检索结果-内蒙古大学图书馆

Improved Deep Reinforcement Learning for Efficient Motion control of Autonomous Vehicle with Domain-Centralized Electronic and Electrical Architecture

引用

IEEE Internet of Things Journal 2025年第11期12卷 15620-15635页

作者： Du, Guodong Zou, Yuan Zhang, Xudong Fan, Jie ETH Zurich Institute of Dynamic System and Control Zurich8092 Switzerland Beijing Institute of Technology National Engineering Laboratory for Electric Vehicles School of Mechanical Engineering Beijing China Beijing Institute of Technology National Engineering Laboratory for Electric Vehicles School of Mechanical Engineering Collaborative Innovation Center of Electric Vehicles Beijing China

With the rapid development of intelligent connected vehicles, the domain-based electronic and electrical (E/E) architecture is providing the potential upgrade for the autonomous vehicle. As a representative, the domain-centralized E/E architecture can be installed in the autonomous vehicle which performs its powerful software updates, cabling reduction, and functional integration. For the efficient and stable motion control of autonomous vehicles equipped with domain-centralized E/E architecture, this paper proposes an improved deep reinforcement learning framework based on multi-hops loop delay and accelerated gradient optimization. Firstly, the domain-centralized E/E architecture and motion control problem of autonomous vehicle are modeled, respectively. Then, a multi-hops loop delay analysis is carried out for the E/E architecture to estimate the theoretical boundary value of heterogeneous topology loop delay. Subsequently, the deep reinforcement learning algorithm using modified heuristic experience replay is developed for the motion control of autonomous vehicle equipped with domain-centralized E/E architecture. In the implementation of deep reinforcement learning system, the estimated loop delay value is integrated into the motion controller optimization, and the Nesterov accelerated gradient is introduced and combined with the adaptive moment estimation to improve the optimization effect. Finally, the real-world scenarios and virtual driving environment simulation are applied to evaluate the performance of the improved deep reinforcement learning framework. The results show that the proposed motion control framework achieves better performance and guarantees the stability to the loop delay caused by domain-centralized E/E architecture. © 2014 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A transferable energy management strategy for hybrid electric vehicles via dueling deep deterministic policy gradient

引用

Green Energy and Intelligent Transportation 2022年第2期1卷 75-87页

作者： Jingyi Xu Zirui Li Guodong Du Qi Liu Li Gao Yanan Zhao School of Mechanical Engineering Beijing Institute of Technology100081BeijingChina Department of Transport and Planning Delft University of TechnologyDelft2628 CDthe Netherlands Institute of Dynamic System and Control ETH ZurichSonneggstrasse 38092ZurichSwitzerland

Due to the high mileage and heavy load capabilities of hybrid electric vehicles(HEVs),energy management becomes crucial in improving energy *** avoid the over-dependence on the hard-crafted models,deep reinforcement learning(DRL)is utilized to learn more precise energy management strategies(EMSs),but cannot generalize well to different driving situations in most *** driving cycles are changed,the neural network needs to be retrained,which is a time-consuming and laborious task.A more efficient transferable way is to combine DRL algorithms with transfer learning,which can utilize the knowledge of the driving cycles in other new driving situations,leading to better initial performance and a faster training process to *** this paper,we propose a novel transferable EMS by incorporating the DRL method and dueling network architecture for *** results indicate that the proposed method can generalize well to new driving cycles,with comparably initial performance and faster convergence in the training process.

