检索结果-内蒙古大学图书馆

A gait skeleton model extraction method based on the fusion between vision and tactility

VISUAL COMPUTER 2019年第12期35卷 1713-1723页

作者： Dai, Shijie Wang, Rui Zhang, Huibo Hebei Univ Technol Sch Mech Engn Tianjin Peoples R China Hebei Univ Technol Hebei Key Lab Robot Percept & Human Robot Interac Tianjin Peoples R China

In the traditional gait skeleton model, the fixed length proportions among different bones cause the loss of model personality, and the shoulder and hip points that are blocked by the body are difficult to be extracted. For those problems, a method based on the spatial and temporal fusion between vision and tactility is proposed, by which a equal proportion 3D gait skeleton model can be restructured in the camera coordinate system accurately through a single-frame image. In the geometric analysis process, some logical assumptions are proposed according to human anatomy and the laws of human movement, and an effective method is proposed for the extraction of thigh slope. The experimental result shows that the consistent equal proportion models, in which single bone length error is eventually controlled within +/- 5mm, can be extracted in different position under the premise of rapidity with the aid of this method. The extracted shoulder and hip points also meet the real human body skeleton structure, which lays the foundation for the integrity and rationality of the entire skeletal model.

关键词： 3D gait skeleton model Spatial and temporal fusion Shoulder and hip points Equal proportion restructure

来源：评论

学校读者我要写书评

暂无评论

Numerical simulation-based loaded inflation height modeling of nursing bed airbag

引用

MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING 2022年第11期60卷 3231-3242页

作者： Xiao, Yunxuan Liu, Teng Zhang, Zhong Zhang, Jianjun Guo, Shijie Hebei Univ Technol Sch Mech Engn State Key Lab Reliabil & Intelligence Elect Equip Hebei Key Lab Robot Percept & Human Robot Interac Tianjin 300130 Peoples R China

In previous studies, the numerical simulation models of industrial airbags were verified to have high accuracy regarding their actual dynamics. However, numerical methods were scarcely utilized to simulate and investigate the inflation height behaviors of nursing bed airbag. For this problem, this study constructs a numerical simulation model illustrating the association between the internal pressure and inflating height of nursing bed airbag, under various external loads. Firstly, based on an averaged pressure prerequisite, an airbag dynamic model is established by the control volume approach (the air inside the airbag follows the gas state equation of Poisson's law). Besides, the elastic mechanical behaviors of airbag film material are determined according to a material constitutive model built by the quasi-static uniaxial tensile test. The obtained data are used as the boundary conditions, for the numerical dynamics modeling of the nursing bed airbag. Verification experiments clarify that this numerical modeling is accurate for describing airbag inflation behaviors, and then can be effectively applied to the design and optimization phases of nursing bed airbags. Based on the simulation modeling above, the mathematical equation of controlling airbag inflating height by its internal pressure is obtained. It provides a vital basis for the differentiated and intelligent control of the airbag nursing bed.

关键词： Airbag nursing bed Numerical modeling Control volume method Airbag internal pressure Inflating height

来源：评论

学校读者我要写书评

暂无评论

Unconstrained Identification of the Positions of Chest and Abdomen and Detection of Respiratory Motions in Sleep by Using a Bed-Size Tactile Sensor Sheet

引用

IEEE SENSORS JOURNAL 2023年第14期23卷 16276-16286页

作者： Song, Yao Guo, Shijie Xiao, Sen Zhao, Xingli Hebei Univ Technol Hebei Key Lab Robot Percept & Human Robot Interact Tianjin 300130 Peoples R China Hebei Univ Technol State Key Lab Reliabil & Intelligence Elect Equipm Tianjin 300130 Peoples R China Hebei Univ Technol Hebei Key Lab Robot Sensing & Human Robot Interact Tianjin 300130 Peoples R China

Respiratory diseases can be effectively screened by monitoring chest and abdominal motions during respiration. Respiratory inductance plethysmography (RIP) is commonly used for this purpose in clinics. However, RIP has strong constraints on human body, limiting its daily use. Several unconstrained methods have been developed, but they cannot replace RIP due to their inability to accurately distinguish between chest and abdominal motions. The authors' group proposed an unconstrained method that has the potential to replace RIP by using a bed-size tactile sensor sheet. To increase its accuracy, the present work investigates the personalized identification method of optimal measurement regions of the chest and abdomen based on the body pressure distribution measured by the tactile sensor sheet. A new discriminative feature procedure and a corresponding mathematical model were proposed, and tests were conducted on 16 healthy subjects. The results demonstrate that the proposed method can enhance the measurement accuracy of the sensor sheet method, providing a convenient and practical way to early screening of respiratory diseases.

