检索结果-内蒙古大学图书馆

2022 IEEE International Conference on systems, Man, and Cybernetics, SMC 2022

作者： Kobayashi, Shoki Shibuya, Takeshi University of Tsukuba Master's Program in Intelligent and Mechanical Interaction Systems Ibaraki Japan University of Tsukuba Faculty of Engineering Information and Systems Ibaraki Japan

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Extreme environments, such as space and underwater, are difficult for humans to enter because they involve risks, hence it is necessary to employ autonomous robots instead of humans. When robots fail in extreme environments, it is essential for the robot to automatically recover control following the rules of failure because humans cannot repair the robot directly. Reinforcement learning is expected to automatically acquire the control rule;however, the retrieval of the control rule requires significant trial-and-error. Imitation learning cannot acquire the control rule if no suitable expert data exist. Methods combining imitation learning and reinforcement learning reduce the number of trial-and-errors;however, they are still not effective against robot failure because these methods cannot utilize expert data effectively. This paper proposes a reinforcement learning method that efficiently recovers control performance from failures by utilizing both the control rules prepared by the designer and multiple discriminators to calculate measures similar to expert data. Experimental results show that the proposed method recovers the control performance with fewer episodes than the conventional method. The main contribution of the proposed method is its efficiency against robot failure through utilizing expart data prepared for failure by the designers for imitation learning. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

CIRCUIT AND BRANCH RECTIFICATION OF THE SPATIAL 4C MECHANISM

CIRCUIT AND BRANCH RECTIFICATION OF THE SPATIAL 4C MECHANISM

引用

ASME 2000 International Design engineering Technical Conferences and Computers and Information in engineering Conference, IDETC-CIE 2000

作者： Larochelle, Pierre M. Mechanical Engineering Program Robotics and Spatial Systems Laboratory Florida Institute of Technology MelbourneFL32904 United States

ISBN: (纸本)9780791835173

Spatial 4C mechanisms are two degree of freedom kinematic closed-chains consisting of four rigid links simply connected in series by cylindrical(C) joints. In this work we are concerned with the design of spatial 4C mechanisms which move a rigid body through a finite sequence of prescribed locations in space. This task is referred to as rigid-body guidance by Suh and Radcliffe (20) and as motion generation by Erdman and Sandor (6). When 4C mechanisms are synthesized for such a task, for example by utilizing Roth's spatial generalization of Burmester's planar methods (17;18), the result is the physical dimensions which kinematically define the mechanism. However, the motion of the mechanism which takes the work piece through the sequence of prescribed locations in space is not determined. In fact, it may be impossible for the mechanism to move the body through all of the desired locations without disassembling the mechanism. This condition is referred to as a circuit defect. Moreover, in some cases the mechanism may enter a configuration which requires an additional mechanical input to guide the moving body as desired. These are referred to as branch defects. This paper presents a methodology for analyzing spatial 4C mechanisms to eliminate circuit and branch defects in motion generation tasks. Copyright © 2000 by ASME.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Underwater visible light communication using phase-shift keying and rolling-shutter effect 9

Underwater visible light communication using phase-shift key...

引用

9th IEEE Global Conference on Consumer Electronics, GCCE 2020

作者： Hamagami, Ritsuki Ebihara, Tadashi Wakatsuki, Naoto Mizutani, Koichi University of Tsukuba Master's Program in Intelligent and Mechanical Interaction Systems Tsukuba Japan University of Tsukuba Faculty of Engineering Information and Systems Tsukuba Japan

ISBN: (纸本)9781728198026

We propose an underwater visible light communication (VLC) system for use in drones. The transmitter modulates a message using phase-shift keying (PSK) and emits the signal as LED fast-blinking light. The receiver captures this pattern with a CMOS image sensor using a rolling-shutter effect, and demodulates PSK. In existing VLC systems, rolling-shutter effect is used to transmit baseband signals;this system transmits a passband signal tolerant of low-frequency optical interference noise. System performance was evaluated in test-tank experiments. Findings suggested that the VLC system with PSK outperformed that using on-off keying when noise frequency did not exceed carrier frequency. © 2020 IEEE.

关键词： Phase shift keying

来源：评论

学校读者我要写书评

暂无评论

Spades: Software for synthesizing spatial 4c mechanisms

Spades: Software for synthesizing spatial 4c mechanisms

引用

ASME 1998 Design engineering Technical Conferences, DETC 1998

作者： Larochelle, Pierre M. Robotics and Spatial Systems Laboratory Mechanical Engineering Program Florida Institute of Technology MelbourneFL32901 United States

ISBN: (纸本)9780791880319

In this paper we present SPADES, an interactive graphics based software package for SPAtial mechanismDESign. The program provides a platform for the synthesis of a mechanism that guides a body through either three or four prescribed positions in space. The purpose of this work is to assemble the current spatial 4C synthesis theory into a software package that is useful for spatial mechanism design and research. © 1998 by ASME.

