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

44 篇 会议
27 篇 期刊文献

馆藏范围

71 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

47 篇 工学
- 33 篇 控制科学与工程
- 29 篇 计算机科学与技术...
- 29 篇 软件工程
- 13 篇 机械工程
- 9 篇 交通运输工程
- 6 篇 林业工程
- 6 篇 生物工程
- 5 篇 农业工程
- 4 篇 光学工程
- 2 篇 船舶与海洋工程
- 1 篇 仪器科学与技术
- 1 篇 动力工程及工程热...
- 1 篇 化学工程与技术
- 1 篇 纺织科学与工程
- 1 篇 生物医学工程（可授...
18 篇 理学
- 7 篇 物理学
- 6 篇 生物学
- 5 篇 数学
- 2 篇 统计学（可授理学、...
- 1 篇 系统科学
13 篇 农学
- 13 篇 作物学
6 篇 管理学
- 6 篇 管理科学与工程(可...
- 1 篇 工商管理
2 篇 医学
- 1 篇 临床医学

主题

12 篇 reinforcement le...
9 篇 fruits
5 篇 pallets
5 篇 robots
4 篇 automation
3 篇 cameras
3 篇 intelligent robo...
3 篇 machine vision
3 篇 robot vision sys...
2 篇 orchards
2 篇 generative adver...
2 篇 manuals
2 篇 lighting
2 篇 robot sensing sy...
2 篇 feature extracti...
2 篇 random forests
2 篇 computer aided s...
2 篇 manufacturing
2 篇 performance eval...
2 篇 anthropomorphic ...

机构

41 篇 centre for autom...
8 篇 centre for autom...
8 篇 new dexterity re...
8 篇 school of engine...
5 篇 centre for autom...
4 篇 bremworth ltd au...
4 篇 the centre for a...
3 篇 the school of en...
2 篇 computer graphic...
2 篇 centre for artif...
2 篇 centre for autom...
2 篇 the university o...
2 篇 department of ch...
2 篇 australian centr...
2 篇 school of comput...
2 篇 information tech...
2 篇 school of automa...
2 篇 school of scienc...
2 篇 department of co...
2 篇 key laboratory o...

作者

31 篇 williams henry
22 篇 nejati mahla
22 篇 gee trevor
15 篇 ahn ho seok
14 篇 macdonald bruce
12 篇 macdonald bruce ...
11 篇 henry williams
9 篇 xing yuning
9 篇 valencia david
8 篇 mike duke
8 篇 lim jongyoon
7 篇 bruce a. macdona...
7 篇 liarokapis minas
6 篇 hin lim
6 篇 ben mcguinness
5 篇 qureshi ans
5 篇 smith david
5 篇 david smith
5 篇 bruce macdonald
5 篇 trevor gee

语言

64 篇 英文
7 篇 其他

检索条件"机构=The Centre for Automation and Robotic Engineering Science"

共 71 条记录，以下是11-20 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：

On the Efficient Learning and Execution of Real-World, Dexterous In-Hand Manipulation Tasks with Phased Behaviour-Guiding Reward

On the Efficient Learning and Execution of Real-World, Dexte...

引用

2024 Australasian Conference on robotics and automation, ACRA 2024

作者： Xing, Yuning van Rijnsoever, Koen Valencia, David Gee, Trevor MacDonald, Bruce A. Liarokapis, Minas Williams, Henry Centre for Automation and Robotic Engineering Science The University of Auckland New Zealand New Dexterity research group The University of Auckland New Zealand

Reinforcement Learning (RL) training typically occurs in simulations using standardized, simple reward functions, often requiring millions of steps before a task is learned. However, due to physical limitations and resource constraints, such extensive training is impractical for real-world applications, especially for the execution of dexterous manipulation tasks. Additionally, training in simulation and successfully transferring the model to real-world scenarios remains a significant challenge due to the sim-to-real gap. This paper addresses these challenges by introducing a Phased Behavior-Guiding Reward Function to enhance the efficiency of RL in learning and executing complex, real-world dexterous, in-hand manipulation tasks. The proposed approach uses evolving rewards across distinct phases, allowing the agent to learn incrementally and produces a cohesive policy for the entire task. Experiments conducted on a low-cost, physical robotic manipulation testbed demonstrate that the phased reward function achieves faster learning and higher task success rates, outperforming single-phased and traditional distance-based reward functions. These results suggest that the proposed method could be a sample-efficient and scalable solution for complex real-world robotic applications. © 2024 Australasian robotics and automation Association. All rights reserved.

