检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

24,618 篇 会议
154 篇 期刊文献
57 册 图书
1 篇 学位论文

馆藏范围

24,830 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

10,141 篇 工学
- 6,339 篇 控制科学与工程
- 4,109 篇 计算机科学与技术...
- 2,664 篇 软件工程
- 2,151 篇 电气工程
- 1,865 篇 机械工程
- 1,146 篇 仪器科学与技术
- 735 篇 信息与通信工程
- 585 篇 生物工程
- 474 篇 生物医学工程（可授...
- 431 篇 光学工程
- 403 篇 力学（可授工学、理...
- 386 篇 电子科学与技术（可...
- 263 篇 化学工程与技术
- 252 篇 交通运输工程
- 251 篇 材料科学与工程（可...
- 244 篇 动力工程及工程热...
- 217 篇 土木工程
- 206 篇 建筑学
- 183 篇 安全科学与工程
3,073 篇 理学
- 1,766 篇 数学
- 905 篇 物理学
- 642 篇 生物学
- 578 篇 统计学（可授理学、...
- 482 篇 系统科学
- 229 篇 化学
1,224 篇 管理学
- 959 篇 管理科学与工程(可...
- 312 篇 工商管理
- 306 篇 图书情报与档案管...
328 篇 医学
- 287 篇 临床医学
- 205 篇 基础医学(可授医学...
124 篇 经济学
106 篇 法学
87 篇 农学
53 篇 教育学
27 篇 文学
16 篇 军事学
13 篇 艺术学
1 篇 哲学

主题

2,481 篇 predictive model...
1,995 篇 robots
1,827 篇 robotics and aut...
1,741 篇 computational mo...
1,715 篇 automation
1,656 篇 data models
1,585 篇 robot sensing sy...
1,491 篇 analytical model...
1,410 篇 adaptation model...
1,390 篇 training
1,187 篇 accuracy
1,141 篇 mathematical mod...
1,100 篇 trajectory
1,048 篇 mobile robots
922 篇 feature extracti...
845 篇 robustness
840 篇 robot kinematics
793 篇 control systems
718 篇 solid modeling
698 篇 uncertainty

机构

179 篇 university of ch...
144 篇 school of artifi...
111 篇 robotics institu...
89 篇 school of automa...
84 篇 institute of aut...
72 篇 shenyang institu...
68 篇 the robotics ins...
68 篇 school of electr...
68 篇 institutes for r...
64 篇 state key labora...
62 篇 school of mechat...
50 篇 department of au...
49 篇 department of au...
48 篇 state key labora...
46 篇 school of automa...
44 篇 school of mechan...
42 篇 robotics institu...
39 篇 school of automa...
32 篇 school of automa...
30 篇 college of autom...

作者

37 篇 secchi cristian
34 篇 yuechao wang
32 篇 yun-hui liu
31 篇 cristian secchi
29 篇 shugen ma
28 篇 lining sun
24 篇 xiang li
22 篇 jian wang
22 篇 jianda han
22 篇 fabio ramos
20 篇 xinyu wu
20 篇 wu xinyu
20 篇 daniela rus
19 篇 tomizuka masayos...
19 篇 wei li
19 篇 levine sergey
18 篇 c. laugier
18 篇 jie zhao
18 篇 chen chen
18 篇 dinesh manocha

语言

23,753 篇 英文
993 篇 其他
102 篇 中文
2 篇 西班牙文
1 篇 俄文

检索条件"任意字段=International Conference on Methods and Models in Automation and Robotics"

共 24830 条记录，以下是3891-3900 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning

Robot Fine-Tuning Made Easy: Pre-Training Rewards and Polici...

引用

IEEE international conference on robotics and automation (ICRA)

作者： Jingyun Yang Max Sobol Mark Brandon Vu Archit Sharma Jeannette Bohg Chelsea Finn Department of Computer Science Stanford University

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

The pre-train and fine-tune paradigm in machine learning has had dramatic success in a wide range of domains because the use of existing data or pre-trained models on the internet enables quick and easy learning of new tasks. We aim to enable this paradigm in robotic reinforcement learning, allowing a robot to learn a new task with little human effort by leveraging data and models from the Internet. However, reinforcement learning often requires significant human effort in the form of manual reward specification or environment resets, even if the policy is pre-trained. We introduce RoboFuME, a reset-free fine-tuning system that pre-trains a multi-task manipulation policy from diverse datasets of prior experiences and self-improves online to learn a target task with minimal human intervention. Our insights are to utilize calibrated offline reinforcement learning techniques to ensure efficient online fine-tuning of a pre-trained policy in the presence of distribution shifts and leverage pre-trained vision language models (VLMs) to build a robust reward classifier for autonomously providing reward signals during the online fine-tuning process. In a diverse set of five real robot manipulation tasks, we show that our method can incorporate data from an existing robot dataset collected at a different institution and improve on a target task within as little as 3 hours of autonomous real-world experience. We also demonstrate in simulation experiments that our method outperforms prior works that use different RL algorithms or different approaches for predicting rewards. Project website: https://***

关键词： Reinforcement learning Manuals Prediction algorithms Multitasking Data models Internet Task analysis

来源：评论

学校读者我要写书评

暂无评论

Transfer-Robot Task Allocation Algorithm Considering Production Priority for Flexible Job-Shop Scheduling Problem

Transfer-Robot Task Allocation Algorithm Considering Product...

