检索结果-内蒙古大学图书馆

Object Affordance Driven Inverse Reinforcement Learning Through Conceptual Abstraction and Advice

Paladyn 2018年第1期9卷 277-294页

作者： Bhattacharyya, Rupam Hazarika, Shyamanta M. Department of CSE Indian Institute of Information Technology Bhagalpur Bihar India Biomimetic and Cognitive Robotics Lab Department of Mechanical Engineering Indian Institute of Technology Guwahati Assam India

Within human Intent Recognition (IR), a popular approach to learning from demonstration is Inverse Reinforcement Learning (IRL). IRL extracts an unknown reward function from samples of observed behaviour. Traditional IRL systems require large datasets to recover the underlying reward function. Object affordances have been used for IR. Existing literature on recognizing intents through object affordances fall short of utilizing its true potential. In this paper, we seek to develop an IRL system which drives human intent recognition along with the capability to handle high dimensional demonstrations exploiting the capability of object affordances. An architecture for recognizing human intent is presented which consists of an extended Maximum Likelihood Inverse Reinforcement Learning agent. Inclusion of Symbolic Conceptual Abstraction Engine (SCAE) along with an advisor allows the agent to work on Conceptually Abstracted Markov Decision Process. The agent recovers object affordance based reward function from high dimensional demonstrations. This function drives a Human Intent Recognizer through identification of probable intents. Performance of the resulting system on the standard CAD-120 dataset shows encouraging result. © by Rupam Bhattacharyya, published by De Gruyter 2018.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

Development of a low cost active upper-limb prosthesis using design thinking methodology for improvement user suitability

Journal of Orthopaedic Reports

引用

Journal of Orthopaedic Reports 2024年

作者： Francys Marcel Rodriguez Jimenez Bruna Aparecida Rezende Mariana Ribeiro Volpini Luciano Machado Gomes Vieira Paulo Eustáquio de Faria Juan Carlos Campos Rubio Universidade Federal de Minas Gerais Graduate Program in Mechanical Engineering Department of Mechanical Engineering Universidade Federal de Minas Gerais. Antônio Carlos Avenue 6627 Pampulha - 31270-901 - Belo Horizonte MG – Brazil Federal Institute of Education Science and Technology of Minas Gerais Campus Bambui Faz. Varginha - Rodovia Bambuí/Medeiros - Km 05 – 38900-000 - Bambuí – MG - Brazil Faculdade Ciências Médicas de Minas Gerais Physiotherapy department Ezequiel Dias Avenue 275 Centro – 30130-110 – Belo Horizonte MG – Brazil Universidade Federal de Minas Gerais Department of Production Engineering Universidade Federal de Minas Gerais. Antônio Carlos Avenue 6627 Pampulha - 31270-901 - Belo Horizonte MG – Brazil

Introduction The absence of an upper limb, either due to amputation or to congenital malformation, can impair the quality of life, interfering with their ability to perform daily activities and working routine, generating physical and psychological impacts. Thus, the rehabilitation process improves the person's functionality, developing skills, and promoting independence and social participation which are the priority issue. In this sense, the prosthesis plays an important role, as it is a therapeutic technological resource capable of expanding the functional capabilities of the person amputated. Objectives Currently, the orthopedic workshops certificated by the Brazilian Unified Health System (BUHS) are responsible for providing the demands of orthoses and prostheses to insured patients. Normally, these equipment are manufactured by a handmade process, which can initially cause discomfort to the patient that induces adjustment and consequently to substantial increases in the production time. In addition, BUHS provides to the insured patients only standard basic models type prostheses, therefore, it is not offered the chance to make use of the benefits of a robotic prosthesis. Thus, implementing other manufacturing methodologies capable of providing a faster and better adaptable prosthesis to the patient is necessary because this behavior can decrease the discomfort and enable other prosthetic options. In this sense, the development of personalized products using 3D scanning and rapid prototyping techniques appears as essential alternatives. In this manner, a novel model of the prosthesis with automatic movement which has the potential to be included as a viable alternative to be provided by the BUHS is socially important. Methods This work aims to develop a robotic prosthesis of the upper limb for individuals with trans-radial amputation, by means to apply the project methodology called "Design Thinking". Likewise, the features as low cost and shorter production ti

