检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Lian, Lihan Inyang-Udoh, Uduak Department of Robotics University of Michigan Ann ArborMI United States Department of Mechanical Engineering University of Michigan Ann ArborMI United States

In this paper, we propose a method to solve nonlinear optimal control problems (OCPs) with constrained control input in real-time using neural networks (NNs). We introduce what we have termed co-state Neural Network (CoNN) that learns the mapping from any given state value to its corresponding optimal co-state trajectory based on the Pontryagin’s Minimum (Maximum) Principle (PMP). In essence, the CoNN parameterizes the Two-Point Boundary Value Problem (TPBVP) that results from the PMP for various initial states. The CoNN is trained using data generated from numerical solutions of TPBVPs for unconstrained OCPs to learn the mapping from a state to its corresponding optimal co-state trajectory. For better generalizability, the CoNN is also trained to respect the first-order optimality conditions (system dynamics). The control input constraints are satisfied by solving a quadratic program (QP) given the predicted optimal co-states. We demonstrate the effectiveness of our CoNN-based controller in a feedback scheme for numerical examples with both unconstrained and constrained control input. We also verify that the controller can handle unknown disturbances effectively. Copyright © 2025, The Authors. All rights reserved.

关键词： Quadratic programming

来源：评论

学校读者我要写书评

暂无评论

Design and Evaluation of a Powered Hip Exoskeleton for Frontal and Sagittal Plane Assistance

Design and Evaluation of a Powered Hip Exoskeleton for Front...

引用

IEEE/RAS-EMBS International Conference on Biomedical robotics and Biomechatronics (BioRob)

作者： Dante Archangeli Brendon Ortolano Rosemarie Murray Lukas Gabert Tommaso Lenzi Department of Mechanical Engineering and the Robotics Center University of Utah Salt Lake City UT USA Rocky Mountain Center for Occupational and Environmental Health Department of Biomedical Engineering University of Utah

ISBN: (数字)9798350386523

ISBN: (纸本)9798350386530

Powered exoskeletons have the potential to improve ambulation for millions of individuals who struggle with mobility. Most powered exoskeletons aim to improve walking economy and increase speed by generating propulsive torque in the sagittal plane. However, individuals with mobility impairments typically have limited mediolateral balance, which requires assistance in the frontal plane. Here we present the design and preliminary evaluation of an autonomous powered hip exoskeleton that can generate torque in both the frontal and sagittal planes. The exoskeleton leverages a unique parallel actuator to produce up to 30 Nm of torque while achieving a compact and lightweight design that adds only 3 cm posterior and 8 cm lateral to the user and weighs only 5.3 kg. Preliminary validation tests with two healthy subjects show that the proposed powered hip exoskeleton can successfully assist gait by controlling the frontal plane torque to alter step width and providing sagittal plane torque to assist with hip flexion. A device with these characteristics has the potential to improve both gait economy and balance in clinical populations.

关键词： Legged locomotion Actuators Torque Exoskeletons Wearable robots Kinematics Biomechatronics Hip Testing

来源：评论

学校读者我要写书评

暂无评论

Interactive Learning of Physical Object Properties Through Robot Manipulation and Database of Object Measurements

Interactive Learning of Physical Object Properties Through R...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Andrej Kruzliak Jiri Hartvich Shubhan P. Patni Lukas Rustler Jan Kristof Behrens Fares J. Abu-Dakka Krystian Mikolajczyk Ville Kyrki Matej Hoffmann Department of Cybernetics Faculty of Electrical Engineering Czech Technical University in Prague Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Mechanical Engineering Department Faculty of Engineering New York University Abu Dhabi UAE Department of Electrical and Electronic Engineering Imperial College London London UK Department of Electrical Engineering and Automation Intelligent Robotics Group School of Electrical Engineering Aalto University

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

This work presents a framework for automatically extracting physical object properties, such as material composition, mass, volume, and stiffness, through robot manipulation and a database of object measurements. The framework involves exploratory action selection to maximize learning about objects on a table. A Bayesian network models conditional dependencies between object properties, incorporating prior probability distributions and uncertainty associated with measurement actions. The algorithm selects optimal exploratory actions based on expected information gain and updates object properties through Bayesian inference. Experimental evaluation demonstrates effective action selection compared to a baseline and correct termination of the experiments if there is nothing more to be learned. The algorithm proved to behave intelligently when presented with trick objects with material properties in conflict with their appearance. The robot pipeline integrates with a logging module and an online database of objects, containing over 24,000 measurements of 63 objects with different grippers. All code and data are publicly available, facilitating automatic digitization of objects and their physical properties through exploratory manipulations.