关键词： Empirical modal decomposition response surface model tactile sensor sheet thoracoabdominal movement unconstrained respiration monitoring

来源：评论

学校读者我要写书评

暂无评论

Inertial Measurement Unit-Based Optimization Control of a Soft Exosuit for Hip Extension and Flexion Assistance

引用

JOURNAL OF MECHANISMS AND robotICS-TRANSACTIONS OF THE ASME 2021年第2期13卷 021016页

作者： Chen, Qiang Guo, Shijie Sun, Lei Liu, Qiming Jin, Shanhai Hebei Univ Technol Sch Mech Engn State Key Lab Reliabil & Intelligence Elect Equip Hebei Key Lab Robot Sensing & Human Robot Interac Tianjin 300401 Peoples R China Yanbian Univ Sch Engn Yanji 133002 Peoples R China

The optimization of the assistive force of a soft exosuit is crucial to the assistive effect. In this paper, an inertial measurement unit (IMU)-based optimization controller was designed to provide effective hip extension and flexion assistance for a soft hip-assistive exosuit. The parameters of the assistive profiles that were defined by two functions were approximatively estimated based on an analysis of biological hip power, and then optimized in real time using the hip angles measured by two IMUs bound to the thighs of the wearer. The peak and offset timings were determined using the parameters of the previous gait, while the start and stop points were determined from those of the current gait. Confi rina lion experiment was conducted in which four subjects were tested to demonstrate the validity of the optimization by applying the optimized parameters to the soft exosuit developed by the authors' group. Two of the subjects completed the outdoor walking test at a self-determined pace while carrying a load of 15 kg. All the subjects conducted the walking test on a treadmill at a constant speed of 1.53 m/s with the same load. The results showed that the proposed optimization controller worked well without considering individual differences. In the outdoor walking test, the wearer's natural gait could be maintained by applying the optimized assistive forces. In the treadmill walking test, metabolic rate with assistance turned on was reduced by 8.53 +/- 2.65% (average +/- SEM) compared with the result of assistance turned off.

关键词： soft exosuit hip assistance assistive profiles optimization control metabolic rate robot design wearable robots

来源：评论

学校读者我要写书评

暂无评论

A recurrent reinforcement learning approach applicable to highly uncertain environments

引用

INTERNATIONAL JOURNAL OF ADVANCED robotIC SYSTEMS 2020年第2期17卷

作者： Li, Yang Guo, Shijie Zhu, Lishuang Mukai, Toshiharu Gan, Zhongxue Hebei Univ Technol State Key Lab Reliabil & Intelligence Elect Equip Hebei Key Lab Robot Sensing & Human Robot Interac 81 Rd Tianjin 300130 Peoples R China Meijyo Univ Fac Informat Sci Nagoya Aichi Japan Fudan Univ Inst AI & Robot Shanghai Peoples R China

Reinforcement learning has been a promising approach in control and robotics since data-driven learning leads to non-necessity of engineering knowledge. However, it usually requires many interactions with environments to train a controller. This is a practical limitation in some real environments, for example, robots where interactions with environments are restricted and time inefficient. Thus, learning is generally conducted with a simulation environment, and after the learning, migration is performed to apply the learned policy to the real environment, but the differences between the simulation environment and the real environment, for example, friction coefficients at joints, changing loads, may cause undesired results on the migration. To solve this problem, most learning approaches concentrate on retraining, system or parameter identification, as well as adaptive policy training. In this article, we propose an approach where an adaptive policy is learned by extracting more information from the data. An environmental encoder, which indirectly reflects the parameters of an environment, is trained by explicitly incorporating model uncertainties into long-term planning and policy learning. This approach can identify the environment differences when migrating the learned policy to a real environment, thus increase the adaptability of the policy. Moreover, its applicability to autonomous learning in control tasks is also verified.