关键词： Design Thinking Prosthesis Transradial amputation Additive manufacturing

来源：评论

学校读者我要写书评

暂无评论

Control of brain network dynamics across diverse scales of space and time

引用

Physical Review E 2020年第6期101卷 062301-062301页

作者： Evelyn Tang Harang Ju Graham L. Baum David R. Roalf Theodore D. Satterthwaite Fabio Pasqualetti Danielle S. Bassett Department of Bioengineering School of Engineering & Applied Science University of Pennsylvania Pennsylvania 19104 USA Max Planck Institute for Dynamics and Self-Organization Göttingen 37079 Germany Neuroscience Graduate Program Perelman School of Medicine University of Pennsylvania Pennsylvania 19104 USA Department of Psychiatry Perelman School of Medicine University of Pennsylvania Pennsylvania 19104 USA Department of Mechanical Engineering University of California Riverside Riverside California 92521 USA Department of Physics & Astronomy College of Arts & Sciences University of Pennsylvania Pennsylvania 19104 USA Department of Electrical & Systems Engineering School of Engineering & Applied Science University of Pennsylvania Pennsylvania 19104 USA Department of Neurology Perelman School of Medicine University of Pennsylvania Pennsylvania 19104 USA Santa Fe Institute Santa Fe New Mexico 87501 USA

The human brain is composed of distinct regions that are each associated with particular functions and distinct propensities for the control of neural dynamics. However, the relation between these functions and control profiles is poorly understood, as is the variation in this relation across diverse scales of space and time. Here we probe the relation between control and dynamics in brain networks constructed from diffusion tensor imaging data in a large community sample of young adults. Specifically, we probe the control properties of each brain region and investigate their relationship with dynamics across various spatial scales using the Laplacian eigenspectrum. In addition, through analysis of regional modal controllability and partitioning of modes, we determine whether the associated dynamics are fast or slow, as well as whether they are alternating or monotone. We find that brain regions that facilitate the control of energetically easy transitions are associated with activity on short length scales and slow timescales. Conversely, brain regions that facilitate control of difficult transitions are associated with activity on long length scales and fast timescales. Built on linear dynamical models, our results offer parsimonious explanations for the activity propagation and network control profiles supported by regions of differing neuroanatomical structure.

关键词： Network diffusion Synchronization Brain network Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Learning stabilizable nonlinear dynamics with contraction-based regularization

arXiv

引用

arXiv 2019年

作者： Singh, Sumeet Richards, Spencer M. Sindhwani, Vikas Slotine, Jean-Jacques E. Pavone, Marco Department of Aeronautics and Astronautics Stanford University Google Brain Robotics New York Department of Mechanical Engineering Massachusetts Institute of Technology

We propose a novel framework for learning stabilizable nonlinear dynamical systems for continuous control tasks in robotics. The key contribution is a control-theoretic regularizer for dynamics fitting rooted in the notion of stabilizability, a constraint which guarantees the existence of robust tracking controllers for arbitrary open-loop trajectories generated with the learned system. Leveraging tools from contraction theory and statistical learning in Reproducing Kernel Hilbert Spaces, we formulate stabilizable dynamics learning as a functional optimization with convex objective and bi-convex functional constraints. Under a mild structural assumption and relaxation of the functional constraints to sampling-based constraints, we derive the optimal solution with a modified Representer theorem. Finally, we utilize random matrix feature approximations to reduce the dimensionality of the search parameters and formulate an iterative convex optimization algorithm that jointly fits the dynamics functions and searches for a certificate of stabilizability. We validate the proposed algorithm in simulation for a planar quadrotor, and on a quadrotor hardware testbed emulating planar dynamics. We verify, both in simulation and on hardware, significantly improved trajectory generation and tracking performance with the control-theoretic regularized model over models learned using traditional regression techniques, especially when learning from small supervised datasets. The results support the conjecture that the use of stabilizability constraints as a form of regularization can help prune the hypothesis space in a manner that is tailored to the downstream task of trajectory generation and feedback control, resulting in models that are not only dramatically better conditioned, but also data efficient. Copyright © 2019, The Authors. All rights reserved.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