引用

international conference on Control, automation, robotics and Vision (ICARCV)

作者： Meng Zhou Xinheng Wang Zhongxing Liang Chang Wang Jing Wang College of Electrical and Control Engineering North China University of Technology Beijing P. R. China Beijing Aerospace Automatic Control Institute Beijing China College of Intelligent Systems Science and Engineering Harbin Engineering University Harbin P. R. China

ISBN: (数字)9798331518493

ISBN: (纸本)9798331518509

This paper proposes a flexible job-shop scheduling problem optimization method, which focuses on providing solutions for industrial production. First, in terms of model construction, the method further considers the cost of automated guided vehicles and the priority of workpiece production based on previous methods. Then, this method solves the model by non-dominated sorting genetic algorithm with self-cross and delete-mutation. It reduces the production time and energy by an average of 6.4% and 19.4%, which are 5.4% and 15.1% with the priority. Finally, the simulation verifies that the method effectively reduces the production cost while realizing the adjustment of the automated guided vehicle number and the workpiece production sequence.

关键词： Hands Remotely guided vehicles Job shop scheduling Costs Optimization methods Production Resource management Vehicle dynamics Sorting Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

SPATIO-TEMPORAL APPROXIMATION: A TRAINING-FREE SNN CONVERSION FOR TRANSFORMERS 12

SPATIO-TEMPORAL APPROXIMATION: A TRAINING-FREE SNN CONVERSIO...

引用

12th international conference on Learning Representations, ICLR 2024

作者： Jiang, Yizhou Hu, Kunlin Zhang, Tianren Gao, Haichuan Liu, Yuqian Fang, Ying Chen, Feng Department of Automation Tsinghua University Beijing China Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China College of Computer and Cyber Security Fujian Normal University Fuzhou China LSBDPA Beijing Key Laboratory Beijing China

Spiking neural networks (SNNs) are energy-efficient and hold great potential for large-scale inference. Since training SNNs from scratch is costly and has limited performance, converting pretrained artificial neural networks (ANNs) to SNNs is an attractive approach that retains robust performance without additional training data and resources. However, while existing conversion methods work well on convolution networks, emerging Transformer models introduce unique mechanisms like self-attention and test-time normalization, leading to non-causal nonlinear interactions unachievable by current SNNs. To address this, we approximate these operations in both temporal and spatial dimensions, thereby providing the first SNN conversion pipeline for Transformers. We propose Universal Group Operators to approximate non-linear operations spatially and a Temporal-Corrective Self-Attention Layer that approximates spike multiplications at inference through an estimation-correction approach. Our algorithm is implemented on a pretrained ViT-B/32 from CLIP, inheriting its zero-shot classification capabilities, while improving control over conversion losses. To our knowledge, this is the first direct training-free conversion of a pretrained Transformer to a purely event-driven SNN, promising for neuromorphic hardware deployment. Codes are available at https://***/ViviaHu/STA. © 2024 12th international conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Modern methods of Searching for the Optimal Assessment of Product Quality

Modern Methods of Searching for the Optimal Assessment of Pr...

引用

international Russian automation conference, RusAutoCon 2022

作者： Pipiay, G. Chernenkaya, L. Peter the Great St.Petersburg Polytechnic University 29 Polytechnic St St. Petersburg194021 Russia

ISBN: (纸本)9783031223105

The modern theory of product quality management, and in particular the subject of qualimetry, contains a large list of models and methods for assessing product quality, and over the past 5 years, this list has only expanded. However, the tools used in the processing of heterogeneous information, in the analysis of product quality and decision-making, are mainly focused on the opinions of experts or on mass production, which limits the functionality of the existing theory of product quality management. Authors proposes modern methods of two-level optimization for solving problems of product quality management. The authors give an example of applying the theory of bilevel optimization to find the optimal estimate of product quality. The example contains an algorithm for solving an analytical problem and the results obtained. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Classification Method of Hot-Rolled Steel Strip Mechanical Properties Dataset Based on Mechanism and Data Mining to Improve Model Accuracy

Classification Method of Hot-Rolled Steel Strip Mechanical P...

