检索结果-内蒙古大学图书馆

3rd International conference on Computer, Big Data and Artificial Intelligence, ICCBDAI 2022

作者： Fu, Zongli Liu, Zhandong Hu, Chuangye Ding, Nan College of Computer Science and Technology Xinjiang Normal University Urumqi China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment Dalian University of Technology Dalian China

The Q-Learning (QL) algorithm is widely used for path planning. As the scene in which the mobile robot is located becomes complex, the algorithm suffers from the limitations of low convergence speed and long exploration paths. Therefore, a Max Reward-Q-learning (MR-QL) path planning algorithm based on maximum reward is proposed for complex unknown scenarios. The original algorithm's discrete reward function and action selection strategy are improved, and a new reward function is designed to dynamically adjust the reward mechanism to heuristically guide the robot motion. The action selection strategy is also optimized to avoid invalid exploration and improve the algorithm's convergence. Finally, three experimental environments with different complexity are constructed to demonstrate the feasibility of the proposed algorithm. The simulation results show that the MR-QL algorithm is about 50% of the original algorithm in terms of exploration step length and training time, and the convergence speed of the algorithm is better than the original algorithm. © Published under licence by IOP Publishing Ltd.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

SBRDF Hyperspectral Ray Tracing Rendering for 3D Representation Based on Target Surface Material 8th

SBRDF Hyperspectral Ray Tracing Rendering for 3D Representat...

引用

8th International Symposium of space Optical Instruments and Applications, ISSOIA 2023

作者： Yi, Jia Jiang, Huilin Wang, Xiaoyong Ying, Du Graduate School Changchun University of Science and Technology Changchun130022 China School of Physics Changchun University of Science and Technology Changchun130022 China Beijing Institute of Space Mechanics and Electricity Beijing100190 China National and Local Joint Engineering Research Center of Space Optoelectronics Technology Changchun University of Science and Technology Changchun130022 China Fundammontal Science On Space-Ground Laser CommunicationTechnology Laboratory Changchun University of Science and Technology Changchun130022 China Key Laboratory of Education Ministry Optoelectronics Measurement and Control and Optical Shapingba China

ISBN: (纸本)9789819767175

Spectral technology is one of the key means for long-distance non-contact detection and identification of materials. It is an important force for ground-based detection satellites which can play a role in monitoring satellite operation status and safety, and identifying satellite types except for radar. However, for complex targets detected at ultra long distances, the detection object is equivalent to a point source, and the distribution of surface materials is not clear. Usually, material spectral unmixing can only focus on the distribution of planar materials, making it difficult to analyze the target structure. This article uses the spectral BRDF function to construct a hyperspectral ray tracing rendering 3D representation method based on the relationship between illumination, target surface normals, and detection points. It obtains a 3D rendering of a single material on a composite target, laying the foundation for analyzing the structural features of long-distance point target detection. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

An Offline Learning-Based Anti-interference Communication Scheme for UAV Networks 7th

An Offline Learning-Based Anti-interference Communication Sc...

引用

7th International Conference on Wireless Communications, Networking and Applications, WCNA 2023

作者： Tang, Tao Zhao, Runhui Wen, Hong Feng, Xuewei Shi, Weihong Peng, Yulin School of Aeronautics and Astronautics University of Electronic Science and Technology of China Chengdu611731 China Aircraft Swarm Intelligent Sensing and Cooperative Control Key Laboratory of Sichuan Province Chengdu611731 China Sichuan Intelligent IoT Communication Technology Engineering Research Center UESTC Chengdu China

ISBN: (纸本)9789819624089

Unmanned Aerial Vehicles (UAV) face challenges from advanced interference technologies, making them susceptible to malicious node attacks, data interception, and tampering. Traditional anti-interference decisions have limitations, as they cannot adaptively adjust to changes in interference signals. Moreover, anti-interference communication models based on Deep Reinforcement Learning (DRL) require prolonged interactions with the environment, demanding high requirements for anti-interference environments. This paper investigates an offline anti-interference decision based on Decision-Transformers, which can quickly and stably acquire practical anti-interference decision models. Simulation experiments have verified the effectiveness of this algorithm in making anti-interference decisions under AWGN and fading channel conditions. Furthermore, this offline approach can achieve the expected reward targets with fewer training iterations. © The Author(s) 2025.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Thruster Configuration Method for spacecraft Six-Dimensional control

A Thruster Configuration Method for Spacecraft Six-Dimension...

