Markovian Robust Compliance Control Based on Electromyographic Signals

This study develops a comprehensive robotic system, termed the robot cognitive system, for complex environments, integrating three models: the engagement model, the intention model, and the human-robot interaction (HRI) model. The system aims to enhance the naturalness and comfort of HRI by enabling robots to detect human behaviors, intentions, and emotions accurately. A novel dual-arm-hand mobile robot, Mobi, was designed to demonstrate the system's efficacy. The engagement model utilizes eye gaze, head pose, and action recognition to determine the suitable moment for interaction initiation, addressing potential eye contact anxiety. The intention model employs sentiment analysis and emotion classification to infer the interactor's intentions. The HRI model, integrated with Google Dialogflow, facilitates appropriate robot responses based on user feedback. The system's performance was validated in a retail environment scenario, demonstrating its potential to improve the user experience in HRIs.

In this study, the observation model of Kalman Filter (KF) is extended to an errors-in-variables (EIV) model because the observations may exist in the design matrix of the observation model. Then, a robust total least squares method (RTLS) is introduced into the KF, and a robust total Kalman filter (RTKF) algorithm is derived. The RTKF is a simple, flexible and effective algorithm. It is simple because its computational formulae are similar to the computational formulae of a standard KF; it is flexible because it can be used in a wide range of applications; it is effective because the influence of outliers on estimated results is weakened. Finally, the simulated example of the indoor location and the empirical example of pseudorange differential positioning are used to demonstrate the performance of the RTKF algorithm. The results prove the validity, robustness, and reliability of the RTKF in dealing with the outliers that exist in both observation vector and design matrix of the EIV model. Furthermore, the results of the empirical example show that the RTKF improves the precision of a pseudorange differential positioning compared with KF and robust Kalman filter (RKF) algorithms regardless the observation model has outliers or not in this empirical example.

Electromyography (EMG) signals hold critical significance in biomedical research, capturing muscle electrical activity during rest and contraction in the upper limb. Their versatility in applications, particularly in human-assisting robotic tools, drives ongoing exploration and research. This paper presents an original study focusing on leveraging machine learning techniques to classify EMG datasets and efficiently control a robotic arm based on predicted gestures. Data acquisition involves strategically placing an EMG muscle sensor on the forearm to ensure precise measurement of signals associated with hand gestures and movements. Diverse classifiers including random forest, support vector machine (SVM), K-nearest neighbors (KNN), Gaussian naïve Bayes, gated recurrent unit (GRU), long short-term memory (LSTM), artificial neural network (ANN), recurrent neural network (RNN), convolutional neural network (CNN), and vision transformer (ViT) are employed. Performance results are meticulously analyzed and presented in tabular format, showcasing the ViT classifier as the most successful, achieving an impressive 97.7% accuracy in robotic arm control. Notably, ANN, RNN, and CNN also exhibit high accuracy exceeding 90%. Furthermore, this work is comprehensively compared with existing literature, laying the groundwork for future advancements in human-robot interaction and cutting-edge assistive technologies that markedly enhance the quality of life for individuals with motor impairments or disabilities. The findings carry significant implications for designing and implementing intuitive, responsive robotic systems based on EMG signals.

In recent years, advances in human robot interaction (HRI) has shown massive potential for universal control of robots. Among them, electromyography (EMG) signals generated by motions of muscles have been identified as an important and useful source. Powered by recently emerged machine learning algorithms, real-time classification has been proved applicable to control robots. However, collecting EMG signals with minimum number of electrodes for real-time classification and robotic control is still a challenge. In this paper, we demonstrate that twenty five robotic commands in a robotic arm can be controlled in real time by using the EMG signals collected from only two pairs of active surface electrodes on each forearm of human subjects. To achieve this task, a variety of tested ML models for this classification were tested. Among them, the Gaussian Naïve Bayes (GNB) achieved an accuracy of >96%. This unprecedented level of classification accuracy of the EMG signals collected from the least number of active electrodes suggest that by combination of optimized electrode configuration and a suitable ML model, the capability of robotic control can be maximized.

Compliance control is highly relevant to human safety in human–robot interaction (HRI). This paper presents a review of various compliance control techniques. The paper is aimed to provide a good background knowledge for new researchers and highlight the current hot issues in compliance control research. Active compliance, passive compliance, adaptive and reinforcement learning-based compliance control techniques are discussed. This paper provides a comprehensive literature survey of compliance control keeping in view physical human robot interaction (pHRI) e.g., passing an object, such as a cup, between a human and a robot. Compliance control may eventually provide an immediate and effective layer of safety by avoiding pushing, pulling or clamping in pHRI. Emerging areas such as soft robotics, which exploit the deformability of biomaterial as well as hybrid approaches which combine active and passive compliance are also highlighted.