关键词： Reinforcement learning migration adaptive policy environmental encoder

来源：评论

学校读者我要写书评

暂无评论

Periodic event-triggered sliding mode control for lower limb exoskeleton based on human-robot cooperation

引用

ISA TRANSACTIONS 2022年 123卷 87-97页

作者： Wang, Jie Liu, Jiahao Zhang, Gaowei Guo, Shijie Univ Sci & Technol Beijing Inst Artificial Intelligence Beijing 100083 Peoples R China Hebei Univ Technol Sch Artificial Intelligence Tianjin 300130 Peoples R China Hebei Key Lab Robot Sensing & Human Robot Interac Tianjin 300130 Peoples R China

This paper presents a periodic event-triggered sliding mode control (SMC) scheme based on humanrobot cooperation for lower limb exoskeletons. Firstly, a Genetic Algorithm-Back propagation (GA-BP) neural network is proposed to estimate the motion intention of the wearer through electromyography (EMG) signals. Secondly, the periodic event-triggered SMC strategy based on tanh function is designed to ensure the asymptotic convergence of the exoskeleton system and save communication resources, where the detailed expressions of sampling period and control gain are designed. Finally, comparative simulation and experimental analysis is presented to verify the effectiveness of the proposed control method. (C) 2021 Published by Elsevier Ltd on behalf of ISA.

关键词： Lower limb exoskeleton Genetic algorithm Sliding mode control Periodic event-triggered strategy Asymptotic convergence

来源：评论

学校读者我要写书评

暂无评论

Flexible, Freestanding, Ultrasensitive, and Iontronic Tactile sensing Textile

引用

ACS APPLIED ELECTRONIC MATERIALS 2021年第5期3卷 2195-2202页

作者： Wang, Peng Li, Guoxian Liu, Jun Hou, Zhanrui Meng, Chuizhou Guo, Shijie Hebei Univ Technol State Key Lab Reliabil & Intelligence Elect Equip Hebei Key Lab Smart Sensing & Human Robot Interac Tianjin 300401 Peoples R China Hebei Univ Technol Sch Mech Engn Tianjin 300401 Peoples R China

Recently, flexible textile-based sensors have drawn great interest due to their promising application in wearable electronics. However, most previous work has been done either by attaching conventional sensors to a textile-based substrate or by sewing fiber-like sensors into fabrics. The use of an additional substrate would interfere with detection performance and to some extent reduce user experience. Herein, we propose a flexible, freestanding tactile sensor by using the MXene/cotton composite thread as electronic electrodes and ionic gel (IG) as an iontronic electrolyte. Two or more such fiber electrodes are crisscross placed and bonded with a small amount of IG as glue at the intersection points to form the sensor unit or array without using any substrate. Due to its supercapacitive sensing mechanism upon optimization of electrode thickness and IG composition, it shows a high sensitivity of 9.62 kPa(-1) (0-40 kPa), ultralow detection limit of 0.884 Pa, and short response time of 24 ms. The sensor is capable of detecting micromotions like pulse beat at the wrist, water dripping, and sound wave through the air. In addition, a 6 x 6 sensor array is demonstrated to acquire 2D pressure mapping with recognition of different object shapes. Moreover, the sensor array can be conformally attached on a complex surface of 3D objects such as a table tennis ball to detect 3D positioned pressures. The proposed tactile-sensing textile in the true sense would provide a concept to develop advanced sensing devices with comfort for wearable systems.