引用

Advanced Information, Mechanical Engineering, robotics and automation (AIMERA), IEEE international conference on

作者： Shiwei Zhang Feifei Li Qiang Guo Institute of Engineering Technology University of Science and Technology Beijing Beijing China

ISBN: (数字)9798350343335

ISBN: (纸本)9798350343342

Due to the variety of steel grades, predicting and modeling the mechanical properties of hot-rolled steel strips is challenging. Additionally, the limited availability of certain steel grades prevents smooth model construction. Based on clustering algorithms and metallurgical principles, this study proposes an analysis method that combines mechanisms with big data to analyze the correlation between steel grades. This method enables the merging of steel grade samples with similar patterns, providing an effective data processing approach for modeling steel grades with small sample sizes. It considers both data distribution characteristics and internal patterns. Firstly, the dataset undergoes feature transformation based on solid solution and precipitation strengthening. Then, on the basis of normalization, a hierarchical clustering algorithm is employed to categorize the data, aggregating data with similar distribution characteristics. Subsequently, the t-SNE algorithm and polynomial regression assess cluster internal consistency, facilitating merging of similar clusters. Finally, mechanical property prediction models are constructed for each cluster to validate the method’s effectiveness. The results indicate that after dividing the dataset according to the proposed method, the prediction accuracies of yield strength, tensile strength, and elongation have increased by 2.31%, 1.32%, and 2.28% respectively. This has certain reference value for the industrial application of mechanical property prediction technology.

关键词： Strips Accuracy Merging Clustering algorithms Predictive models Prediction algorithms Mechanical factors Polynomials Partitioning algorithms Steel

来源：评论

学校读者我要写书评

暂无评论

ADAPT: Action-aware Driving Caption Transformer

ADAPT: Action-aware Driving Caption Transformer

引用

IEEE international conference on robotics and automation (ICRA)

作者： Bu Jin Xinyu Liu Yupeng Zheng Pengfei Li Hao Zhao Tong Zhang Yuhang Zheng Guyue Zhou Jingjing Liu Chinese Academy of Sciences Institute of Automation China Institute for AI Industry Research (AIR) Tsinghua University China Xidian University China Department of Computer Science and Technology Tsinghua University China Southern University of Science and Technology China School of Mechanical Engineering and Automation Beihang University China

End-to-end autonomous driving has great potential in the transportation industry. However, the lack of transparency and interpretability of the automatic decision-making process hinders its industrial adoption in practice. There have been some early attempts to use attention maps or cost volume for better model explainability which is difficult for ordinary passengers to understand. To bridge the gap, we propose an end-to-end transformer-based architecture, ADAPT (Action-aware Driving cAPtion Transformer), which provides user-friendly natural language narrations and reasoning for each decision making step of autonomous vehicular control and action. ADAPT jointly trains both the driving caption task and the vehicular control prediction task, through a shared video representation. Experiments on BDD-X (Berkeley DeepDrive eXplanation) dataset demonstrate state-of-the-art performance of the ADAPT framework on both automatic metrics and human evaluation. To illustrate the feasibility of the proposed framework in real-world applications, we build a novel deployable system that takes raw car videos as input and outputs the action narrations and reasoning in real time. The code, models and data are available at https://***/jxbbb/ADAPT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient Multiview Object Detection with Adaptive Action Prediction

Towards Efficient Multiview Object Detection with Adaptive A...

引用

IEEE international conference on robotics and automation (ICRA)

作者： Xu, Qianli Fang, Fen Gauthier, Nicolas Liang, Wenyu Wu, Yan Li, Liyuan Lim, Joo-Hwee ASTAR Inst Infocomm Res Singapore Singapore

ISBN: (纸本)9781728190778

Active vision is a desirable perceptual feature for robots. Existing approaches usually make strong assumptions about the task and environment, thus are less robust and efficient. This study proposes an adaptive view planning approach to boost the efficiency and robustness of active object detection. We formulate the multi-object detection task as an active multiview object detection problem given the initial location of the objects. Next, we propose a novel adaptive action prediction (A2P) method built on a deep Q-learning network with a dueling architecture. The A2P method is able to perform view planning based on visual information of multiple objects;and adjust action ranges according to the task status. Evaluated on the AVD dataset, A2P leads to 21.9% increase in detection accuracy in unfamiliar environments, while improving efficiency by 22.7%. On the T-LESS dataset, multi-object detection boosts efficiency by more than 30% while achieving equivalent detection accuracy.

关键词： Visualization automation Adaptive systems conferences Object detection Prediction methods Robustness

来源：评论

学校读者我要写书评

暂无评论

Celebrating Robustness in Efficient Off-Policy Meta-Reinforcement Learning

Celebrating Robustness in Efficient Off-Policy Meta-Reinforc...