关键词： Energy management strategies Deep reinforcement learning Dueling network architecture Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Postmastectomy radiotherapy in breast reconstruction:Current controversies and trends

引用

Cancer Innovation 2024年第1期3卷 113-123页

作者： Honghong Zhang Dandan Song Liangxi Xie Ning Zhan Wenjia Xie Jianming Zhang Department of Radiation Oncology Xiang'an Hospital of Xiamen UniversityCancer Research CenterSchool of MedicineXiamen UniversityXiang'anXiamenFujianChina Fujian Provincial Key Laboratory of Intelligent Identification and Control of Complex Dynamic System Quanzhou Institute of Equipment ManufacturingHaixi InstitutesChinese Academy of SciencesQuanzhouFujianChina

Breast cancer is the most common cancer among women *** radiotherapy(PMRT)is an essential component of combined therapy for early-stage,high-risk breast *** reconstruction(BR)is often considered for patients with breast cancer who have undergone *** has been a considerable amount of discussion about the optimal approach to combining PMRT with BR in the treatment of breast *** may increase the risk of complications and prevent good aesthetic results after BR,while BR may increase the complexity of PMRT and the radiation dose to surrounding normal *** purpose of this review is to give a broad overview and summary of the current controversies and trends in PMRT and BR in the context of the most recent literature available.

关键词： breast reconstruction postmastectomy radiotherapy radiotherapy techniques

来源：评论

学校读者我要写书评

暂无评论

A multiobjective flexible job shop scheduling method based on deep reinforcement learning 9

A multiobjective flexible job shop scheduling method based o...

引用

9th International Symposium on Sensors, Mechatronics, and Automation system, ISSMAS 2023

作者： Liu, Weiqi Chen, Hao Zhang, Jianming Wang, Yaozong College of Computer and Cyber Security Fujian Normal University Fujian Fuzhou China Quanzhou Institute of Equipment Manufacturing Haixi Institutes Chinese Academy of Science Fujian Quanzhou China Fujian Provincial Key Laboratory of Intelligent Identification and Control of Complex Dynamic System Fujian Quanzhou China

ISBN: (纸本)9781510672802

To address the multiobjective flexible job shop scheduling problem, this paper establishes a Markov Decision Process for Multiobjective Flexible Job-Shop Scheduling Problem, aiming to minimize makespan and total machine load. Additionally, a multiobjective optimization algorithm base deep reinforcement learning is proposed. Firstly, a multiobjective decomposition strategy is introduced to decompose the problem into a set of subproblems, and graph neural networks with identical structures are employed to represent the priority dispatching rules for each subproblem. Experimental results demonstrate that this approach exhibits better generalization, higher solution quality, and faster convergence compared to previous methods. © 2024 SPIE.

关键词： deep reinforcement learning flexible job shop scheduling problem multi-objective optimization

来源：评论

学校读者我要写书评

暂无评论

Immovable Cultural Relics Preservation Through 3D Reconstruction Using NeRF 5

Immovable Cultural Relics Preservation Through 3D Reconstruc...

引用

5th International Conference on Artificial Intelligence Technologies and Applications, ICAITA 2023

作者： Lai, Zhiqing Lian, Mingchang Chen, Songhang Chen, Guoqing Lai, Xiaoling Quanzhou Institute of Equipment Manufacturing Haixi Institutes Chinese Academy of Sciences Quanzhou362200 China Fujian Provincial Key Laboratory of Intelligent Identification and Control of Complex Dynamic System Quanzhou362200 China Jingwei Space Information Technology Co. Ltd Longyan364030 China

ISBN: (纸本)9781643684840

Urban and rural development poses significant threats to immovable cultural relics, leading to their degradation and potential extinction. To address this issue, 3D reconstruction has emerged as an effective preservation method. However, traditional radar-based techniques require close scanning and extensive manual intervention, limiting their efficiency. This paper explores the application of neural radiance fields (NeRF) for visually reconstructing immovable cultural relics. NeRF employs a fully connected non-convolutional neural network to generate high-quality 3D models from 2D images. The study discusses NeRF's sampling strategy, positional encoding, field architecture, and rendering process. Experimental investigations evaluate the impact of Fourier parameters on reconstruction quality. A case study reconstructing Tianhou Temple using NeRF is presented, comparing it with ContextCapture software. All results demonstrate that NeRF offers an efficient, and cost-saving solution for reconstructing and preserving immovable cultural relics, providing accurate and realistic models with superior structural integrity. © 2024 The Authors.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Recommendation system Based on Adaptive Genetic Algorithm for Enclosed Spaces 6

A Recommendation System Based on Adaptive Genetic Algorithm ...