关键词： Uncertainty Databases Volume measurement Pipelines Measurement uncertainty Inference algorithms Probability distribution Bayes methods Intelligent robots Material properties

来源：评论

学校读者我要写书评

暂无评论

Optimal Reorientation of Planar Floating Snake Robots with Collision Avoidance

SSRN

引用

SSRN 2023年

作者： Itani, Omar Shammas, Elie Jaoude, Dany Abou Vision and Robotics Lab Mechanical Engineering Department American University of Beirut Beirut Lebanon Control and Optimization Lab Mechanical Engineering Department American University of Beirut Beirut Lebanon

In this paper, a motion planning algorithm for floating planar under-actuated hyper-redundant snake robots is proposed. The presented algorithm generates locally optimal shape trajectories, i.e., continuous trajectories in the base space of the robot. Such shape trajectories produce a desired rotation of the snake robot, i.e., change in the uncontrolled orientation fiber variable. The proposed method formulates the motion planning problem as an optimization problem where the objective function could be defined to minimize various metrics, such as energy-based cost functions. Additionally, the proposed motion planning algorithm uses a heuristic to generate shape trajectories that avoid self-intersections and obstacle collision. Hence, the motion planning method generates shape trajectories that locally minimize user-defined cost functions and eliminate self-intersections or obstacle collision. The proposed gait generation method is validated using numerical simulations of five-link and seven-link snake robots. © 2023, The Authors. All rights reserved.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Corpuscular Volume Estimation Using a Small Amount of Blood via Microscope Images 23

Corpuscular Volume Estimation Using a Small Amount of Blood ...

引用

23rd International Conference on Control, Automation and Systems, ICCAS 2023

作者： Ryu, Jegyeong Nam, Dahyun Son, Junghyun John Han, Amy Kyungwon Lee, Deukhee Center for Healthcare Robotics Korea Institute of Science and Technology Seoul Korea Republic of Yonsei University Division of Mechanical Engineering Seoul Korea Republic of Doping Control Center Korea Institute of Science and Technology Seoul Korea Republic of Seoul National University Department of Mechanical Engineering Seoul Korea Republic of Kist School University of Science and Technology Division of AI-Robotics Seoul Korea Republic of Yonsei-KIST Convergence Research Institute Yonsei University Seoul13391 Korea Republic of

ISBN: (纸本)9788993215274

Blood is an analysis serves as a valuable diagnostic tool that can easily and simply diagnose health, and in particular, red blood cells (RBC) or hematocrit (Hct) and mean corpuscular volume (MCV) can diagnose various diseases. Electrochemical methods have been proposed to find out RBC, Hct, and MCV, but it is difficult to use them for infants or the elderly because they require a large amount of blood. As an alternative, method like blood smear has been suggested to make a diagnosis with a small amount of blood, but it takes a long time to dry the sample. In this study, we present a methodology to make the simple and quick blood analysis. This method uses a microscope image of a small amount of blood, without drying the blood sample. From the image, in order to detect all the blood cells, we adopt a loop algorithm consist of concave point detection, ellipse fitting, and blob detection. To assess the validity and accuracy of the proposed method, an investigation is conducted to examine its correlation with the Sysmex XN-1000, a widely utilized medical reference standard;we show that the correlation coefficients are higher than 0.88, showing more correlation than the method in previous studies by comparing the estimation results. By developing this method, it will be possible to establish a simple quick blood analysis method using microscope images, decreasing a time consumed for the health checkup, saving more lives. © 2023 ICROS.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

A Probabilistic Formulation of LiDAR Mapping with Neural Radiance Fields

arXiv

引用

arXiv 2024年

作者： McDermott, Matthew Rife, Jason The Mechanical Engineering Ph.D. program Tufts University MedfordMA United States The Department of Mechanical Engineering Tufts University in Medford MA United States

In this paper we reexamine the process through which a Neural Radiance Field (NeRF) can be trained to produce novel LiDAR views of a scene. Unlike image applications where camera pixels integrate light over time, LiDAR pulses arrive at specific times. As such, multiple LiDAR returns are possible for any given detector and the classification of these returns is inherently probabilistic. Applying a traditional NeRF training routine can result in the network learning "phantom surfaces" in free space between conflicting range measurements, similar to how "floater" aberrations may be produced by an image model. We show that by formulating loss as an integral of probability (rather than as an integral of optical density) the network can learn multiple peaks for a given ray, allowing the sampling of first, nth, or strongest returns from a single output channel. Copyright © 2024, The Authors. All rights reserved.

关键词： Aberrations

来源：评论

学校读者我要写书评

暂无评论

On the dynamic behavior of an asymmetric self-regulated planetary-type vibration exciter 56

On the dynamic behavior of an asymmetric self-regulated plan...

