检索结果-内蒙古大学图书馆

human-in-the-loop control of Robotic Leg Prostheses With Sensory Feedback

IEEE-ASME TRANSACTIONS ON MECHATRONICS 2024年第3期29卷 1844-1855页

作者： Pi, Ming Li, Zhijun Li, Qinjian Kang, Yu Kan, Zhen Song, Rong Southwest Univ Sci & Technol Sch Informat Engn Mianyang 621010 Peoples R China Hefei Comprehens Natl Sci Ctr Inst Artificial Intelligence Hefei 230031 Peoples R China Tongji Univ Sch Mech Engn Shanghai 200092 Peoples R China Univ Sci & Technol China Dept Automat Hefei 230027 Peoples R China Univ Sci & Technol China Inst Adv Technol Dept Automat Hefei 230027 Peoples R China Sun Yat Sen Univ Sch Engn Guangzhou 510000 Peoples R China

human during walking can sense the joint angle and the contact force between the leg and the ground and uses such information as the feedback to regulate walking performance. To complete this motor control for the amputee with the leg prosthesis, human-in-the-loop control was proposed. This control method involves the restoration of the sensory feedback and the unified gait generator. By restoring the sensory feedback of the prosthesis with noninvasive Functional Electrical Stimulation (nFES), the subject can sense touch-down moment, leave-off moment, and height of small obstacles on the ground. Then, the unified gait generator converts the subject's intent into the prosthesis' motor command according to the damping and Spring-Loaded Inverted Pendulum (D-SLIP) model. When walking is slow, the prosthesis is stiff. When walking is fast, the prosthesis is compliant. Three experiments were conducted to prove the improvement of walking performance, such as the precision to sense the height of small obstacles, and the amount of increment for walking speed and frequency on level ground, S curve, or stairs. These results showed that the proposed control method can improve the motion capability of subjects greatly.

关键词： Legged locomotion Robot sensing systems Prosthetics Electrodes Impedance Knee human in the loop human-in-the-loop control robotic leg prostheses sensory feedback

来源：评论

学校读者我要写书评

暂无评论

Fast human-in-the-loop control for HVAC Systems via Meta-Learning and Model-Based Offline Reinforcement Learning

IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING

引用

IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING 2023年第3期8卷 504-521页

作者： Chen, Liangliang Meng, Fei Zhang, Ying Georgia Inst Technol Sch Elect & Comp Engn Atlanta GA 30332 USA Chinese Univ Hong Kong Dept Elect Engn Hong Kong Peoples R China

Reinforcement learning (RL) methods can be used to develop a controller for the heating, ventilation, and air conditioning (HVAC) systems that both saves energy and ensures high occupants' thermal comfort levels. However, the existing works typically require on-policy data to train an RL agent, and the occupants' personalized thermal preferences are not considered, which is limited in the real-world scenarios. This paper designs a high-performance model-based offline RL algorithm for personalized HVAC systems. The proposed algorithm can quickly adapt to different occupants' thermal preferences with a few thermal feedbacks, guaranteeing the high occupants' personalized thermal comfort levels efficiently. First, we use a meta-supervised learning algorithm to train an occupant's thermal preference model. Then, we train an ensemble neural network to predict the thermal states of the considered zone. In addition, the obtained ensemble networks can indicate the regions in the state and action spaces covered by the offline dataset. With the personalized thermal preference model updated via meta-testing, model-based RL is used to derive the optimal HVAC controller. Since the proposed algorithm only requires offline datasets and a few online thermal feedbacks for training, it contributes to a more practical deployment of the RL algorithm to HVAC systems. We use the ASHRAE database II to verify the effectiveness and advantage of the meta-learning algorithm for modeling different occupants' thermal preferences. Numerical simulations on the EnergyPlus environment demonstrate that the proposed algorithm can guarantee personalized thermal preferences with a slight increase of power consumption of 1.91% compared with the model-based RL algorithm with on-policy data aggregation.

