for the same time (30 min/day). All patients underwent assessment by instruments such as the National Institutes of Health Stroke Scale (NIHSS) and the Fugl–Meyer upper and lower limb motor function and balance tests, at 2 and 4 weeks of treatment and at 3 months after the end of treatment. Patients were also tested before treatment and after 4 weeks by leg motor evoked potential (MEP) and diffusion tensor imaging/tractography (DTI/DTT) of the head. Results. After 4 weeks, the Fugl–Meyer leg function and NIHSS scores were significantly improved in the treatment group vs. controls ( P < 0.01 ). At 3 months, further significant improvement was observed. The MEP amplitude and latency of the treatment group were significantly improved vs. controls. The effect of treatment on fractional anisotropy values was not significant. Conclusions. The BCI-LLRR promoted leg functional recovery after stroke and improved activities of daily living, possibly by improving cerebral-cortex excitability and white matter connectivity.

Multi-Domain Dynamic Modelling of a Low-Cost Upper Limb Rehabilitation Robot

Tracking patient progress through a course of robotic tele-rehabilitation requires constant position data logging and comparison, alongside periodic testing with no powered assistance. The test data must be compared with previous test attempts and an ideal baseline, for which a good understanding of the dynamics of the robot is required. The traditional dynamic modelling techniques for serial chain robotics, which involve forming and solving equations of motion, do not adequately describe the multi-domain phenomena that affect the movement of the rehabilitation robot. In this study, a multi-domain dynamic model for an upper limb rehabilitation robot is described. The model, built using a combination of MATLAB, SimScape, and SimScape Multibody, comprises the mechanical electro-mechanical and control domains. The performance of the model was validated against the performance of the robot when unloaded and when loaded with a human arm proxy. It is shown that this combination of software is appropriate for building a dynamic model of the robot and provides advantages over the traditional modelling approach. It is demonstrated that the responses of the model match the responses of the robot with acceptable accuracy, though the inability to model backlash was a limitation.

Research on Intelligent Following Motion Control System of Rehabilitation Robot

Background: In response to the current problem of low intelligence of mobile lower limb motor rehabilitation aids, this article proposes an intelligent control scheme based on human movement behavior in order to control the rehabilitation robot to follow the patient's movement. Methods: Firstly, a multi-sensor data acquisition system is designed according to the motion characteristics of human body. By analyzing and processing the motion data, the change law of human center of gravity and behavior intention are obtained, and the behavior intention of human is used as the control command of the robot following motion. In order to achieve the goal of the rehabilitation robot following human motion, an adaptive radial basis function neural network (ARBFNN) sliding mode controller is designed based on the robot dynamic model. The controller can reduce the impact of fluctuations in the human center of gravity on changes in the parameters of the robot control system, and enhance the adaptability of the system to other disturbance factors, and improve the accuracy of following human motion. Finally, the motion following experiment of the rehabilitation robot is carried out. Results: The experimental results show that the robot can recognize the motion intention of human body, and achieve the training goal of following different subjects to complete straight lines and curves. Conclusions: According to the experimental results, the accuracy of the multi-sensor data acquisition system and control algorithm design is verified, which demonstrates the feasibility of the proposed intelligent control scheme.

Deep reinforcement learning-based rehabilitation robot trajectory planning with optimized reward functions

Deep reinforcement learning (DRL) provides a new solution for rehabilitation robot trajectory planning in the unstructured working environment, which can bring great convenience to patients. Previous researches mainly focused on optimization strategies but ignored the construction of reward functions, which leads to low efficiency. Different from traditional sparse reward function, this paper proposes two dense reward functions. First, azimuth reward function mainly provides a global guidance and reasonable constraints in the exploration. To further improve the efficiency, a process-oriented aspiration reward function is proposed, it is capable of accelerating the exploration process and avoid locally optimal solution. Experiments show that the proposed reward functions are able to accelerate the convergence rate by 38.4% on average with the mainstream DRL methods. The mean of convergence also increases by 9.5%, and the percentage of standard deviation decreases by 21.2%–23.3%. Results show that the proposed reward functions can significantly improve learning efficiency of DRL methods, and then provide practical possibility for automatic trajectory planning of rehabilitation robot.