Electromyography(EMG)has already been broadly used in human-machine interaction(HMI)applications.Determining how to decode the information inside EMG signals robustly and accurately is a key problem for which we urgen...Electromyography(EMG)has already been broadly used in human-machine interaction(HMI)applications.Determining how to decode the information inside EMG signals robustly and accurately is a key problem for which we urgently need a solution.Recently,many EMG pattern recognition tasks have been addressed using deep learning methods.In this paper,we analyze recent papers and present a literature review describing the role that deep learning plays in EMG-based HMI.An overview of typical network structures and processing schemes will be provided.Recent progress in typical tasks such as movement classification,joint angle prediction,and force/torque estimation will be introduced.New issues,including multimodal sensing,inter-subject/inter-session,and robustness toward disturbances will be discussed.We attempt to provide a comprehensive analysis of current research by discussing the advantages,challenges,and opportunities brought by deep learning.We hope that deep learning can aid in eliminating factors that hinder the development of EMG-based HMI systems.Furthermore,possible future directions will be presented to pave the way for future research.展开更多
Exoskeleton robots and their control methods have been extensively developed to aid post-stroke rehabilitation. Most of the existing methods using linear controllers are designed for position control and are not suita...Exoskeleton robots and their control methods have been extensively developed to aid post-stroke rehabilitation. Most of the existing methods using linear controllers are designed for position control and are not suitable for human-machine interaction(HMI) force control, as the interaction system between the human body and exoskeleton is uncertain and nonlinear. We present an approach for HMI force control via model reference adaptive impedance control(MRAIC) to solve this problem in case of index finger exoskeleton control. First, a dynamic HMI model, which is based on a position control inner loop, is formulated. Second, the theoretical MRAC framework is implemented in the control system. Then, the adaptive controllers are designed according to the Lyapunov stability theory. To verify the performance of the proposed method, we compare it with a proportional-integral-derivative(PID) method in the time domain with real experiments and in the frequency domain with simulations. The results illustrate the effectiveness and robustness of the proposed method in solving the nonlinear HMI force control problem in hand exoskeleton.展开更多
For human assistance device, the particular properties are usually focused on high precision, compliant interaction, large torque generation and compactness of the mechanical system. To realize the high performance of...For human assistance device, the particular properties are usually focused on high precision, compliant interaction, large torque generation and compactness of the mechanical system. To realize the high performance of lower extremity augmentation device, in this paper, we introduce a novel control methodology for compact elastic module. Based on the previous work, the elastic module consists of two parts, i.e., the proximal interaction module and the distal control module. To improve the compactness of the exoskeleton, we only employ the distal control module to achieve both purposes of precision force control and human intention recognition with physical human-machine interaction. In addition, a novel control methodology, so-called high precision data-driven force control with disturbance observer is adopted in this paper. To assess our proposed control methodology, we compare our novel force control with several other control methodologies on the lower extremity augmentation single leg exoskeleton system. The experiment shows a satisfying result and promising application feasibility of the proposed control methodology.展开更多
In this article I will address the issue of the meaning of Embodied Artificial Intelligence(EAI)as it is configured today.My starting point is the refined interactive perspective on the semantics of EAI,as was recentl...In this article I will address the issue of the meaning of Embodied Artificial Intelligence(EAI)as it is configured today.My starting point is the refined interactive perspective on the semantics of EAI,as was recently suggested by Froese and colleagues.This perspective rests on the assumption that the concept of human bodily subjectivity must be extended to include meaning-making processes,which are enabled by advanced AI systems that may be incorporated in the human biological body.After having clarified the technical background,I will introduce the genetic component of the phenomenological method as a suitable tool to face the aforementioned issue.Towards this end,I will place the genetic method in the context of the so-called New Human-Machine Interaction(New HMI).I will further outline a genetic phenomenology of visual embodiment,suggesting a futuristic application based on the thesis of the“technological supplementation of phenomenological methodology”through the synthetic method.The case at stake is that of patients with a severe clinical picture characterised by the loss of corneal function,who in the near future could be treated with synthetic corneal prosthetic implants produced by a 3D bio-printing process by using an advanced EAI technique.I will conclude this article with a brief review of the main problems that still remain open.展开更多
