检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Zhou, Feng Guo, Jia Zhao, Yan Chu, Xiaohong Liu, Lei Zhou, Changshi Zhao, Zhengzhi Collaborative Innovation Center of Steel Technology University of Science and Technology Beijing Beijing100083 China Beijing Laboratory for Modern Transportation Advanced Metal Materials and Processing Technology University of Science and Technology Beijing Beijing100083 China Shougang Technician college Beijing100083 China Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai200092 China

In this study, Nb-Ti microalloyed weathering steel was studied, and the isothermal compression test was carried out in the range of deformation temperature 1050~1150 ℃ and strain rate 0.001~0.1 s-1 using the Gleeble-3800 thermomechanical simulator. The dynamic softening mechanism under different deformation conditions was analyzed according to the flow stress curves, the dynamic recrystallization (DRX) activation energy of Nb-Ti microalloyed weathering steel was calculated as 321.1 KJ/mol, and the characteristic points on the flow stress curves under different deformation conditions were obtained. To more accurately describe DRX behavior of Nb-Ti microalloyed weathering steel, a DRX kinetics model is proposed based on strain rate and deformation temperature as variables. A high-temperature flow stress model, including DRX kinetics, is established based on the KM model, which shows better accuracy and reliability and can accurately predict the flow stresses under different deformation conditions. Based on the dislocation-driven nucleation conditions and the kinetic theory of grain growth, a cellular automaton (CA) model of the DRX process， including second-phase particles in microalloyed steels, was constructed for the first time, and the dynamic recrystallization evolution was successfully simulated. The average grain size and DRX evolution characteristics under different deformation conditions were accurately predicted by adjusting the size and volume fraction of the second phase particles. The model offers a powerful tool and method to gain a comprehensive understanding of the high temperature deformation behavior and microstructure evolution in microalloyed steels. Furthermore, it serves as a valuable reference for optimizing the design of microalloy compositions and the rolling process of microalloyed steels. © 2023, The Authors. All rights reserved.

关键词： Dynamic recrystallization

来源：评论

学校读者我要写书评

暂无评论

Theory of Mind Abilities Predict Robot's Gaze Effects on Object Preference

引用

IEEE Transactions on Affective Computing 2025年

作者： Manzi, Federico Ishikawa, Mitsuhiko Dio, Cinzia Di Itakura, Shoji Kanda, Takayuki Ishiguro, Hiroshi Massaro, Davide Marchetti, Antonella Università Cattolica del Sacro Cuore Research Unit on Theory of Mind Department of Psychology Milan Italy Università Cattolica del Sacro Cuore Research Unit in Psychology and Robotics in the Lifespan Department of Psychology Milan Italy IRCCS Fondazione Don Carlo Gnocchi Milan Italy Hitotsubashi University Hitotsubashi Institute for Advanced Study Japan Ritsumeikan University Kyoto Japan Kyoto University Department of Computer Science Human-Robot Interaction Laboratory Kyoto Japan IRC'HIL Keihana Science City Advanced Telecommunications Research Institute International Kyoto Japan Osaka University Department of Intelligent Systems Toyonaka Japan

This study investigated the differences between human and robot gaze in influencing preference formation, and examined the role of Theory of Mind (ToM) abilities in this process. Human eye gaze is one of the most important sources of information for social interaction and research has demonstrated its effectiveness in influencing people's preference. With increasing technological development, we will interact with robots that can exhibit gaze behavior and influence people's preference. It is unclear whether there are any differences between humans and robots in this process. The present study aimed to analyze the role of the gaze of a robot and a human in influencing the ascription of a preference to the gazer and the participants' preference. Furthermore, we examined the role of ToM abilities in preference formation. The results showed that the gaze has a greater effect on the gazer preference compared to participants' preference regardless of the agent (human or robot). In addition, ToM abilities predict both gazer and individual preferences in the robot's condition only even though different socio-cognitive mechanisms are involved. The study suggests that adults are cognitively able to process the gaze of a robot similar to a human, recognizing the underlying mental state. However, only for the robot, different cognitive mechanisms are involved in the gazer (i.e., perspective taking) and participants' preference formation (i.e., advanced ToM). © 2010-2012 IEEE.