引用

56th International Conference on Vibroengineering

作者： Korendiy, Vitaliy Kuzio, Igor Nikipchuk, Serhij Kotsiumbas, Oleh Dmyterko, Petro Department of Robotics and Integrated Mechanical Engineering Technologies Lviv Polytechnic National University Lviv Ukraine Department of Motor Vehicle Transport Lviv Polytechnic National University Lviv Ukraine

The problems of studying the dynamic behavior and improving the operational efficiency of various vibratory equipment are currently of significant interest. Special attention is paid to the possibilities of developing the enhanced designs of the planetary-type vibration exciters for the conveying, screening, and sieving machines. The novelty of the present research consists in providing the changeable inertial parameters of the improved planetary-type vibration exciter in order to adjust its operational conditions in accordance with the technological requirements. The mathematical model of the single-mass vibratory screening conveyor equipped with the proposed exciter is developed using the Lagrange-d’Alembert principle. The simulation of the system kinematic and dynamic characteristics under different operational conditions is carried out in the Mathematica software using the integrated Runge-Kutta methods. Copyright © 2022 Vitaliy Korendiy, et al.

关键词： Conveyors

来源：评论

学校读者我要写书评

暂无评论

Logarithmically Quantized Distributed Optimization over Dynamic Multi-Agent Networks

arXiv

引用

arXiv 2024年

作者： Doostmohammadian, Mohammadreza Pequito, Sérgio Mechatronics Department Faculty of Mechanical Engineering Semnan University Semnan Iran Department of Electrical and Computer Engineering Institute for Systems and Robotics Instituto Superior Técnico University of Lisbon Portugal

Distributed optimization finds many applications in machine learning, signal processing, and control systems. In these real-world applications, the constraints of communication networks, particularly limited bandwidth, necessitate implementing quantization techniques. In this paper, we propose distributed optimization dynamics over multi-agent networks subject to logarithmically quantized data transmission. Under this condition, data exchange benefits from representing smaller values with more bits and larger values with fewer bits. As compared to uniform quantization, this allows for higher precision in representing near-optimal values and more accuracy of the distributed optimization algorithm. The proposed optimization dynamics comprise a primary state variable converging to the optimizer and an auxiliary variable tracking the objective function's gradient. Our setting accommodates dynamic network topologies, resulting in a hybrid system requiring convergence analysis using matrix perturbation theory and eigenspectrumanalysis. © 2024, CC BY.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Study of MRI-compatible Notched Plastic Ultrasonic Stator with FEM Simulation and Holography Validation

arXiv

引用

arXiv 2024年

作者： Zhao, Zhanyue Tang, Haimi Carvalho, Paulo Furlong, Cosme Fischer, Gregory S. Department of Robotics Engineering Worcester Polytechnic Institute WorcesterMA01605 United States Department of Mechanical & Materials Engineering Worcester Polytechnic Institute WorcesterMA01605 United States

Intra-operative image guidance using magnetic resonance imaging (MRI) can significantly enhance the precision of surgical procedures, such as deep brain tumor ablation. However, the powerful magnetic fields and limited space within an MRI scanner require the use of robotic devices to aid surgeons. Piezoelectric motors are commonly utilized to drive these robots, with piezoelectric ultrasonic motors being particularly notable. These motors consist of a piezoelectric ring stator that is bonded to a rotor through frictional coupling. When the stator is excited at specific frequencies, it generates distinctive mode shapes with surface waves that exhibit both in-plane and out-of-plane displacement, leading to the rotation of the rotor. In this study, we continue our previous work and refine the motor design and performance, we combine finite element modeling (FEM) with stroboscopic and time-averaged digital holography to validate a further plastic-based ultrasonic motor with better rotary performance. © 2024, CC BY-NC-SA.

关键词： Piezoelectric motors

来源：评论

学校读者我要写书评

暂无评论

Humanoid Pianist: Dexterous Piano Playing with Synergy-based Hand Representation*

Humanoid Pianist: Dexterous Piano Playing with Synergy-based...

引用

IEEE Workshop on Advanced robotics and its Social Impacts, ARSO

作者： W. Jason Li Zhuo Li Junjia Liu Zhipeng Dong Zheng Sun Fei Chen Department of Mechanical and Automation Engineering T-Stone Robotics Institute The Chinese University of Hong Kong Hong Kong Faculty of Engineering The University of Hong Kong Hong Kong

ISBN: (数字)9798350344639

ISBN: (纸本)9798350344646

Playing the piano with dexterous hands has long presented unique challenges for robotics research due to the complex dexterity required. Traditional approaches utilizing individual control of each finger and joint in a robot hand make achieving fluent musical performances difficult and introduce significant control complexity due to the high degree-of-freedom nature of the dexterous hand workspace. This paper introduces a system that explores dexterous piano playing more naturally through a synergistic approach. The system employs a dual-armed robot with hands designed around two main synergies governing coordinated finger movements, which allows defining simple poses to represent both single-note and double-note playing. A mapping connects specific musical notes to the corresponding hand poses and precise timing required for a realistic piano rendition. A robot operating system is utilized to allow complex sequences and rhythms to be concisely specified. Results show that a synergistic approach is feasible and allows convenience with considerable accuracy and repeatability.

关键词： Measurement Codes Accuracy Robot kinematics Operating systems Humanoid robots Keyboards

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：