关键词： HVAC Data models Computational modeling Prediction algorithms Atmospheric modeling Optimization Buildings HVAC systems model-based offline rein- forcement learning meta-learning human-in-the-loop control

来源：评论

学校读者我要写书评

暂无评论

human-in-the-loop control Strategy of Unilateral Exoskeleton Robots for Gait Rehabilitation

引用

IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS 2021年第1期13卷 57-66页

作者： Wei, Dong Li, Zhijun Wei, Qiang Su, Hang Song, Bo He, Wei Li, Jianqiang Univ Sci & Technol China Dept Automat Hefei 230026 Peoples R China Politecn Milan Dipartimento Elettron Informaz & Bioingn I-20133 Milan Italy Chinese Acad Sci Lab Robot Sensor Robot & Human Machine Interact Inst Intelligent Machines Hefei 230031 Peoples R China Univ Sci & Technol Beijing Sch Automat & Elect Engn Inst Artificial Intelligence Beijing 100083 Peoples R China Univ Sci & Technol Beijing Key Lab Knowledge Automat Ind Proc Minist Educ Beijing 100083 Peoples R China Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen 518060 Guangdong Peoples R China

In this article, a human-in-the-loop control methodology is proposed for the gait rehabilitation of patients with hemiplegia. It utilizes a unilateral exoskeleton system consisting of a unilateral lower limb exoskeleton and a real-time robot follower, such that the affected legs can be coordinated with the healthy legs with the assistance of the exoskeleton robot. In order to achieve immersive training during the physical therapy, the human-in-the-loop controller is developed. Furthermore, a region-based barrier Lyapunov function (BLF) is designed to separate the task workspace of the exoskeleton into a human region and a robot region, enabling the human leg to follow the desired motion trajectory in a compliant region, and the motion control of the exoskeleton is determined by humans;while in the robot region, the exoskeleton dominates the movement of human subjects. In order to make the motion control transit smoothly between the robot region and the human region, an adaptive controller is exploited to counteract the system's nonlinear uncertainties. Both the theoretical analysis and experimental results support the effectiveness and practicability on hemiplegic patients of our control strategy.

关键词： Exoskeletons Legged locomotion Robot kinematics Training Real-time systems Cameras Gait rehabilitation human-in-the-loop control unilateral exoskeleton

来源：评论

学校读者我要写书评

暂无评论

human-in-the-loop control Using Euler Angles

引用

JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS 2020年第2期97卷 271-285页

作者： Perrusquia, Adolfo Yu, Wen IPN CINVESTAV Dept Control Automat Ave IPN 2508 Mexico City 07360 DF Mexico

In this paper, we proposed a human-in-the-loop (HITL) control based on the Euler angles solution of the robot end-effector. When humans are in the control loop, we can linearize the Euler angles such that they have direct relation with the joint angles and they are also decoupled. So the Jacobian matrix and the inverse kinematics are not needed. We simplify the admittance control using the Euler angles. The stability of those controllers is proven. The experiments, with a two-degree-of-freedom (2-DOF) pan and tilt robot and a four-degree-of-freedom exoskeleton, show that our Euler angles based controllers are simple and effective.

关键词： human-in-the-loop control Euler angles Admittance control

来源：评论

学校读者我要写书评

暂无评论

An embodiment paradigm in evaluation of human-in-the-loop control

An embodiment paradigm in evaluation of human-in-the-loop co...

引用

2nd International-Federation-of-Automatic-control (IFAC) Conference on Cyber-Physical and human-Systems (CPHS)

作者： Froehner, Jakob Beckerle, Philipp Endo, Satoshi Hirche, Sandra Tech Univ Munich Chair Informat Oriented Control D-80333 Munich Germany Tech Univ Dortmund Robot Res Inst Elast Lightweight Robot Grp D-44221 Dortmund Germany Tech Univ Darmstadt Inst Mechatron Syst D-64287 Darmstadt Germany

This study introduces a novel approach for evaluating the quality of human-in-the-loop control using the psychological construct of embodiment in a haptic human-machine interaction task. Despite the fact that various forms of assistive control have been introduced, these methods mainly design semi-autonomous control to improve task-specific interaction performance. From a user perspective, however, the introduction of semi-autonomous control reduces controllability of the system, which could lead to negative user experience. Psychological research suggests sensory-motor factors dynamically modulate cognition of an external entity belonging to one's own body, i.e., embodiment. In our paradigm, we apply methods for evaluating embodiment in a virtual reality (VR) environment where the human users perform a reaching task with semi-autonomous haptic assistance to measure the degree to which the embodiment is effected by the quality of semi-autonomy. Our results with 8 participants show good persistence of subjective embodiment and subcomponents of presence within VR environment when a predictable assistive control is introduced while unpredictable assistance hindered the subjective embodiment. Results indicate embodiment can be exploited as a quantitative evaluation method of semi-autonomous controllers from a user-centric perspective. (C) 2019, IFAC (International Federation of Automatic control) Hosting by Elsevier Ltd. All rights reserved.