关键词： Social robots

来源：评论

学校读者我要写书评

暂无评论

Training Human Teacher to Improve Robot Learning from Demonstration: A Pilot Study on Kinesthetic Teaching

Training Human Teacher to Improve Robot Learning from Demons...

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Maram Sakr Martin Freeman H. F. Machiel Van der Loos Elizabeth Croft Collaborative Advanced Robotics and Intelligent Systems (CARIS) Laboratory Mechanical Engineering University of British Columbia Electrical and Computer Systems Engineering Monash University Stanford University

ISBN: (数字)9781728160757

ISBN: (纸本)9781728160764

Robot Learning from Demonstration (LfD) allows robots to implement autonomous manipulation by observing the movements executed by a demonstrator. As such, LfD has been established as a key element for useful user interactions in everyday environments. Kinesthetic teaching, a teaching technique within LfD, entails physically guiding the robot to achieve a task. When demonstrating complex actions on a multi-DoF manipulator, novice users typically encounter difficulties with trajectory continuity and joint orientation, necessitating training by an expert. A comparison between different training approaches is conducted in a study of nine novice users. These approaches are kinesthetic, observational and discovery-learning. The kinesthetic method utilizes record and playback functions implemented on a 7-DoF Barrett Technology WAM robot. A novice user passively holds the arm while an expert's trajectory is replayed. A visual demonstration by the expert is used for the observational training group. The discovery-learning group does not receive an expert demonstration; they use trial-and-error to produce the trajectory on their own. Task-space performance is evaluated pre- and post-training for each user to determine the relative and absolute performance improvements of the groups across the three training approaches. Absolute performance improvements are compared to the performance of an expert and a minimum-jerk trajectory to gauge how skillful the participant becomes with respect to the expert. The kinesthetic approach shows superior indicators of performance in trajectory similarity to the minimum-jerk trajectory with 39% and 13% improvement over the observational and discovery methods, respectively. Observational training shows greater improvement in terms of the smoothness of the velocity profile with 32.7% compared to 29.5% and 21.9% for both discovery and kinesthetic training, respectively.

关键词： Robots Task analysis Training Trajectory End effectors Robot learning Robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

Low-Cost and Unobtrusive Respiratory Condition Monitoring Based on Raspberry Pi and Recurrent Neural Network

Low-Cost and Unobtrusive Respiratory Condition Monitoring Ba...

引用

IEEE International Symposium on Circuits and systems

作者： Yunlu Wang Menghan Hu Chaohua Yang Na Li Jian Zhang Qingli Li Guangtao Zhai Simon X. Yang Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University China Key Laboratory of Artificial Intelligence Ministry of Education China Advanced Robotics and Intelligent Systems Laboratory University of Guelph Canada

This paper presents a low-cost and unobtrusive intelligent respiratory monitoring system. To achieve low-cost and remote measurement of respiratory signal, an RGB camera collaborated with marker tracking is used as data acquisition sensor, and a Raspberry Pi is used as data processing platform. To overcome challenges in actual applications, the signal processing algorithms are designed for removing sudden body movements and smoothing the raw signal. To discover more specific information in the respiratory signal, respiratory rate is estimated by a translational cross point algorithm, and respiratory pattern is identified by recurrent neural network. Finally, the obtained decision-making information and some original information are sent to user's smartphone via a cloud service platform. For estimating respiratory rate, the Bland-Altman plot demonstrates the satisfactory results with agreement ranges of -0.13 ± 5.85 bpm. With respect to the classification of breathing patterns, the results validate that the system has the good performance with the accuracy, precision, recall, and F1 of 92.5%, 92.5%, 93.3%, and 92.9%, respectively. This work may contribute to the development of low-cost and non-contact respiratory monitoring products specific to home or work health care.