This paper proposes a new algorithm for tracking time-varying channels in impulsive noise environment using a robust Kalman filter. It employs a simple dynamical model of the channel, where the changes in the impulse response coefficients are due entirely to the innovations of the Kalman filter. This reduces the arithmetic complexity, while offering reasonable good performance. The robust Kalman filter is used to restrain the adverse effect of impulsive noise and provide estimates of the covariance matrices of the state and measurement noises. The noisy channel estimates from the Kalman filter can be used to estimate the parameters of the channel coefficients when they are assumed to follow an AR model. Finally, the two processes can be coupled together to further improve the performance. Simulation results show that the new algorithm gives more stable performance than the conventional methods under impulsive noise environment.

For multisensor systems with uncertain noise variances, a centralized fusion steady-state robust Kalman filter with the upper bound of noise variances is presented. Based on the Lyapunov equation, it is proved that the local and centralized fusion steady-state Kalman filter are robust, i.e., the variances of the actual filtering errors are less than conservative variances of the corresponding robust Kalman filters. Further, it is proved that the robust accuracy of the centralized fusion robust Kalman filter is higher than that of the local robust Kalman filter. A Monte-Carlo simulation example shows its correctness.

Time-differenced carrier phase (TDCP) is a commonly used method of precise velocimetry, but when the receiver is in a dynamic or complex observation environment, the estimation accuracy is reduced. Doppler velocimetry aims at estimating instantaneous velocity, and the accuracy is restricted by the accuracy of measurement. However, in such unfavourable cases, the Doppler measurement is more reliable than the carrier phase measurement. This paper derives the relationship between Doppler observation and TDCP observation, then proposes a Doppler enhanced TDCP algorithm, for the purpose of improving the velocity estimation accuracy in dynamic and complex observation environments. In addition, considering the error caused by the constant speed state update model in the robust Kalman filter (RKF), this paper designs a terrain adaptive and robust Kalman filter (TARKF). After three experimental tests, the improved TDCP algorithm can significantly increase the speed measurement accuracy to sub-metre per second, and the accuracy can be further improved after using TARKF.

This chapter provides a comprehensive overview of electromyography (EMG), a widely used technique for recording and evaluating electrical impulses generated by skeletal muscles. EMG signals have gained significant attention in the field of assistive robotics as a means of facilitating human–machine interaction (HMI). The chapter delves into the generation of EMG signals by muscles and their conversion into neurological commands that actuate body parts. Various techniques for recording EMG signals, such as Surface EMG (sEMG), Intramuscular EMG (iEMG), High-Density EMG (HD-EMG), Wireless EMG, and Dry EMG, are discussed in detail. The chapter further investigates the factors that can significantly impact the quality of EMG signals, including electrode placement, muscle fiber orientation, muscle contraction intensity, fatigue, skin impedance, crosstalk, filtering, and movement artifact. This chapter also provides insights into the implementation areas of EMG in assistive robotics, including prosthetics, exoskeletons, rehabilitation, wheelchair control, home automation, augmentative and alternative communication (AAC), human–robot interaction (HRI), and biomechanical analysis, where EMG signals have been increasingly utilized to enhance communication and control in human–robot interfaces. The chapter concludes with a discussion of the latest research advancements in the field of EMG and its application in assistive robotics, including the use of machine learning and artificial intelligence to improve EMG signal processing and interpretation, the development of new electrode materials and configurations, and the integration of EMG with other sensing technologies.

This paper studies the problem of the designing the robust local and centralized fusion Kalman filters for multisensor system with uncertain noise variances. Using the minimax robust estimation principle, the centralized fusion robust time-varying Kalman filters are presented based on the worst-case conservative system with the conservative upper bound of noise variances. A Lyapunov approach is proposed for the robustness analysis and their robust accuracy relations are proved. It is proved that the robust accuracy of robust centralized fuser is higher than those of robust local Kalman filters. Specially, the corresponding steady-state robust local and centralized fusion Kalman filters are also proposed and the convergence in a realization between time-varying and steady-state Kalman filters is proved by the dynamic error system analysis (DESA) method and dynamic variance error system analysis (DVESA) method. A Monte-Carlo simulation example shows the robustness and accuracy relations. DOI : http://dx.doi.org/10.11591/telkomnika.v12i6.5490 Full Text: PDF

This article proposes two robust Kalman filters to solve the issue of inaccurate modeling in multiplicative noise systems due to epistemic limitations. First, we construct all conceivable state/measurement transition probability densities as an ambiguity set. This ambiguity set chooses the Wasserstein distance or the moment‐based metric as the distance metric. Besides, this set is an inequality set with a chosen tolerance, which can be seen as a non‐negative radius ball. Then, by combining the robust solution of the least favorable model in that ball with the alternating direction method of multipliers or an efficient direct solution method, we propose two robust Kalman filters based on the minimum mean square error criterion. A classical example is provided to verify the effectiveness of the proposed robust filters in comparison to existing state‐of‐the‐art filters.

