检索结果-内蒙古大学图书馆

2025 IEEE/SICE International Symposium on System Integration, SII 2025

作者： Sakai, Yu Morioka, Kazuyuki Meiji Univ Graduation School of Advanced Mathematical Sciences Network Design Program Japan

ISBN: (纸本)9798331531614

Data sharing among robots will be an important issue in a future robotic society including many kinds of networked robots. This study proposes a model-sharing system for autonomous mobile robot networks. The model in this study means an action model trained by deep reinforcement learning for mobile robot navigation. The proposed system assumes that the mobile robots in the network can share useful and efficient models among robots. The proposed system uses the Ethereum blockchain as a platform to consider the value and ownership of action models. The owners of the models can receive payments from robots that use the shared models for autonomous navigation. The proposed system finally aims to build a future robotic economic system that includes data generation and accumulation, data sharing, and currency transactions among model owners and user robots. This paper introduces the autonomous navigation method of switching action models according to the navigation environment, the data-sharing system using the Ethereum blockchain, and the flow of autonomous navigation using the proposed system. Simulation results shows that the proposed system can achieve navigation of multiple mobile robots through model and currency transactions among Ethereum network participants. © 2025 IEEE.

关键词： Ethereum

来源：评论

学校读者我要写书评

暂无评论

Autonomous Navigation of a Mobile Robot with a Monocular Camera Using Deep Reinforcement Learning and Semantic Image Segmentation

Autonomous Navigation of a Mobile Robot with a Monocular Cam...

引用

2024 IEEE/SICE International Symposium on System Integration, SII 2024

作者： Tsuruta, Ryuto Morioka, Kazuyuki Meiji Univ Graduation School of Advanced Mathematical Sciences Network Design Program Japan

ISBN: (纸本)9798350312072

Navigation systems for mobile robots using deep reinforcement learning have the potential to achieve autonomous movement without relying on precise environmental maps. This study focuses on autonomous navigation of mobile robots using monocular camera images as input through deep reinforcement learning. Typically, RL models are trained in simulation environments. However, there are gaps between simulation and real-world environments, making it challenging to apply trained RL models to actual robots. This challenge is particularly pronounced when using images as input. Semantic segmentation is employed to address this issue, as it can simplify complex RGB images into segmented images, thereby reducing the gaps between environments. In this study, a RL model to reach their destinations and a semantic segmentation model are acquired for mobile robot navigation. These models are applied to a ROS-based autonomous navigation system. Real-world experiments confirm the successful application of the learned models in actual environments. © 2024 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Pedestrian Avoidance Navigation of Mobile Robots Using Monocular Camera in Urban Environments Based on Deep Reinforcement Learning 50

Pedestrian Avoidance Navigation of Mobile Robots Using Monoc...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Soutome, Kei Morioka, Kazuyuki Network Design Program Graduate School of Advanced Mathematical Sciences Meiji University Tokyo Japan School of Interdisciplinary Mathematical Sciences Meiji University Tokyo Japan

ISBN: (纸本)9781665464543

This study aims to acquire RL models for mobile robots to avoid pedestrians in unknown urban environments using deep reinforcement learning. Training is performed in urban environments in a virtual world created by the Unity game engine. The mobile robot runs using only monocular camera images and positional information, and does not use any external sensors other than the monocular camera, such as a LiDAR. Not only the current step, but also the last 5 steps are utilized for input states in learning. This is so that the robot can learn and predict the pedestrians’ movement. Since this is a challenging learning task for the robots, curriculum learning, in which the difficulty of the learning task increases step by step, is adapted. As a result of the learning, the robot acquired the ability to reach the goal while avoiding pedestrians, even in an unknown urban environment including pedestrians with unknown color appearances. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Economic Platform for Action Model Sharing Based on Blockchain in Mobile Robot networks

Economic Platform for Action Model Sharing Based on Blockcha...

引用

IEEE/SICE International Symposium on System Integration

作者： Yu Sakai Kazuyuki Morioka Graduation School of Advanced Mathematical Sciences Network Design Program Meiji Univ Japan

ISBN: (数字)9798331531614

ISBN: (纸本)9798331531621

关键词： Economics Navigation Simulation System integration Switches Deep reinforcement learning Blockchains Mobile robots Currencies Autonomous robots

来源：评论

学校读者我要写书评

暂无评论

Connection Phase Estimation of Pole Mounted Distribution Transformers by Majority Voting of High-quality Solutions using Only Selected Stages

引用

IEEJ Transactions on Power and Energy 2025年第4期145卷 350-358页

作者： Takahashi, Ryu Fukuyama, Yoshikazu Yoshida, Hotaka Oi, Akihiro Jintsugawa, Toru Fujimoto, Hisashi Network Design Program Graduate School of Advanced Mathematical Sciences Meiji University 4-21-1 Nakano Nakano-ku Tokyo164-8525 Japan R&D Headquarters Fuji Electric Co. Ltd. No.1 Fuji-machi Hino191-8502 Japan

This paper proposes connection phase estimation of pole mounted distribution transformers by majority voting of high-quality solutions using sampled stages. The essential challenge of the connection phase estimation of pole mounted distribution transformers problem is that the correct connection phase combination and the combination with the best objective function value do not match because of using inconsistent data. In order to solve the challenge, the proposed method utilizes the concept of majority voting of ensemble learning andtheproximate optimality principle. The proposed method is verified to estimate the connection phase accurately and specify pole mounted distribution transformers with insufficient estimation accuracy using a distribution system model. © 2025 The Institute of Electrical Engineers of Japan.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

Autonomous Navigation of a Mobile Robot with a Monocular Camera Using Deep Reinforcement Learning and Semantic Image Segmentation

Autonomous Navigation of a Mobile Robot with a Monocular Cam...