关键词： tactile sensor supercapacitive iontronic textile and fabric flexible and wearable freestanding and self-supporting

来源：评论

学校读者我要写书评

暂无评论

Model-free prescribed performance fixed-time control for wearable exoskeletons

引用

APPLIED MATHEMATICAL MODELLING 2021年 90卷 61-77页

作者： Sun, Jianjun Wang, Jie Yang, Peng Guo, Shijie Hebei Univ Technol Sch Artificial Intelligence Tianjin 300130 Peoples R China Hebei Univ Technol Engn Ctr Intelligent Rehabil & Detect Technol Minist Educ Tianjin 300130 Peoples R China Hebei Key Lab Robot Sensing & Human Robot Interac Tianjin 300130 Peoples R China

In this paper, a model-free fixed-time control strategy with prescribed performance is pro-posed for the wearable exoskeleton angle tracking control. Firstly, an ultra-local model is employed to formulate the plant dynamic relation between control input and output. Then, an intelligent-proportional-derivative controller is designed based on the time delay estimation technique. To improve the tracking precision, a prescribed performance sliding mode controller is designed and a uniform robust exact disturbance observer is employed to compensate the controller. Besides, based on the universal barrier Lyapunov function, the stability is analyzed for the closed-loop system and the prescribed performance is proved. Finally, a 5 degree-of-freedom wearable exoskeleton virtual prototype is developed in SOLIDWORKS and transferred to MATlab/SimMechanics as the controlled object of visualization simulation, simulation results show the effectiveness of the proposed control strategy. (c) 2020 Elsevier Inc. All rights reserved.

关键词： Wearable exoskeleton Model-free control Fixed-time control Prescribed performance

来源：评论

学校读者我要写书评

暂无评论

Multivariable Finite-Time Control of 5 DOF Upper-Limb Exoskeleton Based on Linear Extended Observer

引用

IEEE ACCESS 2018年 6卷 43213-43221页

作者： Zhang, Gaowei Yang, Peng Wang, Jie Sun, Jianjun Hebei Univ Technol Sch Artificial Intelligence Tianjin 300130 Peoples R China Hebei Univ Technol Engn Res Ctr Intelligent Rehabil Minist Educ Tianjin 300130 Peoples R China Hebei Univ Technol Hebei Key Lab Robot Sensing & Human Robot Interac Tianjin 300130 Peoples R China

An output feedback finite-time control strategy for five degree of freedoms (DOF) upper-limb exoskeleton is investigated in this paper. First, a multivariable second-order sliding mode control is proposed to improve the response speed and stability of the exoskeleton system with parameter uncertainties and external disturbances. Furthermore, for the sake of high control precision with limited information, a finite-time linear extended state observer is constructed to estimate both the unmeasured states and the lumped perturbations. Finally, by utilizing the 5-DOF upper-limb model, simulation results are presented to demonstrate the effectiveness of the control strategy.

关键词： Upper-limb exoskeleton finite-time control sliding mode control extended state observer

来源：评论

学校读者我要写书评

暂无评论

A Tactile-based Brain Computer Interface P300 Paradigm Using Vibration Frequency and Spatial Location

引用

JOURNAL OF MEDICAL AND BIOLOGICAL ENGINEERING 2020年第6期40卷 773-782页

作者： Han, Xiangke Niu, Jianye Guo, Shijie Hebei Univ Technol State Key Lab Reliabil & Intelligence Elect Equip Tianjin Peoples R China Hebei Univ Technol Hebei Key Lab Robot Percept & Human Robot Interac Tianjin Peoples R China Anyang Inst Technol Sch Mech Engn Anyang Peoples R China

Purpose Visual based brain-computer interface (BCI) has been widely investigated for the severely disabled patients. However, this modality is not applicable to the persons who have lost their visual function. This study aims to develop an alternative BCI using tactile stimuli only. Methods An event-related potential (ERP) based BCI applying vibrotactile stimuli was proposed. It featured a combination of frequency and spatial information as a cue for binary choices. Two identical mechanical vibrotactile tactors were tied to each index finger of the two hands of a subject, to provide vibrotactile stimuli at various frequencies and constitute a three-stimulus oddball paradigm with one attended stimulus, one ignored stimulus and one disturbance stimulus. Ten healthy subjects participated in the experiments, and the classification of P300 signals was conducted by a stepwise linear discriminate analysis algorithm. Results Significant P300 components were evoked at approximately 360 ms after the onset of the target stimuli for each subject, and an average classification accuracy of 79% was achieved. Conclusions This work demonstrates the feasibility of employing vibrotactile stimuli to build an ERP based BCI. The patients without a functional visual system could benefit from the presented paradigm.

关键词： Event-related potential Tactile based BCI Spatial location Vibration frequency

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：