关键词： Performance evaluation Recurrent neural networks Smoothing methods Tracking Decision making Signal processing algorithms Medical services

来源：评论

学校读者我要写书评

暂无评论

Semantic Geometric Fusion Multi-object Tracking and Lidar Odometry in Dynamic Environment

arXiv

引用

arXiv 2022年

作者： Ma, Tingchen Ou, Yongsheng The Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China The Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Shenzhen518055 China The Key Laboratory of Human-Machine-Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China The Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China

The SLAM system based on static scene assumption will introduce huge estimation errors when moving objects appear in the field of view. This paper proposes a novel multi-object dynamic lidar odometry (MLO) based on semantic object detection technology to solve this problem. The MLO system can provide reliable localization of robot and semantic objects and build long-term static maps in complex dynamic scenes. For ego-motion estimation, we use the environment features that take semantic and geometric consistency constraints into account in the extraction process. The filtering features are robust to semantic movable and unknown dynamic objects. At the same time, a least square estimator using the semantic bounding box and object point cloud is proposed to achieve accurate and stable multi-object tracking between frames. In the mapping module, we further realize dynamic semantic object detection based on the absolute trajectory tracking list (ATTL). Then, static semantic objects and environmental features can be used to eliminate accumulated localization errors and build pure static maps. Experiments on public KITTI data sets show that the proposed system can achieve more accurate and robust tracking of the object and better real-time localization accuracy in complex scenes compared with existing technologies. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A moving target detection and localization strategy based on optical flow and pin-hole imaging methods using monocular vision

A moving target detection and localization strategy based on...

引用

2021 IEEE International Conference on Real-Time Computing and robotics, RCAR 2021

作者： Wang, Shun Guo, Qingqiang Xu, Sheng Su, Dan School of Control Science and Engineering Shandong University Shandong Jinan250061 China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Shenzhen518055 China Shandong Institute of Advanced Technology Chinese Academy of Sciences Shandong Jinan250102 China Orbbec Inc. Shenzhen518057 China

ISBN: (纸本)9781665436786

This paper proposes a new strategy for moving target detection and localization based on monocular vision. Firstly, to detect a moving target with large displacement and high speed accurately, two consecutive video images captured by a monocular camera are preprocessed using the enhancement and denoising methods. Then, the optical flow representing motion information is calculated iteratively by the modified Lucas-Kanade optical flow method. Secondly, a new interest region extraction method is developed to overcome the negative impacts caused by the noises in the background. Specifically, this proposed method combines a two-level image segmentation strategy from coarse to fine, including median filtering, two-direction dynamic threshold segmentation, the Otsu method, and morphological processing. Thirdly, a low computational cost target localization algorithm is proposed based on pin-hole imaging theory. Besides, it only uses two-dimensional image and camera parameters to obtain the moving target's position in the three-dimensional space. Finally, experimental results show that the proposed strategy can effectively eliminate noise interferences and realize moving target detection, extraction, and localization. © 2021 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A Deep Siamese Neural Network N-Shot Learning Approach for the Recognition of Chinese Calligraphy

SSRN

引用

SSRN 2022年

作者： Zhou, Zhaokun Wang, Weijun Ou, Yuhao Che, Qishu Feng, Wei Shenzhen Key Laboratory of Smart Sensing and Intelligent Systems Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen518055 China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen518055 China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen518055 China Guangzhou Institute of Advanced Technology Chinese Academy of Sciences Guangdong Guangzhou511458 China University of Chinese Academy of Sciences Guangdong Shenzhen518055 China

The forms of Chinese calligraphic characters vary considerably, posing a challenge even for a typical educated Chinese to read. The total number of characters is in the excess of ten thousand, many of which have small numbers of samples surviving to date. Thus, Chinese calligraphy recognition is a unique challenge for the state-of-the art deep-learning algorithms that require large training datasets to accurately categorize. Here we present a novel deep-convolutional Siamese Neural Network (SNN) based architecture that finishes training in one day on a single RTX 2080 Ti graphics card while reaching an accuracy of 95.0% on a vast set of more than 6000 Chinese characters. We found that, after image pre-processing and setting the optimized SNN parameters, our recognition algorithm (i) is light weight, (ii) trains with small numbers of samples, achieving few-/one-shot learning (iii) recognizes a new character that is not present in the training set and (iv) includes the new character in the dictionary so the dictionary is continually expanded. Further work on the improvement of our method is also proposed including the localization of multiple tokens in an image to further automate detections and word prediction with RNNs to boost categorization accuracy. © 2022, The Authors. All rights reserved.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

An Improved UAV Path Optimization Algorithm for Target Accurately and Quickly Localization

An Improved UAV Path Optimization Algorithm for Target Accur...