引用

IEEE/SICE International Symposium on System Integration

作者： Ryuto Tsuruta Kazuyuki Morioka Network Design Program Meiji Univ Graduation School of Advanced Mathematical Sciences Japan

关键词：

来源：评论

学校读者我要写书评

暂无评论

Live Demonstration: Low Cost AES-256 Circuit design and Application 20

Live Demonstration: Low Cost AES-256 Circuit Design and Appl...

引用

20th Asia-Pacific Conference on Circuits and Systems

作者： Chuang, Chia-Chou Jheng, Yu-Lun Huang, Chien Huang, Lu-Ying Chen, Pei-Yin Lee, Narn-Yih Natl Cheng Kung Univ Acad Innovat Semicond & Sustainable Mfg Program Integrated Circuit Design Tainan 701 Taiwan Natl Cheng Kung Univ Dept Comp Sci & Informat Engn Tainan 70101 Taiwan Natl Cheng Kung Univ Network & Informat Secur Div Comp & Network Ctr Tainan 70101 Taiwan

ISBN: (纸本)9798350378788;9798350378771

With the advent of the post-quantum era, the most worrying issue is information security. Quantum computers have been able to crack common asymmetric cryptography, such as RSA, DSA, ECC, etc, by Shor's Algorithm. In terms of common symmetric-key algorithm, Grover's algorithm can reduce the difficulty of brute-force cracking from N attempt to √N [1], which decreases the security. In other words, the symmetric-key algorithm doubling the key size can effectively resist quantum attacks. Hence, AES-256 will be a worthwhile research topic in the future. © 2024 IEEE.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Applications in integrated intelligent infrastructures

引用

JOURNAL OF AMBIENT INTELLIGENCE AND SMART ENVIRONMENTS 2023年第3期15卷 209-210页

作者： Gomez, Carles Bannan, Brenda Fleury, Anthony Univ Politecn Cataluna Network Engn Dept Barcelona Spain George Mason Univ Coll Educ & Human Dev Learning Technol Design Res Program Fairfax VA USA IMT Nord Europe Ctr Digital Syst Douai France

来源：评论

学校读者我要写书评

暂无评论

Pedestrian Avoidance Navigation of Mobile Robots Using Monocular Camera in Urban Environments Based on Deep Reinforcement Learning

Pedestrian Avoidance Navigation of Mobile Robots Using Monoc...

引用

Annual Conference of Industrial Electronics Society

作者： Kei Soutome Kazuyuki Morioka Network Design Program Graduate School of Advanced Mathematical Sciences Meiji University Tokyo Japan School of Interdisciplinary Mathematical Sciences Meiji University Tokyo Japan

ISBN: (数字)9781665464543

ISBN: (纸本)9781665464550

关键词： Training Adaptation models Pedestrians Navigation Service robots Urban areas Robot vision systems Deep reinforcement learning Cameras Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Impact of a virtual environment on the learning effectiveness, motivation, cognitive load, and group self-efficacy of elementary school students in collaborative learning

引用

ETR&D-EDUCATIONAL TECHNOLOGY RESEARCH AND DEVELOPMENT 2022年第6期70卷 2145-2169页

作者： Cho, I-Hsuan Yeo, Jun-Hui Hwang, Gwo-Haur Yang, Hsi-Hsun Natl Yunlin Univ Sci & Technol Dept Digital Media Design Touliu Yunlin Taiwan NetEase Network Co Ltd Hangzhou Zhejiang Peoples R China Natl Yunlin Univ Sci & Technol Bachelor Program Ind Technol Touliu Yunlin Taiwan

Collaborative learning helps to construct a learning situation in which students solve problems together, and their learning effectiveness is promoted. However, collaborative learning often has the problem of unequal participation of learners. Therefore, this study combines the collaborative learning mode of the virtual environment of digital games and applies it to an elementary school art course, in the hope of solving the problems in collaborative learning. Using a quasi-experimental research design, students were divided into a virtual group and a real group to compare whether the different styles of collaborative learning would affect their learning. Participants in this study were 83 fourth-grade students from an elementary school. This study found that the learning effectiveness and motivation of the students in the virtual group were significantly higher than those of the students in the real group. The reason is that the virtual group learned in an active virtual environment in which the students' shared solutions with their partners, and could even manipulate their virtual avatar to give peer guidance, triggering learning motivation to promote inter-group interaction. However, students in the real group were worried about making the classroom dirty, and had to invest more effort. They gave priority to their favorite specific colors, and completed the mixed-color questions independently, with less collaboration and communication, making it difficult for them to correctly answer the questions that their peers solved independently during the learning process. It is suggested that virtual avatars can be introduced in actual teaching to improve student interaction and attention.

关键词： Virtual environment Learning effectiveness Learning motivation Cognitive load Group self-efficacy Collaborative learning

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：