检索结果-内蒙古大学图书馆

25th IEEE International Conference of Young Professionals in Electron Devices and Materials, EDM 2024

作者： Grigorev, Ivan Mursalimov, Eduard Laboratory of Intelligent Information Systems for Marine Robots M.D. Ageev Institute of Marine Technology Problems FEB RAS Vladivostok Russia Laboratory of Robotics and Intelligent Control Systems Sevastopol State University Laboratory of Intelligent Information Systems for Marine Robots M.D. Ageev Institute of Marine Technology Problems FEB RAS Vladivostok Russia

ISBN: (纸本)9798350389234

In most cases, tool impact paths for surface treatment (painting, milling, laser hardening, etc.) represent a set of continuous spatial curves lying on the surface to be treated. For uniform processing, adjacent curves from this set must be equidistant from each other. This paper presents a new method for covering a given polygonal mesh with equidistant lines based on given initial lines (in the form of a set of vertices on this mesh) and a given distance between adjacent lines, that is measured by Euclidean distance. The method is based on constructing spheres from each vertex of the initial line and removing the vertices of the mesh that fall into at least one of the spheres: the desired equidistant line will be represented by not removed vertices lying on the spheres. To construct each subsequent equidistant line, the last constructed line is used as the initial one: thus, the entire mesh is covered along the surface, despite the fact that the distance between adjacent lines is measured in space. Due to this, the proposed method, unlike the existing ones, works with surfaces of any complexity and requires less computing resources. Ordering the points of the constructed lines, to obtain the reference points of the paths that can be executed by the manipulator, is also presented. © 2024 IEEE.

关键词： Spheres

来源：评论

学校读者我要写书评

暂无评论

Learning Rat-Like Behavioral Interaction Using a Small-Scale Robotic Rat

引用

Cyborg and Bionic systems 2023年第1期4卷 225-232页

作者： Hongzhao Xie Zihang Gao Guanglu Jia Shingo Shimoda Qing Shi Intelligent Robotics Institute School of Mechatronical EngineeringBeijing Institute of TechnologyBeijing 100081China Key Laboratory of Biomimetic Robots and Systems(Beijing Institute of Technology) Ministry of EducationBeijing 100081China Nagoya University Graduate School of Medicine NagoyaJapan

In this paper,we propose a novel method for emulating rat-like behavioral interactions in robots using reinforcement ***,we develop a state decision method to optimize the interaction process among 6 known behavior types that have been identified in previous research on rat *** novelty of our method lies in using the temporal difference(TD)algorithm to optimize the state decision process,which enables the robots to make informed decisions about their behavior *** assess the similarity between robot and rat behavior,we use Pearson *** then use TD-λto update the state value function and make state decisions based on *** robots execute these decisions using our dynamics-based *** results demonstrate that our method can generate rat-like behaviors on both short-and long-term timescales,with interaction information entropy comparable to that between real ***,our approach shows promise for controlling robots in robot-rat interactions and highlights the potential of using reinforcement learning to develop more sophisticated robotic systems.

关键词： robot enable similarity

来源：评论

学校读者我要写书评

暂无评论

Recent advances on monolithic perovskite-organic tandem solar cells

引用

Interdisciplinary Materials 2024年第1期3卷 113-132页

作者： Guanshui Xie Huan Li Longbin Qiu Shenzhen Key Laboratory of Intelligent Robotics and Flexible Manufacturing Systems Department of Mechanical and Energy EngineeringSUSTech Energy Institute for Carbon NeutralitySouthern University of Science and TechnologyShenzhenChina