The lightweight human-robot interaction model with high real-time, high accuracy, and strong anti-interference capability can be better applied to future lunar surface exploration and construction work. Based on the feature information inputted from the monocular camera, the signal acquisition and processing fusion of the astronaut gesture and eye-movement modal interaction can be performed. Compared with the single mode, the human-robot interaction model of bimodal collaboration can achieve the issuance of complex interactive commands more efficiently. The optimization of the target detection model is executed by inserting attention into YOLOv4 and filtering image motion blur. The central coordinates of pupils are identified by the neural network to realize the human-robot interaction in the eye movement mode. The fusion between the astronaut gesture signal and eye movement signal is performed at the end of the collaborative model to achieve complex command interactions based on a lightweight model. The dataset used in the network training is enhanced and extended to simulate the realistic lunar space interaction environment. The human-robot interaction effects of complex commands in the single mode are compared with those of complex commands in the bimodal collaboration. The experimental results show that the concatenated interaction model of the astronaut gesture and eye movement signals can excavate the bimodal interaction signal better, discriminate the complex interaction commands more quickly, and has stronger signal anti-interference capability based on its stronger feature information mining ability. Compared with the command interaction realized by using the single gesture modal signal and the single eye movement modal signal, the interaction model of bimodal collaboration is shorter about 79% to 91% of the time under the single mode interaction. Regardless of the influence of any image interference item, the overall judgment accuracy of the proposed model can be maintained at about 83% to 97%. The effectiveness of the proposed method is verified.

Many of the most sophisticated human-robot interaction control schemes fall short when it comes to ensuring safe interactions, primarily because they do not generate bounded control actions. Recent advancements have introduced saturating control schemes to tackle this problem, but these approaches are heavily reliant on precise dynamics of the robotic system. In this context, the paper proposes an innovative adaptive impedance control scheme that utilizes electromyographic (EMG) signals to estimate joint torque, thereby ensuring the generation of bounded control actions to regulate the behavior of exoskeleton-type robotic systems. This scheme is classified as a hybrid controller, which sets it apart from the majority of kinematic controllers that typically use proportional-derivative (PD) or proportional-integral-derivative (PID) control schemes. Unlike these conventional approaches, which depend on accurate mathematical models for effective tracking and stability, the proposed scheme integrates adaptive mechanisms to enhance performance. Validation through numerical simulations and experimental tests using the Hill muscle model confirms the scheme’s effectiveness and reliability in managing both isometric and continuous joint movements, underscoring its significant potential for ensuring safe and adaptive human-exoskeleton interactions.

The paper solves the robust weighted fusion Kalman filtering problem for systems with linearly correlated noise and mixed uncertainties of noise variances, multiplicative noises, and multiple networked inducements including missing measurements, packets dropouts, and two‐step random measurement delays. It is assumed that system noise variances are uncertain but bounded above, and the other four uncertainties are compensated to fictitious white noise by the proposed model‐transformation method. For the transformed local multimodel system with correlated fictitious noise, the robust local time‐varying recursive Kalman filters are presented by decorrelation technique and minimax robust filtering principle. Then the six weighted fusion robust Kalman filters are presented in a unified form. The robustness of local and fused robust Kalman filters is proved by the extended Lyapunov equation approach, matrix factorization, and elementary transformation. Further, the local and fused steady‐state robust Kalman filters are designed. Finally, a simulation study applied to F404 aircraft engine system is provided to examine effectiveness and applicability of the proposed algorithm.

This paper investigates the output‐constrained control problem for physical human–robot interaction using electromyography signals. An interaction force estimation method based on surface electromyography (sEMG) signals is introduced, where random forest is provided to extract interaction force information from sEMG signals. Using sEMG, the interaction force between the robotic and human operator can be separated from that in the environment. An adaptive optimal tracking controller based on robot velocity prediction error feedback is designed, in which an asymmetric time‐varying integral barrier Lyapunov function is used to deal with dynamic spatial constraints. Finally, stability analysis is provided, and the effectiveness is verified by experiments based on a 7‐degree‐of‐freedom Franka Panda robot.