检索结果-南通市图书馆

基于policy gradient强化学习的无人车控制方法研究

在线全文

学校读者我要写书评

暂无评论

基于Policy Gradient强化学习的无人车控制方法研究

作者：张鑫垚吉林大学

学位级别：硕士

自动驾驶技术的开发将会极大地有利于行车安全,减少交通事故的发生,因此在当代,自动驾驶的实现已经势在必行。由于基于模型的控制算法无法适应多变的行车环境,因此能够与环境交互,不断学习环境的强化学习算法将会在智能车领域扮演极为... 详细信息

自动驾驶技术的开发将会极大地有利于行车安全,减少交通事故的发生,因此在当代,自动驾驶的实现已经势在必行。由于基于模型的控制算法无法适应多变的行车环境,因此能够与环境交互,不断学习环境的强化学习算法将会在智能车领域扮演极为重要的角色,但是由于强化学习算法存在一定的失效问题,这将有可能导致严重的交通事故,所以减少强化学习算法在智能车应用中的失效,提高行车安全将是未来智能车研究中不可或缺的部分。本文以自动驾驶汽车为研究对象,主要研究了针对自动驾驶汽车从实时场景到动作输出的端到端控制算法和对当前场景的可行驶区域识别算法,然后对可行驶区域是否包含车辆受控后的下一时刻的预估位置(或车辆在执行当前动作后的下一时刻是否在可行驶区域之内)进行了分析验证,最终使两种算法之间互相监督验证以提高自动驾驶汽车的行驶安全性。本文的研究工作主要有以下几点:研究了可行驶区域识别算法PSPnet。搭建可行驶区域识别算法的网络结构,基于BDD100k开源数据集和Carl场景的自建数据集将其标签文件.json转化为神经网络可以识别的标签图片,与原始场景图片作为一组对网络结构进行训练,提升神经网络对自动驾驶汽车场景的可行驶区域的识别能力,然后在Carla环境中通过场景图片对可行驶区域识别的效果进行验证。研究了适应于自动驾驶汽车的端到端控制算法policy gradient。根据强化学习算法policy gradient的基本原理和自动驾驶汽车所处的Carla环境以及Carla中车辆控制的特性在Python中编写policy gradient算法,以实现从摄像头的实时场景到动作输出的端到端控制,policy gradient算法和Carla仿真环境之间通过TCP交互采集环境数据,并与网络输出值和动作在场景下的回报值放入策略网络进行训练,不断提升无人车在环境之中的表现。设计了多个场景的仿真验证,对自动驾驶汽车的端到端算法在不同场景下对自动驾驶汽车的控制表现进行了评估,通过Python和Carla的脚本配置所需求的车辆模型和传感器模型,在不同的仿真交通场景下进行试验,并通过车辆的速度、加速度、角速度和轨迹等与端到端算法policy gradient回报函数设计的匹配性进行了分析评估,验证了本文所编写的自动驾驶汽车的端到端控制算法的有效性,最后通过在对控制算法整个训练过程中可行驶区域识别算法的正确预警率和误警率的变化曲线验证了可行驶区域识别与自动驾驶汽车的端到端控制算法可以相互监督以提高行驶安全的方案的有效性。

关键词： PSPnet policy gradient 强化学习语义分割

Reinforcement learning-based cost-sensitive classifier for imbalanced fault classification

同方学位论文库评论

在线全文

同方学位论文库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2023年第11期66卷 113-126页

作者： Xinmin ZHANG Saite FAN Zhihuan SONG State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University

Fault classification plays a crucial role in the industrial process monitoring domain. In the datasets collected from real-life industrial processes, the data distribution is usually imbalanced. The datasets contain a large amount of normal data(majority) and only a small amount of faulty data(minority); this phenomenon is also known as the imbalanced fault classification problem. To solve the imbalanced fault classification problem, a novel reinforcement learning(RL)-based cost-sensitive classifier(RLCC) based on policy gradient is proposed in this paper. In RLCC, a novel cost-sensitive learning strategy based on policy gradient and the actor-critic of RL is developed. The novel cost-sensitive learning strategy can adaptively learn the cost matrix and dynamically yield the sample weights. In addition, RLCC uses a newly designed reward to train the sample weight learner and classifier using an alternating iterative approach. The alternating iterative approach makes RLCC highly flexible and effective in solving the imbalanced fault classification problem.The effectiveness and practicability of the proposed RLCC method are verified through its application in a real-world dataset and an industrial process benchmark.