Perovskite-organic tandem solar cells(TSCs)have emerged as a groundbreaking technology in the realm of photovoltaics,showcasing remarkable enhancements in efficiency and significant potential for practical ***-organic TSCs also exhibit facile fabrication surpassing that of all-perovskite or all-organic TSCs,attributing to the advantageous utilization of orthogonal solvents enabling sequential solution process for each *** perovskite-organic TSCs capitalize on the complementary light absorption characteristics of perovskite and organic *** is a promising prospect of achieving further enhanced power conversion efficiencies by covering a broad range of the solar spectrum with optimized perovskite absorber,organic semiconductors as well as the interconnecting layer's optical and electrical *** review comprehensively analyzes the recent advancements in perovskite-organic TSCs,highlighting the synergistic effects of combining perovskite with a low open-circuit voltage deficit,organic materials with broader light absorption,and interconnecting layers with reduced optical and electrical ***,the underlying device architecture design,regulation strategies,and key challenges facing the high performance of the perovskite-organic TSCs are also discussed.

关键词： interconnecting layer narrow‐bandgap organic solar cells recombination layer tandem solar cells wide‐bandgap perovskite solar cells

来源：评论

学校读者我要写书评

暂无评论

Entropy Seeking Constrained Multiagent Reinforcement Learning 23

Entropy Seeking Constrained Multiagent Reinforcement Learnin...

引用

23rd International Conference on Autonomous Agents and Multiagent systems, AAMAS 2024

作者： Aydeniz, Ayhan Alp Marchesini, Enrico Amato, Christopher Tumer, Kagan Collaborative Robotics and Intelligent Systems Institute Oregon State University United States Laboratory for Information Decision Systems Massachusetts Institute of Technology United States Khoury College of Computer Sciences Northeastern University United States

Multiagent Reinforcement Learning (MARL) has been successfully applied to domains requiring close coordination among many agents. However, real-world tasks require safety specifications that are not generally considered by MARL algorithms. In this work, we introduce an Entropy Seeking Constrained (ESC) approach aiming to learn safe cooperative policies for multiagent systems. Unlike previous methods, ESC considers safety specifications while maximizing state-visitation entropy, addressing the exploration issues of constrained-based solutions. © 2024 International Foundation for Autonomous Agents and Multiagent systems.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Mechanical Properties Inside Origami-Inspired Structures: An Overview

引用

Applied Mechanics Reviews 2025年第1期77卷 011001页

作者： Yan, Peng Huang, Hailin Meloni, Marco Li, Bing Cai, Jianguo Department of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen518052 China Harbin Institute of Technology Shenzhen518052 China Key Laboratory of C & PC Structures of Ministry of Education National Prestress Engineering Research Center Southeast University Nanjing211189 China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150001 China Guangdong Provincial Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics Harbin Institute of Technology Shenzhen518052 China Key University Laboratory of Mechanism Machine Theory and Intelligent Unmanned Systems of Guangdong Habin Institute of Technology Shenzhen518052 China

In recent decades, origami has transitioned from a traditional art form into a systematic field of scientific inquiry, characterized by attributes such as high foldability, lightweight frameworks, diverse deformation modes, and limited degrees-of-freedom. Despite the abundant literature on smart materials, actuation methods, design principles, and manufacturing techniques, comprehensive reviews focusing on the mechanical properties of origami-inspired structures are relatively rare and unsystematic. This review aims to fill this void by analyzing and summarizing the significant studies conducted on the mechanical properties of origami-inspired structures from 2013 to 2023. We begin with an overview that includes essential definitions of origami, classical origami patterns, and their associated tessellated or stacked structures. Following this, we delve into the principal dynamic modeling method for origami and conduct an in-depth analysis of the key mechanical properties of origami-inspired structures. These properties include tunable stiffness, bistability and multistability, metamechanical properties demonstrated by origami-based metamaterials, and bio-inspired mechanical properties. Finally, we conclude with a comprehensive summary that discusses the current challenges and future directions in the field of origami-inspired structures. Our review provides a thorough synthesis of both the mechanical properties and practical applications of origami-inspired structures, aiming to serve as a reference and stimulate further research. © 2025 American Society of Mechanical Engineers (ASME). All rights reserved.