关键词： Embodiment Shared-control human-in-the-loop control

来源：评论

学校读者我要写书评

暂无评论

Real-time human-in-the-loop Remote control for a Life-size Traffic Police Robot with Multiple Augmented Reality Aided Display Terminals 2

Real-time Human-in-the-loop Remote Control for a Life-size T...

引用

2nd International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Gong, Liang Gong, Changyang Ma, Zhao Zhao, Lujie Wang, Zhenyu Li, Xudong Jing, Xiaolong Yang, Haozhe Liu, Chengliang Shanghai Jiao Tong Univ Sch Mech Engn Shanghai 200240 Peoples R China

ISBN: (纸本)9781538632604

Policing of road traffic is listed in the most hazardous tasks since many traffic police personnel injured in a series of accidents at intersections. A life-size traffic cop robot called "IWI" is invented as an alternative to human traffic police in the street for directing traffic on point duty, and this paper proposes a human-robot cooperation scheme with wearable augmented glasses as an HMI to obtain a more immersing teleoperation experience with the aid of wearable augmented reality glasses. First, a humanoid robot is tailored for mobile surveillance with raspberry pi camera based eyes and omnidirectional Mecanum wheels. Second, the real-time video stream acquired by the on-site robot is distributed to multiple terminals, such as the central sever, the wearable augmented reality glasses and the mobile control tablet. Third, with a depth of focus estimation the augmented indications are displayed to aid to understand the remote scenario. Finally, the human policing results, such as STOP, PULL OVER, TURN-LEFT, are compiled and programmed as simplified patterns to control the robot body/hand pantomime. Experimental results show that the proposed methodology and control scheme is feasible in real-time application with high real-time performance of less than 0.5s latency, and open possibilities of easing the traffic jam via simultaneously scheduling multiple traffic cop robots.

关键词： Traffic police robot augmented reality glasses wearable robotics human-in-the-loop control life-size humanoid robot human-robot cooperation

来源：评论

学校读者我要写书评

暂无评论

human-in-the-loop control of an irrigation canal using time instant optimization model predictive control

Human-in-the-loop control of an irrigation canal using time ...

引用

European control Conference (ECC)

作者： Sadowska, A. van Overloop, P. -J. Maestre, J. M. De Schutter, B. Delft Univ Technol Delft Ctr Syst & Control Delft Netherlands Delft Univ Technol Water Resources Management Sect Delft Netherlands Univ Seville Dept Syst & Automat Seville Spain

ISBN: (纸本)9783952426937

In the paper we discuss the recently introduced Mobile Model Predictive control (Mobile MPC) approach for an irrigation canal. Mobile MPC is a configuration of MPC that explicitly incorporates the role of the human operator traveling between the gates as ordered by a remote centralized controller. The operator provides the controller with up-to-date measurements from the locations visited and acts as the actuator as required by the remote controller. Mobile MPC provides a solution in between fully manual and fully automatic canal operation, as the first one may give poor performance and the second one might be impracticable in some situations, where it is not possible to rely on the equipment installed in the field. In the current paper we improve the performance of the original Mobile MPC approach by allowing the controller to decide the exact time instants when the operator should arrive at a specific gate and change the gate's settings as well as we include a penalty in the objective function for the controller to minimize the workload of the human operator. We show that the new approach yields enhanced performance in comparison to the previous method, and we demonstrate the benefits of the new method as opposed to the previous one in a case study.

关键词： canals irrigation mobile communication optimisation predictive control telecontrol human operator traveling human-in-the-loop control irrigation canal mobile MPC mobile model predictive control remote centralized controller time instant optimization model predictive control up-to-date measurements Actuators Irrigation Logic gates Mobile communication Predictive control

来源：评论

学校读者我要写书评

暂无评论

human-in-the-loop Coordinated Path Following of Marine Vehicles Based on Continuous Twisting control

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2025年第1期21卷 465-474页

作者： Lv, Mingao Gu, Nan Wang, Dan Han, Bing Peng, Zhouhua Dalian Maritime Univ Sch Marine Elect Engn Dalian 116026 Peoples R China Dalian Maritime Univ Sch Marine Elect Engn Dalian Peoples R China State Key Lab Maritime Technol & Safety Dalian 116026 Peoples R China Dalian Key Lab Swarm Control & Elect Technol Intel Dalian 116026 Peoples R China Minjiang Univ Coll Phys & Elect Informat Engn Fuzhou Fujian Peoples R China Shanghai Ship & Shipping Res Inst Co Ltd Shanghai 200135 Peoples R China