关键词： imbalanced fault classification fault diagnosis industrial process monitoring deep reinforcement learning cost-sensitive learning policy gradient sample weights

An Initial Residual Stress Inference Method by Incorporating Monitoring Data and Mechanism Model

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Mechanical Engineering 2022年第5期35卷 47-65页

作者： Shuguo Wang Yingguang Li Changqing Liu Zhiwei Zhao Nanjing University of Aeronautics and Astronautics Nanjing 210016China

Initial residual stress is the main reason causing machining deformation of the workpiece,which has been deemed as one of the most important aspects of machining quality issues.The inference of the distribution of initial residual stress inside the blank has significant meaning for machining deformation control.Due to the principle error of existing residual stress detection methods,there are still challenges in practical applications.Aiming at the detection problem of the initial residual stress field,an initial residual stress inference method by incorporating monitoring data and mechanism model is proposed in this paper.Monitoring data during machining process is used to represent the macroscopic characterization of the unbalanced residual stress,and the finite element numerical model is used as the mechanism model so as to solve the problem that the analytic mechanism model is difficult to establish;the policy gradient approach is introduced to solve the gradient descent problem of the combination of learning model and mechanism model.Finally,the initial residual stress field is obtained through iterative calculation based on the fusing method of monitoring data and mechanism model.Verification results show that the proposed inference method of initial residual stress field can accurately and effectively reflect the machining deformation in the actual machining process.

关键词： Initial residual stress Inference Monitoring data Mechanism model policy gradient

Deep reinforcement learning based task offloading in blockchain enabled smart city

在线全文

学校读者我要写书评

暂无评论

High Technology Letters 2023年第3期29卷 295-304页

作者：金凯琦 WU Wenjun GAO Yang YIN Yufen SI Pengbo Faculty of Information Technology Beijing University of TechnologyBeijing 100124P.R.China

With the expansion of cities and emerging complicated application,smart city has become an in-telligent management mechanism.In order to guarantee the information security and quality of service(QoS)of the Internet of Thing(IoT)devices in the smart city,a mobile edge computing(MEC)en-abled blockchain system is considered as the smart city scenario where the offloading process of com-puting tasks is a key aspect infecting the system performance in terms of service profit and latency.The task offloading process is formulated as a Markov decision process(MDP)and the optimal goal is the cumulative profit for the offloading nodes considering task profit and service latency cost,under the restriction of system timeout as well as processing resource.Then,a policy gradient based task of-floading(PG-TO)algorithm is proposed to solve the optimization problem.Finally,the numerical re-sult shows that the proposed PG-TO has better performance than the comparison algorithm,and the system performance as well as QoS is analyzed respectively.The testing result indicates that the pro-posed method has good generalization.

关键词： mobile edge computing(MEC) blockchain policy gradient task offloading

Admission Control with Elastic QoS for Video on Demand Systems

在线全文

学校读者我要写书评

暂无评论

International Journal of Automation and computing 2012年第5期9卷 467-473页

作者： Fu-Shou Lin 1 Bao-Qun Yin 1,2 Jing Huang 1 Xu-Min Wu 1 1 Key Lab of Anhui Network Communication System and Control, University of Science and Technology of China, Hefei 230027, China 2 National Network New Media Engineering Research Center, Institute of Acoustics, Chinese Academy of Science, Beijing 100190, China Key Lab of Anhui Network Communication System and Control University of Science and Technology of China Hefei China National Network New Media Engineering Research Center Institute of Acoustics Chinese Academy of Science Beijing China

In network service systems, satisfying quality of service (QoS) is one of the main objectives. Admission control and resource allocation strategy can be used to guarantee the QoS requirement. Based on partially observable Markov decision processes (POMDPs), this paper proposes a novel admission control model for video on demand (VOD) service systems with elastic QoS. Elastic QoS is also considered in resource allocation strategy. policy gradient algorithm is often available to find the solution of POMDP problems, with a satisfactory convergence rate. Through numerical examples, it can be shown that the proposed admission control strategy has better performance than complete admission control strategy.

关键词： Partially observable Markov decision processes (POMDPs) admission control resource allocation elastic quality of service (QoS) policy gradient

Generative Adversarial Network Based Status Generation Simulation Approach

在线全文

学校读者我要写书评

暂无评论

国际计算机前沿大会会议论文集 2021年第1期 246-255页

作者： Zhiru Chen Zhi Zhang Xi Zhao Liang Guo State Grid ShanDong Marketing Service Center(Metrology Center) Jinan 250000ShandongChina Measuring Center State Grid Shandong Electric Power Research InstituteJinan 250000ShandongChina State Grid Shandong Electric Power Company Jinan 250000ShandongChina

The generative adversarial network based methods have beenapplied in many fields for simulation data generation. For power equipment,due to the combined influences of multiple factors, how to generatereasonable simulation data that meets specific requirements has becomea challenge. This paper proposes a power equipment status generationapproach based on generative confrontation network. This approach considersthe changing factors of power equipment and takes it as the conditionaldistribution of simulation data during training. The proposedapproach is applied to the status generation of power equipment, andthe rationality and effectiveness of the approach are verified throughexperiments.

关键词： Generative adversarial network Simulation data policy gradient

GLEU-guided Multi-Resolution Network for Short Text Conversation

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

GLEU-guided Multi-Resolution Network for Short Text Conversa...