关键词： Degrees of freedom (mechanics)

来源：评论

学校读者我要写书评

暂无评论

IIITDWD_SVC@DravidianLangTech-2024: Breaking Language Barriers;Hate Speech Detection in Telugu-English Code-Mixed Text 4

IIITDWD_SVC@DravidianLangTech-2024: Breaking Language Barrie...

引用

4th Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, DravidianLangTech 2024

作者： Sai, Chava Srinivasa Kumar, Rangoori Vinay Saumya, Sunil Biradar, Shankar Department of Data Science and Intelligent Systems Indian Institute of Information Technology Karnatka Dharwad India

ISBN: (纸本)9798891760783

Social media platforms have become increasingly popular and are utilized for a wide range of purposes, including product promotion, news sharing, accomplishment sharing, and much more. However, it is also employed for defamatory speech, intimidation, and the propagation of untruths about particular groups of people. Further, hateful and offensive posts spread quickly and often have a negative impact on people;it is important to identify and remove them from social media platforms as soon as possible. Over the past few years, research on hate speech detection and offensive content has grown in popularity. One of the many difficulties in identifying hate speech on social media platforms is the use of code-mixed language. The majority of people who use social media typically share their messages in languages with mixed codes, like Telugu–English. To encourage research in this direction, the organizers of DravidianLangTech@EACL-2024 conducted a shared task to identify hateful content in Telugu-English code-mixed text. Our team participated in this shared task, employing three different models: Xlm-Roberta, BERT, and Hate-BERT. In particular, our BERT-based model secured the 14th rank in the competition with a macro F1 score of 0.65. © 2024 Association for Computational Linguistics.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Crawling Gait Enables Stable Quadrupedal Locomotion in A Bioinspired Robotic Rat

Crawling Gait Enables Stable Quadrupedal Locomotion in A Bio...

引用

2024 IEEE International Conference on Real-Time Computing and robotics, RCAR 2024

作者： Wang, Ruochao Quan, Xiaolong Xiao, Hang Du, Rongjie Qin, Boyang Shi, Qing Beijing Institute of Technology Intelligent Robotics Institute School of Mechatronical Engineering Beijing China Key Laboratory of Biomimetic Robots and Systems Beijing Institute of Technology Ministry of Education Beijing China

ISBN: (纸本)9798350372601

Constrained by the performance of actuators and controllers, achieving stable walking in small-scale quadruped robots has been more challenging compared to larger ones. Rats, in their natural habitat, can achieve stable walking even in extreme environments like narrow spaces by utilizing crawling motion to lower their center of mass. Inspired by this, we conducted a comparative study of the walking stability between crawling and trot gaits on a ratinspired robot named SQuRo. Initially, we collected motion data for both crawling and trot gaits of SQuRo in a simulated environment. Subsequently, we analyzed the dynamic stability of the robot using Poincaré maps. The results indicate that SQuRo's phase trajectories converged into closed loops with periodicity under both gaits, demonstrating the presence of limit cycles. Moreover, fixed points were observed in the Poincaré maps for both gaits, suggesting the dynamic stability of quadrupedal locomotion. Compared to the trot gait, the convergence loops of the crawling gait phase trajectories were smaller, indicating more stable locomotion. We tested the performance of SQuRo's crawling gait in challenging outdoor environments, where SQuRo demonstrated stable walking consistently. This work provides a new approach for achieving stable walking in small-scale quadruped robots and can be readily applied to controller design across different sizes of legged robots. © 2024 IEEE.

关键词： Rats

来源：评论

学校读者我要写书评

暂无评论

External RGB-D Camera Based Mobile Robot Localization in Gazebo Environment with Real-Time Filtering and Smoothing Techniques 16th

External RGB-D Camera Based Mobile Robot Localization in Gaz...