关键词： Robot applications

来源：评论

学校读者我要写书评

暂无评论

Development of a 3D, High-Fidelity Simulator for Autonomous Racing of F1Tenth Cars

Development of a 3D, High-Fidelity Simulator for Autonomous ...

引用

2024 Australasian Conference on robotics and automation, ACRA 2024

作者： Steiner, Emily Pama, Afereti Zhou, Futian Lee, Kyla Liarokapis, Minas Williams, Henry Centre for Automation and Robotic Engineering Science The University of Auckland New Zealand New Dexterity research group The University of Auckland New Zealand

Autonomous racing is a new field of research stemming from recent developments in autonomous vehicles. Autonomous racing competitions, such as F1Tenth, provide researchers with opportunities to push the limits of autonomous capabilities. However, it is often impossible or unsuitable to develop and test autonomous racecars solely in the real world, due to time constraints, track availability, and crash risks. Therefore, simulators provide platforms for low-risk, low-cost development and testing. Simulators are often custom-built for a given racing competition, vehicle style, or track environment. Currently, the F1Tenth competition lacks a high-fidelity 3D simulator which allows for seamless transfer between simulation and reality. This research developed such a simulator for the F1Tenth competition. The developed simulator was then used for training end-to-end reinforcement learning algorithms on F1Tenth vehicles. The successful deployment of these algorithms in simulation racing and real racing demonstrates the usefulness and high fidelity of the built simulator. © 2024 Australasian robotics and automation Association. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Reinforcement Learning Methods for Dexterous robotic Manipulation with a Three-Fingered Gripper

Benchmarking Reinforcement Learning Methods for Dexterous Ro...

引用

2024 Australasian Conference on robotics and automation, ACRA 2024

作者： Cutler, Elizabeth Xing, Yuning Cui, Tony Zhou, Brendan van Rijnsoever, Koen Hart, Ben Valencia, David Ong, Lee Violet C. Gee, Trevor Liarokapis, Minas Williams, Henry Centre for Automation and Robotic Engineering Science The University of Auckland New Zealand New Dexterity research group The University of Auckland New Zealand

Reinforcement Learning (RL) training is predominantly conducted in cost-effective and controlled simulation environments. However, the transfer of these trained models to real-world tasks often presents unavoidable challenges. This research explores the direct training of RL algorithms in controlled yet realistic real-world settings for the execution of dexterous manipulation. The benchmarking results of three RL algorithms trained on intricate in-hand manipulation tasks within practical, real-world contexts are presented. Our study not only demonstrates the practicality of RL training in authentic real-world scenarios, facilitating direct real-world applications, but also provides insights into the associated challenges and considerations. Additionally, our experiences with the employed experimental methods are shared, with the aim of empowering and engaging fellow researchers and practitioners in this dynamic field of robotics. © 2024 Australasian robotics and automation Association. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Textile Anomaly Detection: Evaluation of the State-of-the-Art for Automated Quality Inspection of Carpet

Textile Anomaly Detection: Evaluation of the State-of-the-Ar...

引用

2023 Australasian Conference on robotics and automation, ACRA 2023

作者： Forsberg, Briony Williams, Henry MacDonald, Bruce Chen, Tracy Hulse, Kirstine Centre for Automation and Robotic Engineering Science The University of Auckland New Zealand Bremworth Ltd Auckland New Zealand

In this study, state-of-the-art unsupervised detection models were evaluated for the purpose of automated anomaly inspection of wool carpets. A custom dataset of four unique types of carpet textures was created to thoroughly test the models and their robustness in detecting subtle anomalies in complex textures. Due to the requirements of an inline inspection system in a manufacturing use case, the metrics of importance in this study were accuracy in detecting anomalous areas, the number of false detections, and the inference times of each model for real-time performance. Of the evaluated models, the student-teacher network based methods were found on average to yield the highest detection accuracy and lowest false detection rates. When trained on a multi-class dataset the models were found to yield comparable if not better results than single-class training. Finally, in terms of detection speed, with exception to the generative model, all other evaluated models were found to have comparable inference times on a GPU, with an average of 0.16s per image. On a CPU, most of these models typically produced results between 1.5 to 2 times the respective GPU inference times. © 2023 Australasian robotics and automation Association. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

The Effect of Dimensional Parameters on the Performance of DDMRs 19

The Effect of Dimensional Parameters on the Performance of D...