Manufacturing and Society – A Freshman Introduction to engineering Course with Manufacturing and Social Science Partnership

引用

Procedia Manufacturing 2020年 48卷 1126-1135页

作者： Albert Shih Lei Chen Noah Webster Alan Hogg Department of Mechanical Engineering University of Michigan 2350 Hayward St. Ann Arbor MI 48109 USA Institute of Social Research University of Michigan 426 Thompson St. Ann Arbor MI 48106 USA Program in Technical Communication College of Engineering University of Michigan 2609 Draper Dr. Ann Arbor MI 48109 USA

The curriculum and pedagogy of a freshman introduction to engineering course on manufacturing and society are presented. This course is designed to use the quadcopter drone as an example to teach knowledge in manufacturing processes and systems, illustrate potential impacts of manufacturing to society, and stimulate learning in innovation, teamwork, and communication in a real-world engineering environment. It is also designed to teach students how to best communicate their findings and conclusions. This course is built on two team-based projects. Students practiced and timed the assembly of a state-of-the-art drone, the DJI Spark, and created a mid-term project presentation and report of their plan to setup an assembly plant in Michigan for this drone. Students learned the assembly line design, cycle time balancing, time study, automation, robotics, ergonomics, process capability index, and plant layout. The final project is the design and manufacture of an attachment to a hobby drone, DJI F330, for a mission that will benefit society. Students learned the social-aspects of manufacturing, computer-aided design, additive manufacturing, fabrication skills, and manufacturing processes. Each team identified a societal need, designed an attachment to the DJI F330 drone, reviewed the design with experienced engineers, manufactured components, assembled the attachment, and evaluated them in drone test flights. This course was implemented in close collaboration with a local community college to share the lecture and lab materials as well as pedagogy in manufacturing to benefit the same cohort of high school graduates. This approach of integrated social science, manufacturing, and technical communication to teach manufacturing using drones and connect manufacturing and society were demonstrated to be effective for an introductory freshman engineering course. Freshman engineering students often experience tremendous changes and pressure in their first semester. The lecture,

关键词： Manufacturing education social science innovation based pedagogy

来源：评论

学校读者我要写书评

暂无评论

Development of microcontroller trainer kit as a teaching aid for electronics course

引用

AIP Conference Proceedings 2024年第1期3115卷

作者： Adhan Efendi Armansyah Maria Mahardini Sakanti Ary Surjanto C. Bambang Dwi Kuncoro Graduate Institute of Precision Manufacturing National Chin-Yi University of Technology No. 57 Section 2 Zhongshan Rd Taiping District Taichung City Taiwan Mechanical Engineering Study Program Faculty of Engineering Universitas Pembangunan Nasional Veteran Jakarta Jalan RS. Fatmawati Raya Pondok Labu Cilandak South Jakarta City Jakarta 12450 Indonesia Department of Refrigeration and Air Conditioning Engineering Politeknik Negeri Bandung Polban Jl. Gegerkalong Hilir Ciwaruga Kec. Parongpong Kabupaten Bandung Barat Jawa Barat 4001 Indonesia Department of Refrigeration Air Conditioning and Energy Engineering National Chin-Yi University of Technology No. 57 Section 2 Zhongshan Rd Taiping District Taichung City Taiwan