引用

6th International Symposium on Autonomous systems, ISAS 2023

作者： Guo, Meng Chen, Songhang Wang, Yaozong Fujian Normal University College of Computer and Cyber Security Fuzhou China Fujian Institute of Research on the Structure of Matter Chinese Academy of Sciences Department of Quanzhou Institute of Equipment Manufacturing Quanzhou China Fujian Provincial Key Laboratory of Intelligent Identification and Control of Complex Dynamic System Department of Quanzhou Institute of Equipment Manufacturing Quanzhou China

ISBN: (纸本)9798350316155

Most of the management systems used in common enclosed spaces only have basic functions such as booking and payment, and do not have epidemic prevention and traceability functions. In the COVID-19 pandemic, enclosed scenes, without an epidemic prevention system, clearly increase the risk of cross-contamination of the population, making it a black box that will amplify the severity of the outbreak. In this paper, we develop an intelligent recommendation system designed to coordinate the operation of enclosed spaces and decentralize the new customers to a low-infection risk box. An adaptive genetic algorithm is proposed to achieve optimal allocation of personnel and boxes, which can avoid contact between customers during low peak hours and minimize cross-contact during peak hours. On the one hand, it guarantees the user experience, and on the other hand, it guarantees these enclosed spaces have a high decentralization of crowd density when an epidemic occurs. This greatly reduces the risk of exposure to infection and is of great significance in preventing the spread of the epidemic. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Localization of Pallets in Narrow Aisles for Unmanned Forklifts 3

Localization of Pallets in Narrow Aisles for Unmanned Forkli...

引用

3rd International Symposium on Computer Technology and Information Science, ISCTIS 2023

作者： Sun, Peng Ding, Wei Lian, Mingchang Chen, Hao Quanzhou Institute of Equipment Manufacturing Haixi Institutes Chinese Academy of Sciences Quanzhou362200 China Fujian Science & Technology Innovation Laboratory for Optoelectronic Information of China Fujian Fuzhou350108 China Fujian Provincial Key Laboratory of Intelligent Identification and Control of Complex Dynamic System Quanzhou362200 China

ISBN: (纸本)9798350325386

As the application of unmanned forklifts becomes more and more widespread, logistics scenarios are constantly evolving. This paper focuses on a scenario where the pick-up of pallets perpendicular to forklift in narrow aisles is required. The narrow aisles only allow the forklift to complete the turning, performing pallet localization in front of it will be difficult. We proposes a method for localizing pallets in narrow aisles for unmanned forklifts. By installing the camera at an oblique angle above the pallet, the collected images are uploaded to the image processing system. The YOLOv5 is used to detect the pallet and extract the bounding boxes of the pallet class. Based on the bounding box coordinates, the original image is cropped. Convert the cropped image to grayscale for Canny edge detection, and then perform Hough line detection to extract the right edge of the pallet. This right edge will be compared with the reference pallet edge to obtain the relative localization between the pallet and the unmanned forklift. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Robust Multi-AGV Cooperative Path Planning Method Considering Spatiotemporal Distance 5

A Robust Multi-AGV Cooperative Path Planning Method Consider...