This article addresses the coordinated path-following (CPF) control under human supervision for marine vehicles (MVs) with unknown disturbances. A human-in-the-loop coordinated path-following (HCPF) control architecture is proposed based on the robust exact differentiator (RED) observer and the output feedback continuous twisting control (OFCTC) method. Specifically, a human manipulation is introduced into a virtual leader to regulate its path update speed in response to sudden circumstances for the follower MVs. All follower MVs synchronize indirectly with the human-in-the-loop virtual leader over a communication graph. Then, the path-following control problem is transformed into the controls of a second-order along-track error dynamic and a third-order cross-track error dynamic. By using the path-following errors only, the RED observers are developed to recover the unknown states of the error dynamics. Finally, the OFCTC laws are designed to achieve the individual path following in finite time regardless of the lumped disturbances. The stability of the closed-loop system is analyzed by employing the cascade theory. A salient feature of the proposed HCPF control architecture is that the CPF for MVs can be implemented under the supervision and intervention of human. Simulation results are given to illustrate the effectiveness of the proposed HCPF control method.

关键词： human in the loop Vehicle dynamics Marine vehicles Observers Informatics Graph theory Velocity measurement Continuous twisting control coordinated path following (CPF) human-in-the-loop control marine vehicles (MVs) robust exact differentiator (RED) observer

来源：评论

学校读者我要写书评

暂无评论

human operator decision support for highly transient industrial processes: a reinforcement learning approach

引用

JOURNAL OF INTELLIGENT MANUFACTURING 2025年第2期36卷 1159-1174页

作者： Ruan, Jianqi Nooning, Bob Parkes, Ivan Blejde, Wal Chiu, George Jain, Neera Purdue Univ Sch Mech Engn 585 Purdue Mall W Lafayette IN 47907 USA Castrip LLC 1915 Rexford Rd Charlotte NC 28211 USA

Most industrial processes are not fully-automated. Although fast and low-level control can be handled by controllers, initializing and adjusting the reference, or setpoint, values, are commonly tasks assigned to human operators. A major challenge is the control policy variation among operators. In turn this can result in inconsistencies in the final product. In order to guide operators to pursue better and more consistent performance, researchers explore the optimal control policy through different approaches. Although in different applications, researchers use different approaches, an accurate process model is still crucial to the approaches. However, for a highly transient process (e.g., the startup of a manufacturing process), modeling can be challenging and inaccurate, and approaches highly relying on a process model may not work well. In this paper, we apply the idea of offline reinforcement learning (RL), which requires the RL agent to learn control policies from a previously collected dataset. More specifically, a modified advantage weighted regression is used to guide the agent to take the more advantageous actions. In addition, we train and verify the agent by using casting data of multiple human operators from an industrial twin-roll steel strip casting process.

关键词： Reinforcement learning Offline learning human-in-the-loop control Decision aid system

来源：评论

学校读者我要写书评

暂无评论

Adaptive Cost Function-Based Shared Driving control for Cooperative Lane-Keeping Systems With User-Test Experiments

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2024年第1期9卷 304-314页

作者： Oudainia, Mohamed Radjeb Sentouh, Chouki Nguyen, Anh-Tu Popieul, Jean-Christophe Univ Polytech Hauts de France CNRS LAMIH UMR 8201 F-59313 Valenciennes France INSA Hauts de France F-59313 Valenciennes France

This article presents a new shared control method with a dynamic driver-automation conflict management for cooperative lane keeping systems (LKS) of automated vehicles. Based on a human-centered control approach, the proposed shared control design takes into account the driver's activity and availability, as well as the surrounding risk to dynamically adapt the driving assistance level via an adaptive cost function. To this end, we propose a method to characterize in real-time the driver's activity, which allows for an appropriate assistance level according to the driving conditions. Linear parameter-varying (LPV) control technique is leveraged to deal with the time-varying nature of the vehicle speed and the level of assistance. The uncertainties of the lateral tires forces are taken into account in the control design via a norm-bounded representation. Using Lyapunov stability theory, the control design conditions are derived in terms of linear matrix inequality (LMI) constraints, which can be effectively solved by semidefinite programming techniques. User-test experiments are performed with the SHERPA dynamic car simulator to demonstrate the effectiveness of the proposed shared controlmethod from both objective and subjective viewpoints.

关键词： Vehicles Vehicle dynamics Cost function control design Automation Torque Adaptation models Lane-keeping systems cooperative control human-in-the-loop control human-machine interaction shared control automated driving

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：