关键词： Software packages

来源：评论

学校读者我要写书评

暂无评论

Rolling-Shutter Sensor-Based Visible Light Communication with Cross-Screen Filter: Communication and Positioning System Using a Commercial Camera 10

Rolling-Shutter Sensor-Based Visible Light Communication wit...

引用

10th IEEE Global Conference on Consumer Electronics, GCCE 2021

作者： Hamagami, Ritsuki Ebihara, Tadashi Wakatsuki, Naoto Maeda, Yuka Mizutani, Koichi University of Tsukuba Master's Program In Intelligent And Mechanical Interaction Systems Tsukuba Japan Faculty of Engineering Information And Systems University of Tsukuba Tsukuba Japan

ISBN: (纸本)9781665436762

We propose a visible light communication system using a commercial camera that achieves communication and positioning simultaneously, which is essential for intelligent transport systems (ITS). The transmitter (Tx) emits the data as fast-blinking light of the LED. The receiver (Rx) captures the signal using a rolling-shutter sensor with a cross-screen filter. Different from the previous system without a cross-screen filter, which can only achieve short-range and single-user communication, the proposed system can achieve long-range communication by diffusing the incoming light in a specific direction using a cross-screen filter. Furthermore, the proposed system has the potential to achieve multi-user communication and positioning, which used to require a high-speed camera, using a commercial camera. We evaluated the performance of the proposed system in indoor experiments. The experimental results suggest that the proposed system can improve communication range compared to the previous system. © 2021 IEEE.

关键词： Visible light communication

来源：评论

学校读者我要写书评

暂无评论

Explainable Reinforcement Learning via Causal Model Considering Agent's Intention

Explainable Reinforcement Learning via Causal Model Consider...

引用

2024 IEEE International Conference on systems, Man, and Cybernetics, SMC 2024

作者： Kim, SeongIn Shibuya, Takeshi University of Tsukuba Doctor's Program in Intelligent and Mechanical Interaction Systems Ibaraki Japan University of Tsukuba Faculty of Engineering Information and Systems Ibaraki Japan

ISBN: (纸本)9781665410205

Explaining agent's decision can offer valuable insights for designers and end-users. One proposed method for explaining an agent's decision-making involves representing a causal relation between state components and action as a causal model and providing explanations for the decisions made using causal model. However, traditional causal model often faces structural limitation, restricting the range of representable control problems. Additionally, providing accurate explanation becomes challenging in control problems with various types of rewards because agent's intention of an action is unknown. In this study, we introduce a causal model capable of representing a broader range of control problems and a method to provide accurate explanations in control problems with various types of reward structures. Through redefining the relationships between nodes in the causal model, we have enabled a broader representation of control problems. Also, by incorporating agent's intention into the explanation, we have achieved to provide a more precise explanation. To validate the effectiveness of our proposed method, we conducted experiments using OpenAI's LunarLander environment. Using a proposed causal model, we defined the causal model of LunarLander, which could not be represented by conventional causal models. Furthermore, by incorporating the intentions of an agent into the explanation, novel interpretations previously inaccessible have become feasible. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A preliminary study of the electrical and interlaminar shear properties of a porous CFRP composite laminate containing carbon nanofiber Z-threads 6

A preliminary study of the electrical and interlaminar shear...

引用

6th Annual Composites and Advanced Materials Expo, CAMX 2019

作者： Kirmse, Sebastian Ranabhat, Bikash Hsiao, Kuang-Ting University of South Alabama Mobile AL36688 United States Systems Engineering Program United States Department of Mechanical Engineering United States

In this study, a porous carbon fiber/epoxy nanocomposite (P-ZT-CFRP) containing a low concentration of z-threaded carbon nanofibers was manufactured. DC electrical conductivity measurements and interlaminar shear tests were performed on the porous nanocomposite. It was hypothesized that the CNFs interlock and connect multiple arrays of carbon fibers using a connecting agent (i.e., resin) at contact locations between the CNFs and carbon fibers, which provides additional strength to the otherwise weak porous composite laminate while making it extremely conductive. The through-thickness DC electrical conductivity was increased by 2840% (9.37 S/m) and 2971% (9.81 S/m) for the unidirectional porous nanocomposite laminate containing 0.85wt% and 2.0wt% of CNF z-threads, respectively, when compared to a traditional carbon fiber reinforced polymer (CFRP) (0.33 S/m). Void characterization showed that the void content in the matrix for the porous nanocomposites was at least 20%, which satisfies the definition of a porous nanocomposite [1]. The interlaminar shear strength of the 0.85wt% CNF z-threaded P-ZT-CFRP with a fiber volume fraction of around 80% was about 50% higher than for a P-CFRP without CNFs. Furthermore, the porous nanocomposite showed good potential in overcoming the effects of void on the mechanical properties of CFRPs. Using the rule of mixture, the P-ZT-CFRP shows a ~10.5% increase in longitudinal tensile strength and modulus when compared to a traditional CFRP. It was concluded that the material has high potential but will require additional research and research collaborations between industry partners to develop a possible next-generation multi-functional nanocomposite. © 2019 by Ever J. Barbero. Published by CAMX - The Composites and Advanced Materials Expo.