引用

16th International Conference on Electromechanics and robotics "Zavalishin’s Readings", ERZR 2021

作者： Kononov, Kirill Lavrenov, Roman Gavrilova, Lilia Tsoy, Tatyana Intelligent Robotics Department Institute of Information Technology and Intelligent Systems Kazan Federal University Kazan Russia

ISBN: (纸本)9789811628139

In previous work, we successfully studied the possibility of a mobile robot localization using an external RGB-D camera. We conducted virtual experiments in a Gazebo simulator using ROS with a Turtlebot3 Waffle Pi as a mobile robot. find_object_2d package was used to localize the Turtlebot3 and send its computed position to ROS. Thus, we extended our research and ratchet that result up by implementing the algorithm for filtering and smoothing the computed mobile robot position. Our task was to develop a thin library that is a wrapper over the find_object_2d package. The filtering algorithm and smoothing can compute the supposed robot position or predict it in cases when the robot disappears from the camera‘s field of view. We conducted virtual experiments over again and draw a comparison between previous results (without filtering and smoothing algorithm) and current results (using filtering and smoothing algorithm with slight improvements). © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Learning Rat-Like Behavior for a Small-Scale Biomimetic Robot

引用

Engineering 2022年第10期17卷 232-243页

作者： Zihang Gao Guanglu Jia Hongzhao Xie Qiang Huang Toshio Fukuda Qing Shi Key Laboratory of Biomimetic Robots and Systems(Beijing Institute of Technology) Ministry of EducationBeijing 100081China Intelligent Robotics Institute School of Mechatronical EngineeringBeijing Institute of TechnologyBeijing 100081China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of TechnologyBeijing 100081China

Existing biomimetic robots can perform some basic rat-like movement primitives(MPs)and simple behavior with stiff combinations of these *** mimic typical rat behavior with high similarity,we propose parameterizing the behavior using a probabilistic model and movement ***,an analysis of fifteen 10 min video sequences revealed that an actual rat has six typical behaviors in the open field,and each kind of behavior contains different bio-inspired combinations of eight *** used the softmax classifier to obtain the behavior-movement hierarchical probability ***,we specified the MPs using movement parameters that are static and *** obtained the predominant values of the static and dynamic movement parameters using hierarchical clustering and fuzzy C-means clustering,*** predominant parameters were used for fitting the rat spinal joint trajectory using a second-order Fourier series,and the joint trajectory was generalized using a back propagation neural network with two hidden ***,the hierarchical probability model and the generalized joint trajectory were mapped to the robot as control policy and commands,*** implemented the six typical behaviors on the robot,and the results show high similarity when compared with the behaviors of actual rats.

关键词： Biomimetic Bio-inspired robot Neural network learning system Behavior generation

来源：评论

学校读者我要写书评

暂无评论

Synthesis of Human-Inspired intelligent Fonts Using Conditional-DCGAN

Synthesis of Human-Inspired Intelligent Fonts Using Conditi...

引用

International Conference on Computer Vision and Machine Intelligence, CVMI 2022

作者： Kalingeri, Ranjith Kushwaha, Vandana Kala, Rahul Nandi, G.C. Center of Intelligent Robotics Indian Institute of Information Technology Allahabad UP Prayagraj211015 India

ISBN: (纸本)9789811978661

Despite numerous fonts already being designed and easily available online, the desire for new fonts seems to be endless. Previous methods focused on extracting style, shape, and stroke information from a large set of fonts, or transforming and interpolating existing fonts to create new fonts. The drawback of these methods is that generated fonts look-alike fonts of training data. As fonts are created from human handwriting documents, they have uncertainty and randomness incorporated into them, giving them a more authentic feel than standard fonts. Handwriting, like a fingerprint, is unique to each individual. In this paper, we have proposed GAN-based models that automate the entire font generation process, removing the labor involved in manually creating a new font. We extracted data from single-author handwritten documents and developed and trained class-conditioned DCGAN models to generate fonts that mimic the author’s handwriting style. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： BCFID cGAN DCGAN FID intelligent fonts Random fonts WCFID

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：