基金supported in part by the National Natural Science Foundation of China(U181321461773369+2 种基金61903360)the Selfplanned Project of the State Key Laboratory of Robotics(2020-Z12)China Postdoctoral Science Foundation funded project(2019M661155)。
文摘Electromyography(EMG)has already been broadly used in human-machine interaction(HMI)applications.Determining how to decode the information inside EMG signals robustly and accurately is a key problem for which we urgently need a solution.Recently,many EMG pattern recognition tasks have been addressed using deep learning methods.In this paper,we analyze recent papers and present a literature review describing the role that deep learning plays in EMG-based HMI.An overview of typical network structures and processing schemes will be provided.Recent progress in typical tasks such as movement classification,joint angle prediction,and force/torque estimation will be introduced.New issues,including multimodal sensing,inter-subject/inter-session,and robustness toward disturbances will be discussed.We attempt to provide a comprehensive analysis of current research by discussing the advantages,challenges,and opportunities brought by deep learning.We hope that deep learning can aid in eliminating factors that hinder the development of EMG-based HMI systems.Furthermore,possible future directions will be presented to pave the way for future research.
基金Project supported by the National Natural Science Foundation of China(No.51221004)
文摘Exoskeleton robots and their control methods have been extensively developed to aid post-stroke rehabilitation. Most of the existing methods using linear controllers are designed for position control and are not suitable for human-machine interaction(HMI) force control, as the interaction system between the human body and exoskeleton is uncertain and nonlinear. We present an approach for HMI force control via model reference adaptive impedance control(MRAIC) to solve this problem in case of index finger exoskeleton control. First, a dynamic HMI model, which is based on a position control inner loop, is formulated. Second, the theoretical MRAC framework is implemented in the control system. Then, the adaptive controllers are designed according to the Lyapunov stability theory. To verify the performance of the proposed method, we compare it with a proportional-integral-derivative(PID) method in the time domain with real experiments and in the frequency domain with simulations. The results illustrate the effectiveness and robustness of the proposed method in solving the nonlinear HMI force control problem in hand exoskeleton.
基金Part of this work was supported by the National Science Foundation of China under Grant No. 51521003.
文摘For human assistance device, the particular properties are usually focused on high precision, compliant interaction, large torque generation and compactness of the mechanical system. To realize the high performance of lower extremity augmentation device, in this paper, we introduce a novel control methodology for compact elastic module. Based on the previous work, the elastic module consists of two parts, i.e., the proximal interaction module and the distal control module. To improve the compactness of the exoskeleton, we only employ the distal control module to achieve both purposes of precision force control and human intention recognition with physical human-machine interaction. In addition, a novel control methodology, so-called high precision data-driven force control with disturbance observer is adopted in this paper. To assess our proposed control methodology, we compare our novel force control with several other control methodologies on the lower extremity augmentation single leg exoskeleton system. The experiment shows a satisfying result and promising application feasibility of the proposed control methodology.
文摘In this article I will address the issue of the meaning of Embodied Artificial Intelligence(EAI)as it is configured today.My starting point is the refined interactive perspective on the semantics of EAI,as was recently suggested by Froese and colleagues.This perspective rests on the assumption that the concept of human bodily subjectivity must be extended to include meaning-making processes,which are enabled by advanced AI systems that may be incorporated in the human biological body.After having clarified the technical background,I will introduce the genetic component of the phenomenological method as a suitable tool to face the aforementioned issue.Towards this end,I will place the genetic method in the context of the so-called New Human-Machine Interaction(New HMI).I will further outline a genetic phenomenology of visual embodiment,suggesting a futuristic application based on the thesis of the“technological supplementation of phenomenological methodology”through the synthetic method.The case at stake is that of patients with a severe clinical picture characterised by the loss of corneal function,who in the near future could be treated with synthetic corneal prosthetic implants produced by a 3D bio-printing process by using an advanced EAI technique.I will conclude this article with a brief review of the main problems that still remain open.