This research aims to develop educational and learning support facilities by developing teaching aids for instructors and practical training to enhance the capabilities of laboratories. The developed exercise materials will be used in the electronics laboratory activities to equip vocational students (Diploma 3 and Diploma 4) with practical skills and knowledge of applied electronics. Microcontroller-based teaching materials designed systematically and interactively developed to support the applied electronic system. As a result, the students learn quickly while installing and programming applied electronic hardware applications. There are exercise manuals for up to seven exercise competencies of electronics laboratory activities. Based on the evaluation results from the expert group member and the laboratory chairman, the developed teaching aids are convenient for electronics laboratory classes. Based on student responses using the developed teaching aids, 43% of students mentioned that the microcontroller teaching laboratory kit and hands-on instructions were interactive, easy to use, understandable, and practical, along with the required electronic instructions. They indicated that the material was presented continuously. Meanwhile, 64% of students report that the microcontroller teaching laboratory kit and hands-on instructions motivate, contribute to comprehension, provide convenience, and increase student attention in electronics laboratory activities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on dual-mode switching fuzzy PID servo algorithm based on micro-linear motor

Research on dual-mode switching fuzzy PID servo algorithm ba...

引用

7th International Symposium on Test Automation and Instrumentation, ISTAI 2018

作者： Sun, Hongchang Ma, Ruijun Deng, Sangpeng Li, Lina Zhang, Jian Qi, Yuming Feng, Yu Zhang, Tianjiang Institute of Robotics and Intelligent Equipment Tianjin University of Technology and Education Tianjin China Department of Mechanical Engineering Beijing Institute of Technology Beijing100081 China Department of Automobile Engineering Tianjin Transportation Vocational College Tianjin300222 China Tianjin Taihua Easy-Robot Science and Technology Co. Ltd China

Micro-linear motor, is the key feed components which is based on macro–micro-motion control technology, the accuracy of its movement directly determines the accuracy of ultra-precision machining level. Based on the study of the open servo characteristics of POWER program multiple axis controller (PMAC), a fuzzy proportional integral derivative (PID) composite control technology is applied to the servo control of the motor. The fuzzy control is used to improve the response speed and dynamic performance of the system, and the precise PID control is used to realise the precise position control. In this study, based on the analysis of linear motor installation and load characteristics, the use of smooth switching fuzzy PID composite control algorithm is applied to the micro-feed motor control. Due to the introduction of the smoothing weighting function, the composite fuzzy PID servo control mode of dual mode switching is implemented without disturbance switching. Finally, the effect of the control algorithm is verified by experiments, especially in the case of small errors, this algorithm still reflects the ability to adapt to the impact of interference. © 2019 Institution of engineering and Technology. All rights reserved.

关键词： Linear motors

来源：评论

学校读者我要写书评

暂无评论

Thermo-responsive poly( N -isopropylacrylamide) (PNIPAM) hydrogel particles improve workability loss and autogenous shrinkage in cement paste

引用

CEMENT 2022年 10卷

作者： Anastasia N. Aday Mohammad G. Matar Jorge Osio-Norgaard Wil V. Srubar Materials Science and Engineering Program University of Colorado Boulder ECOT 441 UCB 428 Boulder CO 80309-0428 USA Department of Civil Environmental and Architectural Engineering University of Colorado Boulder ECOT 441 UCB 428 Boulder CO 80309-0428 USA Department of Mechanical Engineering University of Colorado Boulder ECOT 441 UCB 428 Boulder CO 80309-0428 USA

In this work, we show that non-superabsorbent, thermo-responsive poly(N-isopropyl acrylamide) (PNIPAM) hydrogel particles (< 250 μm) can reduce autogenous shrinkage in cement paste and improve early-age stiffening that can be caused by traditional superabsorbent polymers (SAPs). Swelling measurements in DI water and cement filtrate solution suggest that SAP-induced early-age stiffening is caused by its super-absorbency in low-ionic solutions – a behavior not exhibited by non-superabsorbent PNIPAM. Addition of PNIPAM resulted in a 29% and 60% reduction in autogenous shrinkage strain at 14 days when used alone (0.3 wt% PNIPAM) and in combination with SAP (0.15% PNIPAM, 0.15% SAP), respectively, compared to a Control with no polymer addition. Furthermore, an addition of 0.3 wt.% PNIPAM exhibited a ∼29% and ∼37% decrease in static yield stress compared to a Control and 0.3 wt% SAP-modified cement pastes, respectively. Taken together, the results provide initial evidence to suggest that the use of hydrogels as internal curing agents may not necessarily require super-absorbency to reduce autogenous shrinkage. Non-superabsorbent hydrogels, like PNIPAM, may help reduce autogenous shrinkage while alleviating the effects of SAP-induced early-age stiffening.