引用

2021 International Conference on Information, Cybernetics, and Computational Social systems, ICCSS 2021

作者： Liang, Rui Wu, Kai Xu, Sheng Xu, Tiantian Ma, Xiaoyi Fu, Lianyu City West Power Supply Branch State Grid Tianjin Electric Power Company Tianjin China Shenzhen Institute of Advanced Technology Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen China Shenzhen Institute of Advanced Technology Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen China State Grid Tianjin Information Telecommunication Company Tianjin China

ISBN: (纸本)9781665402453

Angle-of-arrival (AOA) target localization using the unmanned aerial vehicle (UAV) has been widely applied in many practical applications. To localize an invasive target quickly and accurately, both the estimation and UAV path optimization algorithms are required. This paper focuses on developing a path optimization method to improve the target estimation performance. Firstly, the problem formulation of AOA target localization is introduced. Secondly, the classical pseudolinear Kalman filter (PLKF) and the gradient-based path optimization are presented. Thirdly, we analyze the problems that existed in the previous methods and propose an improved gradient-descent path optimization algorithm combined with a simple grid search method. Finally, the simulation examples verify the effectiveness of the proposed methods. © 2021 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

NeRF in robotics: A Survey

arXiv

引用

arXiv 2024年

作者： Wang, Guangming Pan, Lei Peng, Songyou Liu, Shaohui Xu, Chenfeng Miao, Yanzi Zhan, Wei Tomizuka, Masayoshi Pollefeys, Marc Wang, Hesheng The University of Cambridge ETH Zurich Switzerland The Department of Automation Shanghai Jiao Tong University Shanghai200240 China The Key Laboratory of System Control and Information Processing Ministry of Education of China China Engineering Research Center of Intelligent Control for Underground Space Ministry of Education School of Information and Control Engineering Advanced Robotics Research Center China University of Mining and Technology Xuzhou221116 China ETH Zurich Zurich Switzerland Mechanical Systems Control Laboratory University of California Berkeley United States

Meticulous 3D environment representations have been a longstanding goal in computer vision and robotics fields. The recent emergence of neural implicit representations has introduced radical innovation to this field as implicit representations enable numerous capabilities. Among these, the Neural Radiance Field (NeRF) has sparked a trend because of the huge representational advantages, such as simplified mathematical models, compact environment storage, and continuous scene representations. Apart from computer vision, NeRF has also shown tremendous potential in the field of robotics. Thus, we create this survey to provide a comprehensive understanding of NeRF in the field of robotics. By exploring the advantages and limitations of NeRF, as well as its current applications and future potential, we hope to shed light on this promising area of research. Our survey is divided into two main sections: The Application of NeRF in robotics and The Advance of NeRF in robotics, from the perspective of how NeRF enters the field of robotics. In the first section, we introduce and analyze some works that have been or could be used in the field of robotics from the perception and interaction perspectives. In the second section, we show some works related to improving NeRF's own properties, which are essential for deploying NeRF in the field of robotics. In the discussion section of the review, we summarize the existing challenges and provide some valuable future research directions for reference. © 2024, CC BY-NC-ND.

关键词： robotics

来源：评论

学校读者我要写书评

暂无评论

Crossbreeding in random forest

arXiv

引用

arXiv 2021年

作者： Nadi, Abolfazl Moradi, Hadi Taheri, Khalil Advanced Robotics and Intelligent Systems Laboratory School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran11155-4563 Iran SKKU Suwon16419 Korea Republic of

Ensemble learning methods are designed to benefit from multiple learning algorithms for better predictive performance. The tradeoff of this improved performance is slower speed and larger size of ensemble learning systems compared to single learning systems. In this paper, we present a novel approach to deal with this problem in Random Forest (RF) as one of the most powerful ensemble methods. The method is based on crossbreeding of the best tree branches to increase the performance of RF in space and speed while keeping the performance in the classification measures. The proposed approach has been tested on a group of synthetic and real datasets and compared to the standard RF approach. Several evaluations have been conducted to determine the effects of the Crossbred RF (CRF) on the accuracy and the number of trees in a forest. The results show better performance of CRF compared to RF. © 2021, CC BY-NC-ND.

关键词： Learning systems

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：