引用

International Symposium on Autonomous Systems (ISAS)

作者： Min Wang Yongchun Xie Yan Su National Key Laboratory of Science and Technology on Space Intelligent Control Beijing Institute of Control Engineering Beijing China

The configuration of spacecraft thrusters directly affects the realization of precise automatic control and propellant consumption. At present, the design of thruster configuration lacks of theoretical guidance. spacecraft carrying out complex space missions such as rendezvous and docking are often equipped with too many thrusters. This paper proposed a theoretical design method of thruster configuration for six-dimensional position and attitude control missions. Firstly, the mathematical description of thruster configuration is introduced. Then, a general design method of thruster configuration for six-dimensional control task is proposed. Finally, simulation of relative position and attitude control of rendezvous and docking task is taken as an example to verify the correctness and validity of the above method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Time-Sensitive Attribute-Oriented Multi-Message Dynamic Scheduling Method in ROS2-RTPS 7

A Time-Sensitive Attribute-Oriented Multi-Message Dynamic Sc...

引用

7th IEEE International Conference on Smart Internet of Things, SmartIoT 2023

作者： Ji, Cheng Hui Hu, Chuang Ye Liu, Zhan Dong Ding, N. College of Computer Science and Technology Xinjiang Normal University Urumqi China Dalian University of Technology Key Laboratory of Intelligent Control and Optimization for Industrial Equipment Dalian China

ISBN: (纸本)9798350316575

With the development of the era of robot 4.0, the application scale and scope of cloud-edge-end fusion robots are expanding, and the robots that transmit data through the network have higher real-Time performance and reliability requirements. ROS2, which uses Data Distribution Service (DDS) as the communication middleware, ensures low latency and high reliability when robotic applications interact with large amounts of data in real-Time over the network. However, the optimization of ROS2 for the simultaneous transmission of diverse data, multi-modal data, and data with different priorities is not perfect. Therefore, based on the theory of hybrid switching system and the transport protocol-RTPS underlying DDS, this paper designs the ROS2-RTPS multi-Type message scheduling model as a hybrid switching system scheduling model including a priority-based subsystem and a time-based subsystem and proposes a time-sensitive attribute-oriented multi-message dynamic scheduling method for ROS2-RTPS. The proposed method considers both the priority and time of different types of messages in ROS2 applications. Finally, the simulation results show that compared with the existing methods, the proposed method can meet the requirements of high-priority data packet transmission, reduce the packet loss rate, and improve the real-Time performance and reliability in the scenarios of discrete data, continuous data, and different priority data transmission. © 2023 IEEE.

关键词： Reliability

来源：评论

学校读者我要写书评

暂无评论

A Unified Framework Integrating Decision Making and Trajectory Planning Based on Spatio-Temporal Voxels for Highway Autonomous Driving

引用

IEEE Transactions on intelligent Transportation Systems 2022年第8期23卷 10365-10379页

作者： Zhang, Ting Song, Wenjie Fu, Mengyin Yang, Yi Tian, Xiaohui Wang, Meiling Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing100081 China Nanjing University of Science and Technology School of Automation Nanjing210014 China

intelligent decision making and efficient trajectory planning are closely related in autonomous driving technology, especially in highway environment full of dynamic interactive traffic participants. This work integrates them into a unified hierarchical framework with long-term behavior planning (LTBP) and short-term dynamic planning (STDP) running in two parallel threads with different horizon, consequently forming a closed-loop maneuver and trajectory planning system that can react to the dynamic environment effectively and efficiently. In LTBP, a novel voxel structure and the 'voxel expansion' algorithm are proposed for the generation of driving corridors in 3D configuration, which involves the prediction states of surrounding vehicles. By using Dijkstra search, the maneuver with minimal cost is determined in form of voxel sequences, then a quadratic programming (QP) problem is constructed for solving the optimal trajectory. And in STDP, another small-scaled QP problem is performed to track or adjust the reference trajectory from LTBP in response to the dynamic obstacles. Meanwhile, a Responsibility-Sensitive Safety (RSS) Checker keeps running at high frequency for real-time feedback to ensure security. Experiments on real data collected in different highway scenarios demonstrate the effectiveness and efficiency of our work. © 2000-2011 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A Survey of Cooperative Path Planning for Multiple UAVs

A Survey of Cooperative Path Planning for Multiple UAVs

引用

International Conference on Autonomous Unmanned Systems, ICAUS 2021

作者： Sun, Wendi Hao, Mingrui Science and Technology on Complex System Control and Intelligent Agent Cooperative Laboratory Beijing100074 China

ISBN: (纸本)9789811694912

Cooperative mission for Multi UAVs has become an important trend. Cooperative path planning is one of the most killing part for the issue. The algorithms can be divided into the following categories, including optimal algorithm, graph-theory-based planning method, heuristic-information-based planning algorithm, swarm intelligence algorithm and neural network algorithm and so on. This paper systematically presents the research status and trend of the application of path planning in the field of multi-UAV cooperative mission and selects a variety of classic and up-to-date algorithms and their variants to promote future research. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Robust Multi-agent Federated Reinforcement Learning for Task Offloading 7th

Robust Multi-agent Federated Reinforcement Learning for Task...