关键词： Superabsorbent polymers Poly( N -isopropyl acrylamide) (PNIPAM) Static yield stress Autogenous shrinkage

来源：评论

学校读者我要写书评

暂无评论

Electricity energy price forecasting based on hybrid multi-stage heterogeneous ensemble: Brazilian commercial and residential cases

Electricity energy price forecasting based on hybrid multi-s...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Matheus Henrique Dal Molin Ribeiro Ramon Gomes da Silva Cristiane Canton Naylene Fraccanabbia Viviana Cocco Mariani Leandro dos Santos Coelho Industrial & Systems Engineering Graduate Program (PPGEPS) Pontifical Catholic University of Parana (PUCPR) Curitiba Parana Brazil Department of Mathematics Federal Technological University of Parana (UTFPR) Pato Branco Parana Brazil Pato Branco University Center (UNIDEP) Pato Branco Parana Brazil Mechanical Engineering Graduate Program (PPGEM) Pontifical Catholic University of Parana (PUCPR) Curitiba Parana Brazil Department of Electrical Engineering Federal University of Parana (UFPR) Curitiba Parana Brazil

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

The development of accurate models to forecast electricity energy prices is a challenge due to the number of factors which can affect this commodity. In this paper, a hybrid multi-stage approach is proposed to forecast multi-stepahead (one, two and three-month-ahead) Brazilian commercial and residential electricity energy prices. The proposed data analysis combines the pre-processing named complementary ensemble empirical mode decomposition (CEEMD) in the first stage coupled with the coyote optimization algorithm (COA) to define the CEEMD's hyperparameters, aiming to deal with time series non-linearities and enhance the model's performance. On the next stage, four machine learning models named extreme learning machine, Gaussian process, gradient boosting machine, and relevance vector machine are employed to train and predict the CEEMD's components. Finally, in the final stage, the results of the previous step are directly integrated to compose a heterogeneous ensemble learning of components to obtain the final forecasts. In this case, a grid of models is obtained. The best model is one that has better generalization out-of-sample. Through developed comparisons, results showed that combining COA-CEEMD with a heterogeneous ensemble learning can develop accurate forecasts. The modeling developed in this paper is promising and can support decision making in electricity energy price forecasting.

关键词： Predictive models Biological system modeling Forecasting Data models Optimization Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

The Seawater Heavy Metal Content of the Mining Port Close to the Residential Area in the Morowali District

引用

IOP Conference Series: Earth and Environmental Science 2021年第1期940卷

作者： J Delly K Mizuno T E B Soesilo M Gozan School of Environmental Science Universitas Indonesia Jakarta Pusat 10430 Jakarta Indonesia. Mechanical Engineering Department Faculty of Engineering Universitas Halu Oleo Kendari 93117 Indonesia. Bioprocess Engineering Program Department of Chemical Engineering Faculty of Engineering Universitas Indonesia Depok 16424 Indonesia.

Mining port operations are complex and can cause various forms of pollution. Analysis of seawater pollution from mining ports is required and complicated because of the various types of pollution, sources, effects, and different characteristics. This study examines the content of heavy metals in seawater in residential areas very close to mining ports. The method used sampling in three different places, examining seawater's heavy metal properties. Secondary data of the quality of seawater was obtained from the results of data monitoring carried out by the company periodically since the port was built as a comparison material from the results of sample inspection. The results of this study indicate that the waters around the settlements contain heavy metals. The composition of Cd was 10%, Pb was125%, Cu was 625%, Ni was 760%, and Zn was 300% above the standard of seawater quality for the Port Area set by the Indonesian government, which did not match the yearly reports (secondary data). On the other hand, community activities also have a minor role as a source of pollution. Therefore, it is essential to do further research with a focus on finding sources of pollution.

关键词：

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：