引用

19th IEEE International Conference on automation science and engineering, CASE 2023

作者： Tattersall, Andrew McGuinness, Benjamin Lim, Hin Au, Chi Kit Williams, Henry Duke, Mike The School of Engineering University of Waikato Hamilton New Zealand The Centre for Automation and Robotic Engineering Science The University of Auckland New Zealand

ISBN: (纸本)9798350320695

Differential drive mobile robots (DDMRs) are often used in automation research because they are simple mechanically, and low cost as they only require two motors to drive and steer. Work to date has focused on control, with little done to optimise these vehicles in terms of dimensional parameters such as centre of mass position, track width, wheel base and caster dimensions. This paper presents a dynamic model of a DDMR and the dimensional sensitivity of peak drive/braking force, energy consumption, and chassis forces is assessed. The model is applied to a range of trajectories typical in an agricultural setting. Results show that these are all sensitive to vehicle dimensions to different degrees. Energy consumption showed the least sensitivity, while drive forces were found to be significantly influenced, for example, increasing the caster trail from 0.13 to 0.33 m decreased peak drive force by 56%. Optimising dimensional parameters in DDMRs can contribute to more economically viable automated solutions through increased efficency and reduced expense. © 2023 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Redefining Selective Blueberry Harvesting - Localised Shaking with Minimal Damage

Redefining Selective Blueberry Harvesting - Localised Shakin...

引用

2023 Australasian Conference on robotics and automation, ACRA 2023

作者： Sim, Alicia McGuinness, Ben Lim, Shen Hin Williams, Henry Duke, Mike the School of Engineering University of Waikato Hamilton New Zealand the Centre for Automation and Robotic Engineering Science The University of Auckland New Zealand

This paper presents a harvesting system that utilises localised shaking combined with a multi-layer soft catchment device for harvesting ripe blueberries. This paper also introduces a harvesting evaluation process to quantify the efficiency of the developed system. During preliminary testing within a commercial blueberry farm, the device showed a harvesting efficiency of 64% for Eureka and Masena varieties. This is lower in efficiency than existing manual harvesting methods into buckets, which were between 82.7 and 89.3 %. However, the device has not been optimised, and testing was limited. The devices show promise;further developments and trials are required to optimise the shaking frequency to maximise harvest efficiency and determine the harvesting rates. © 2023 Australasian robotics and automation Association. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Pallet Detection from Synthetic Data using Game Engines

Pallet Detection from Synthetic Data using Game Engines

引用

2022 Australasian Conference on robotics and automation, ACRA 2022

作者： Naidoo, Jouveer Bates, Nicholas Gee, Trevor Nejati, Mahla Centre for Automation and Robotic Engineering Science University of Auckland New Zealand

ISBN: (纸本)9781713866480

This research sets out to assess the viability of using game engines to generate synthetic training data for machine learning in the context of pallet segmentation. Using synthetic data has been proven in prior research to be a viable means of training neural networks, and saves hours of manual labour due to the reduced need for manual image annotation. Machine vision for pallet detection can benefit from synthetic data as the industry increases the development of autonomous warehousing technologies. As per our methodology, we developed a tool capable of automatically generating large amounts of annotated training data from 3D models at pixel-perfect accuracy and a much faster rate than manual approaches. Regarding image segmentation, a Mask R-CNN pipeline was used, which achieved an AP50 of 86% for individual pallets. © 2022 Australasian robotics and automation Association. All rights reserved.

关键词： Pallets

来源：评论

学校读者我要写书评

暂无评论

Racing Towards Reinforcement Learning based control of an Autonomous Formula SAE Car

Racing Towards Reinforcement Learning based control of an Au...