引用

7th International Conference on Wireless Communications, Networking and Applications, WCNA 2023

作者： Yan, Dibao Wang, Yongfeng Hou, Wenjing Song, Huanhuan Wen, Hong Ma, Wendi Sun, Fan School of Aeronautics and Astronautics University of Electronic Science and Technology of China Chengdu611731 China Aircraft Swarm Intelligent Sensing and Cooperative Control Key Laboratory of Sichuan Province Chengdu611731 China Sichuan Intelligent IoT Communication Technology Engineering Research Center UESTC Chengdu China

ISBN: (纸本)9789819624089

With the proliferation of various mobile smart devices, edge computing and computational offloading technologies have emerged as pivotal support mechanisms, enhancing the service quality of these devices. To facilitate the learning of task offloading strategies across diverse and complex scenarios, this study introduces a federated learning strategy algorithm based on multi-agent deep reinforcement learning. This algorithm aims to aggregate the training strategies of multiple edge computing devices, thereby enabling the synthesis of superior task offloading strategies tailored to a wide array of environments while also providing safeguards against malicious nodes. This paper specifically examines the reward inversion attack, illustrating the algorithm’s capability to identify and counteract such malicious threats effectively. Experimental results validate that the proposed algorithm not only robustly defends against these attacks but also adeptly learns the task offloading strategies pertinent to each node. © The Author(s) 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Finite-Time Reconfiguration control for spacecraft Formation with Collision Avoidance

Adaptive Finite-Time Reconfiguration Control for Spacecraft ...

引用

International Conference on Guidance, Navigation and control, ICGNC 2020

作者： Yang, Xicheng Zong, Qun Zhang, Xiuyun Liu, Wenjing School of Electrical Automation and Information Engineering Tianjin University Tianjin300072 China Beijing Institute of Control Engineering Science and Technology on Space Intelligent Control Laboratory Beijing100190 China

ISBN: (纸本)9789811581540

This paper studies formation reconstruction problem for multi-spacecraft with collision avoidance. Firstly, the virtual velocity for desired formation is designed based on the artificial potential field (APF) approach. An adaptive potential field for collision avoidance is proposed to enable the spacecraft to adjust the repulsion force automatically when implementing the collision avoidance strategy. An auxiliary function is introduced to solve the local minimum problem without destabilizing the multiple spacecraft system. Then, we propose a new adaptive finite-time reconfiguration controller, which can achieve fully distributed formation under collision avoidance. The stability of the multiple spacecraft system is proved by Lyapunov analysis. Simulation results verify the proposed strategy can accomplish the target of formation reconstruction successfully. © 2022, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Collision avoidance

来源：评论

学校读者我要写书评

暂无评论

PATH OPTIMIZATION FOR DYNAMIC OBSTACLE AVOIDANCE OF PIONEER ROBOT BASED ON DDPG SMART AGENT

引用

UPB Scientific Bulletin, Series D: Mechanical Engineering 2023年第2期85卷 29-42页

作者： Zheng, Qingchun Peng, Zhi Zhu, Peihao Zhao, Yangyang Ma, Wenpeng Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin University of Technology Tianjin300384 China China School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China

To improve the path efficiency for dynamic obstacle avoidance algorithms of Pioneer robots, this paper proposes an approach to create deep deterministic policy gradient (DDPG) smart agents with recurrent neural networks (RNN) to optimize the path strategy. This approach is realized by training RNN with the backpropagation (BP) algorithm to train the agent. First, the SolidWorks model and obstacle avoidance model of the Pioneer robot is established. The LIDAR sensor is used to obtain environmental information. Further, deep reinforcement learning obstacle avoidance algorithm based on RNN is presented. The dynamic obstacle avoidance path of the Pioneer robot is further simulated in two different virtual robot experiment platform (V-REP) scenarios. The simulation results show that the proposed algorithm shortens the training time by 26.3% compared with the DDPG algorithm. Our proposed scheme can improve the path efficiency for dynamic obstacle avoidance of the Pioneer robot. © 2023, Politechnica University of Bucharest. 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

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：