引用

5th International Conference on Computer Engineering and Intelligent control, ICCEIC 2024

作者： Chen, Maolin Chen, Songhang Lian, Mingchang School of Advanced Manufacturing Fuzhou University Quanzhou China Fujian Institute of Research on the Structure of Matter Chinese Academy of Sciences Fuzhou China Fujian Provincial Key Laboratory of Intelligent Identification and Control of Complex Dynamic System Quanzhou China Fujian College University of Chinese Academy of Sciences Fuzhou China Fujian Science & Technology Innovation Laboratory for Optoelectronic Information of China Fuzhou China

ISBN: (纸本)9798331507992

With the widespread application of Automated Guided Vehicles (AGVs) in warehousing and logistics systems, the optimization of multi-AGV path planning has become a critical issue. Current methods primarily focus on minimizing operating time and energy consumption but often overlook spatiotemporal distances between paths, leading to frequent path conflicts and interferences in the system. This paper proposes a neural network based time window estimation model, designed to generate time windows that better align with dynamic environments. Based on this model, we introduce a collaborative multi-AGV path planning method that optimizes spatiotemporal distances between paths. Compared to the Conflict-Based Search (CBS) method, this approach significantly improves the spatiotemporal distance between AGVs during task execution, enhancing the robustness of AGV clusters while only marginally increasing time costs. © 2024 IEEE.

关键词： Automatic guided vehicles

来源：评论

学校读者我要写书评

暂无评论

Deep learning based velocity prediction with consideration of road structure 5

Deep learning based velocity prediction with consideration o...

引用

5th CAA International Conference on Vehicular control and Intelligence, CVCI 2021

作者： Fu, Pengyu Chu, Liang Hou, Zhuoran Xing, Jiaming Gao, Jianbing Guo, Chong Jilin University State Key Lab of Automotive Dynamic Simulation and Control Jilin China University of Leeds Institute of Transportation System Leeds United Kingdom

ISBN: (纸本)9781665408462

Speed prediction of roads is an important part of intelligent transportation system(ITS). Due to the complexity of the traffic environment, the speed of road is not only related to the historical speed of this road, but also has a strong relationship with the adjacent roads. In recent years, with the development and application of various data acquisition devices, a large amount of real-time traffic status information can be obtained. In this paper, we propose a road speed prediction method based on deep learning. Firstly, the method extracts the spatial correlation between the target road and the adjacent roads by convolutional neural networks(CNN). Secondly, long short-term memory(LSTM) is used to obtain the temporal correlation of the data and effectively capture the nonlinear features in the traffic speed sequence. Finally, a multilayer perceptron(MLP) is used to combine the spatio-temporal features. In this paper, the prediction accuracy of the model is evaluated on a real traffic dataset. Compared with traditional statistical methods and advanced deep learning methods, the speed prediction model in this paper obtains a more accurate prediction performance. © 2021 IEEE.

关键词： Speed

来源：评论

学校读者我要写书评

暂无评论

Genetic Algorithm for Block Relocation in Automated Warehouse 5

Genetic Algorithm for Block Relocation in Automated Warehous...

引用

5th International Conference on Artificial Intelligence Technologies and Applications, ICAITA 2023

作者： Wang, Gang Lian, Mingchang Ding, Wei Chen, Songhang Chen, Hao Quanzhou Institute of Equipment Manufacturing Haixi Institutes Chinese Academy of Sciences Quanzhou362200 China College of Computer and Cyber Security Fujian Normal University Fujian Fuzhou350001 China Fujian Science & Technology Innovation Laboratory for Optoelectronic Information of China Fujian Fuzhou350108 China Fujian Provincial Key Laboratory of Intelligent Identification and Control of Complex Dynamic System Quanzhou362200 China

ISBN: (纸本)9781643684840

This paper is based on the research background of block relocation in the automated warehouse and proposes a solution utilizing AGV to relocate goods within the warehouse. Building upon the automated warehouse layout and block relocation process, we formulate a mathematical model to minimize the the number of AGV moving goods and the total travel distance of the AGV. To solve the model, we develop an enhanced genetic algorithm, which zones the block relocation process into multiple stages. Each stage integrates conventional heuristic algorithms to enhance the efficiency of the solution process. The improved genetic algorithm can effectively solve the problem, significantly enhancing the automation level of the warehouse. © 2024 The Authors.

关键词： Genetic algorithms

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：