引用

2022 Australasian Conference on robotics and automation, ACRA 2022

作者： Salvaji, Aakaash Taylor, Harry Valencia, David Gee, Trevor Williams, Henry Centre for Automation and Robotic Engineering Science University of Auckland New Zealand

ISBN: (纸本)9781713866480

With the rising popularity of autonomous navigation research, Formula Student (FS) events are introducing a Driverless Vehicle (DV) category to their event list. This paper presents the initial investigation into utilising Deep Reinforcement Learning (RL) for end-to-end control of an autonomous FS race car for these competitions. We train two state-of-the-art RL algorithms in simulation on tracks analogous to the full-scale design on a Turtlebot2 platform. The results demonstrate that our approach can successfully learn to race in simulation and then transfer to a real-world racetrack on the physical platform. Finally, we provide insights into the limitations of the presented approach and guidance into the future directions for applying RL toward full-scale autonomous FS racing. © 2022 Australasian robotics and automation Association. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Visual based Tomato Size Measurement System for an Indoor Farming Environment

Visual based Tomato Size Measurement System for an Indoor Fa...

引用

2022 Australasian Conference on robotics and automation, ACRA 2022

作者： Kweon, Andy Hu, Vishnu Lim, Jong Yoon Gee, Trevor Liu, Edmond Williams, Henry MacDonald, Bruce A. Nejati, Mahla Sa, Inkyu Ahn, Ho Seok Centre for Automation and Robotic Engineering Science University of Auckland New Zealand

ISBN: (纸本)9781713866480

As technology progresses, smart automated systems will serve an increasingly important role in the agricultural industry. Current existing vision systems for yield estimation face difficulties in occlusion and scalability as they utilize a camera system that is large and expensive, which are unsuitable for orchard environments. To overcome these problems, this paper presents a size measurement method combining a machine learning model and depth images captured from three low cost RGBD cameras to detect and measure the height and width of tomatoes. The performance of the presented system is evaluated on a lab environment with real tomato fruits and fake leaves to simulate occlusion in the real farm environment. To improve accuracy by addressing fruit occlusion, our three-camera system was able to achieve a height measurement accuracy of 0.9114 and a width accuracy of 0.9443. © 2022 Australasian robotics and automation Association. All rights reserved.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Look how they have grown: Non-destructive Leaf Detection and Size Estimation of Tomato Plants for 3D Growth Monitoring

Look how they have grown: Non-destructive Leaf Detection and...

引用

2022 Australasian Conference on robotics and automation, ACRA 2022

作者： Xing, Yuning Pham, Dexter Williams, Henry Smith, David Ahn, Ho Seok Lim, JongYoon MacDonald, Bruce A. Nejati, Mahla Centre for Automation and Robotic Engineering Science University of Auckland New Zealand

ISBN: (纸本)9781713866480

Smart farming is a growing field as technology advances. Plant characteristics are crucial indicators for monitoring plant growth. Research has been done to estimate characteristics like leaf area index, leaf disease, and plant height. However, few methods have been applied to non-destructive measurements of leaf size. In this paper, an automated nondestructive imaged-based measuring system is presented, which uses 2D and 3D data obtained using a Zivid 3D camera, creating 3D virtual representations (digital twins) of the tomato plants. Leaves are detected from corresponding 2D RGB images and mapped to their 3D point cloud using the detected leaf masks, which then pass the leaf point cloud to the plane fitting algorithm to extract the leaf size to provide data for growth monitoring. The performance of the measurement platform has been measured through a comprehensive trial on real-world tomato plants with quantified performance metrics compared to ground truth measurements. Three tomato leaf and height datasets (including 50+ 3D point cloud files of tomato plants) were collected and open sourced in this project. The proposed leaf size estimation method demonstrates an RMSE value of 4.47mm and an R2 value of 0.87. The overall measurement system (leaf detection and size estimation algorithms combine) delivers an RMSE value of 8.13mm and an R2 value of 0.899. © 2022 Australasian robotics and automation Association. All rights reserved.

关键词： Fruits

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8页 << < 1 2 3 4 5 6 7 8 > >>

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：