引用

2022 IEEE international conference on Real-Time Computing and robotics, RCAR 2022

作者： Liu, Ziyi Li, Zongyuan Cao, Qianqian Wan, Yuan Guo, Xian NanKai University Inst. of Robotics and Automat. Info. System and the Tianjin Key Laboratory of Intelligent Robotics College of Artificial Intelligence Tianjin300350 China Wuhan University of Technology Department of Mathematical WuHan430070 China

ISBN: (数字)9781665469838

ISBN: (纸本)9781665469838

Deep reinforcement learning algorithms can enable agents to learn policies for complex tasks without expert knowledge. However, the learned policies are typically specialized to one specific task and can not generalize to new tasks. While meta-reinforcement learning (meta-RL) algorithms can enable agents to solve new tasks based on prior experience, most of them build on on-policy reinforcement learning algorithms which require large amounts of samples during meta-Training and do not consider task-specific features across different tasks and thus make it very difficult to train an agent with high performance. To address these challenges, in this paper, we propose an off-policy meta-RL algorithm abbreviated as CRL (Celebrating Robustness Learning) that disentangles task-specific policy parameters by an adapter network to shared low-level parameters, learns a probabilistic latent space to extract universal information across different tasks and perform temporal-extended exploration. Our approach outperforms baseline methods both in sample efficiency and asymptotic performance on several meta-RL benchmarks. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An Iterative Variable Step Error Compensation Approach for Enhancing Robot Trajectory Accuracy

An Iterative Variable Step Error Compensation Approach for E...

引用

automation, robotics and Computer Engineering (ICARCE), international conference on

作者： Chengzhi Wang Sikai Zhao Tianjiao Zheng Hegao Cai Jie Zhao Yanhe Zhu State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin China

ISBN: (数字)9798331529505

ISBN: (纸本)9798331529512

In this paper, an iterative error compensation approach is analyzed and designed to improve trajectory accuracy of industrial robots. Advanced offline programming and robotic machining tasks require high trajectory accuracy of industrial robots, which is significantly affected by parameter inaccuracy, stiffness deformation, backlash, and so on. Such complicated coupling makes it impossible to model each factor separately, thus data-driven direct error compensation is the major solution to improve trajectory accuracy. Previous methods utilize external measurement equipment to obtain tracking error and rely on the error consistency assumption to compensate for the error by modifying the trajectory commands directly. However, such consistency assumption does not hold. Even a minor incremental modification of the initial commands can lead to unexpected influence on the robot's tracking performance, owning to unaccounted factors such as the robot's dynamic stiffness and natural frequency. This paper decomposes trajectory tracking errors based on servo encoder feedback and external laser tracker, and proposes a variable step error compensation scheme to improve tracking performance. Physical experiments are conducted on a standard 6 degree-of-freedom industrial robot to validate the effectiveness of the proposed method. The results of various error compensation approaches are analyzed to draw a possible error correlation model, in order to account for the error inconsistency in the compensation process.

关键词： Accuracy Service robots Trajectory tracking Measurement uncertainty Error compensation Industrial robots Laser modes Trajectory Iterative methods Load modeling

来源：评论

学校读者我要写书评

暂无评论

Deep Interactive Full Transformer Framework for Point Cloud Registration

Deep Interactive Full Transformer Framework for Point Cloud ...

引用

IEEE international conference on robotics and automation (ICRA)

作者： Guangyan Chen Meiling Wang Qingxiang Zhang Li Yuan Tong Liu Yufeng Yue School of Automation Beijing Institute of Technology Beijing China Pecheng Lab School of Electrical and Computer Engineering at Peking University Shenzhen China

Point cloud registration is a crucial technology in the fields of robotics and computer vision. Despite the significant advances in point cloud registration enabled by Transformer-based methods, limitations persist due to indistinct feature extraction, noise sensitivity, and outlier handling. These limitations stem from three factors: (1) the inefficiency of convolutional neural networks (CNNs) to capture global relationships due to their local receptive fields, resulting in extracted features susceptible to noise; (2) the shallow-wide architecture of Transformers, coupled with a lack of positional information, leading to inefficient information interaction and indistinct feature extraction; and (3) the omission of geometrical compatibility leads to ambiguous identification of incorrect correspondences. To overcome these limitations, we propose the Deep Interactive Full Transformer (DIFT) network for point cloud registration, which consists of three key components: (1) a Point Cloud Structure Extractor (PSE) for modeling global relationships and retrieving structural information; (2) a Point Feature Transformer (PFT) for establishing comprehensive associations and directly learning the relative positions between points; and (3) a Geometric Matching-based Correspondence Confidence Evaluation (GMCCE) method for measuring spatial consistency and estimating correspondence confidence. Experimental results on ModelNet40 and 3DMatch datasets demonstrate the superior performance of our proposed method compared to existing state-of-the-art methods. The code for our method is publicly available at https://***/CGuangyan-BIT/DIFT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共500页 << < 386 387 388 389 390 391 392 393 394 395 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：