关键词： Carbon nanofibers

来源：评论

学校读者我要写书评

暂无评论

The z-directional dc electrical conductivity of carbon nanofiber z-threaded porous cfrp composites manufactured by radial flow alignment technique

The z-directional dc electrical conductivity of carbon nanof...

引用

International SAMPE Conference and Exhibition 2020

作者： Ranabhat, Bikash Kirmse, Sebastian Johnson, Michael Hsiao, Kuang-Ting University of South Alabama Department of Mechanical Engineering 150 Jaguar Drive Shelby Hall Suite 3130 MobileAL36608 United States Department of Mechanical Engineering United States Systems Engineering Program

The non-conductive polymer matrix impedes carbon fiber's excellent electrical conductivity in the carbon fiber reinforced polymer (CFRP) composites. Due to its low z-directional DC electrical conductivity, CFRP composites has limited application capabilities in lightning strike protection (LSP) and electromagnetic shielding. This research demonstrates the ability to manufacture lightweight and electrically conductive (i.e., z-direction) CNFs z-threaded porous CFRP composite utilizing just 50 % of epoxy used in the traditional composites. In this study, the radial flow alignment technique was used to z-thread carbon nanofibers (CNFs) into the carbon fiber fabric. Experimental results showed the z-directional DC electrical conductivity in the 0.85 wt% CNF z-threaded porous (P-ZT-CFRP) was 21.06 S/m, which is an increase of 778 % and 107 % compared to the traditional composite sample and P-CFRP (without nano-reinforcement) laminate, respectively. © 2020 Soc. for the Advancement of Material and Process engineering. All rights reserved.

关键词： Carbon nanofibers

来源：评论

学校读者我要写书评

暂无评论

Potential of SERS for rapid detection of melamine and cyanuric acid extracted from milk

引用

Sensing and Instrumentation for Food Quality and Safety 2010年第1期4卷 13-19页

作者： Liu, Bin Lin, Mengshi Li, Hao Food Science Program Division of Food Systems and Bioengineering University of Missouri Columbia MO 65211 United States Department of Mechanical and Aerospace Engineering University of Missouri Columbia MO 65211 United States

Melamine, a nitrogen-rich chemical, was implicated in the pet and human food recalls in 2007 and in the global food safety scares in 2008 involving milk and other milk-derived products. In this study, we investigated the feasibility of using surface-enhanced Raman spectroscopy (SERS) coupled with SERS-active gold substrates for rapid detection of trace amounts of melamine and its analogue (that is, cyanuric acid) in liquid milk. Raman signals of tested samples were significantly enhanced by SERS. The identification limit for SERS using gold substrate can reach 2 ppm of melamine in liquid milk. Partial least squares (PLS) models were established for the quantification of melamine in liquid milk by SERS: R = 0.90, RMSEP = 1.48 × 10-5. Our results demonstrate that rapid detection of melamine in milk can be achieved by SERS;while detection of cyanuric acid in milk remains a challenging task due to rapid enol-keto tautomerism of cyanuric acid. The SERS method is faster and simpler than other traditional methods, and requires minimum sample preparation. These results demonstrate that SERS could be used to detect food contaminants such as melamine in foods and food ingredients quickly and accurately. © 2009 Springer Science+Business Media, LLC.

关键词： Substrates

来源：评论

学校读者我要写书评

暂无评论

FPGA implementation of the EKF algorithm for localization in mobile robotics using a unified hardware module approach

FPGA implementation of the EKF algorithm for localization in...

引用

International Conference on ReConFigurable Computing and FPGAs, ReConFig 2015

作者： Contreras, Luis Cruz, Sergio Motta, J.M.S.T. Llanos, Carlos H. Graduate Program in Mechatronic Systems Department of Mechanical Engineering University of Brasilia Brasilia D.F.70910-900 Brazil

ISBN: (纸本)9781467394062

In this paper a Hardware Architecture for computing the Extended Kalman Filter (EKF) is presented which is addressed to solve the self-localization problem of autonomous mobile robots. In this case, the overall EKF algorithm has been implemented in hardware over an Altera Cyclone IV FPGA with a Nios II processor, in which the latter is used only for interfacing and communication tasks. The achieved implementation has been adapted and applied to the mobile platform Pioneer 3AT (P3AT) for validation task. The prediction stage of the EKF algorithm was based on a dead-reckoning system model and the estimation stage on a measurement system which uses a sensor of Laser Range Finder (LRF). The proposed architecture has been designed considering a Unified Hardware Module approach using floating-point arithmetic operators, allowing the operations to be computed with large precision and dynamic range. Furthermore, several metrics have been used to evaluate the system performance, measuring both FPGA resources consumption, power consumption and execution time. Finally, the suitability of reconfigurable devices for such kind of applications has been verified and also discussed. © 2015 IEEE.

关键词： Field programmable gate arrays (FPGA)

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：