检索结果-内蒙古大学图书馆

42nd Chinese control Conference, CCC 2023

作者： Zhou, Tongyuehao Zhang, Monan Li, Yichen Zhou, Wei Yu, Wenbin Shanghai Jiao Tong University Department of Automation Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China PLA 91550 Dalian116023 China

ISBN: (纸本)9789887581543

In image fusion, the desirable fused image is to obtain advantage information from different images of the same scene. As for the fusion of the infrared image and the visible image that have distinct features, this paper proposes an adaptive multi-weight fusion based on multi-scale transformation. This method designs different weight matrices according to the characteristics of the infrared image and the visible image. It can also adaptively adjusts the weight size according to the scene. Based on the difference of information entropy between infrared images and visible images, the method of this paper can keep the important information as much as possible. Experimental results prove the method of this paper is fast and effective. It also has certain superiority compared with other methods. © 2023 Technical Committee on control Theory, Chinese Association of automation.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Behavioral control for Nonlinear Autonomous system

引用

IEEE/CAA Journal of Automatica Sinica 2022年第9期9卷 1561-1573页

作者： Zhenyi Zhang Zhibin Mo Yutao Chen Jie Huang the College of Electrical Engineering and Automation Fuzhou UniversityFuzhou 350108 the Key Laboratory of Industrial Automation Control Technology and Information Processing Education Department of Fujian ProvinceFuzhou 350108 G+Industrial Internet Institute Fuzhou UniversityFuzhou 350108China

Behavior-based autonomous systems rely on human intelligence to resolve multi-mission conflicts by designing mission priority rules and nonlinear *** this work,a novel twolayer reinforcement learning behavioral control(RLBC)method is proposed to reduce such dependence by trial-and-error ***,in the upper layer,a reinforcement learning mission supervisor(RLMS)is designed to learn the optimal mission *** with existing mission supervisors,the RLMS improves the dynamic performance of mission priority adjustment by maximizing cumulative rewards and reducing hardware storage demand when using neural *** the lower layer,a reinforcement learning controller(RLC)is designed to learn the optimal control *** with existing behavioral controllers,the RLC reduces the control cost of mission priority adjustment by balancing control performance and *** error signals are proved to be semi-globally uniformly ultimately bounded(SGUUB).Simulation results show that the number of mission priority adjustment and the control cost are significantly reduced compared to some existing mission supervisors and behavioral controllers,respectively.

关键词： Behavioral control mission supervisor nonlinear autonomous system reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient Path Finding and Moving Stability-Focused Trajectory Planning for Mobile Robots

Towards Efficient Path Finding and Moving Stability-Focused ...

引用

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Hou, Muyang Lei, Zhenya Hu, Haidong Wang, Zhong Wang, Yong Xie, Le Wang, Hesheng Shanghai Jiao Tong University Department of Automation Shanghai200240 China School of Information and Control Engineering China University of Mining and Technology Xuzhou221116 China Beijing Institute of Control Engineering Beijing100190 China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Department of Automation Shanghai200240 China

ISBN: (纸本)9781665481090

Nowadays, mobile robots play an important role in a variety of service scenarios. They need to plan and track trajectories to accomplish tasks such as delivery or guided tours. In such tasks, there are two remaining challenges: on one hand, the time and memory consumption of present path planners are still significant;on the other hand, service robots, which have a higher center of gravity, demand greater moving stability than that of current trajectory planners provide. To address these two challenges. Firstly, we propose a safety boundary first A∗ which fully utilizes environmental obstacle information to create a safety boundary and searches in it to quickly find an initial path. Secondly, we formulate the trajectory optimization problem as a nonlinear optimization problem, where the smoothness, safety, feasibility, and moving stability of the robot are taken into account. Furthermore, to constrain the robot's lateral acceleration, we design a time allocation algorithm based on non-uniform B-spline, enhancing the quality of the resulting trajectory. Simulations and real-world experiments demonstrate that our algorithms significantly improve path search efficiency, enhance moving stability, reduce the difficulty of tracking, and improve the quality of task completion. © 2024 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Equilibrium analysis of networked game under best-response dynamics

Equilibrium analysis of networked game under best-response d...

引用

第43届中国控制会议

作者： Yu Xia Qi Su Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Both coordination,a behavioral pattern where individuals adopt the same behavior as the majority,and anticoordination,a behavioral pattern where individuals choose a behavior different from the majority,are prevalent in social and engineering *** include the spread of social norms or innovations for coordination and the division of labor and traffic congestion for *** the large-scale interacting systems driven by coordination and anticoordination is of great significance in understanding,predicting,and optimizing the evolutionary *** existing studies have primarily focused on analyzing the convergence of networked systems and evaluating the time to reach equilibrium,our investigation delves into all possible states of a networked system and scrutinizes all equilibrium ***,we observe that the number of equilibrium states increases exponentially with the network *** for network structure properties,homogeneous networks exhibit more equilibrium states than heterogeneous ***,for specific behavioral switching thresholds,the number of equilibrium states is surprisingly higher than at neighboring switching *** work reveals the intricate interplay between evolutionary dynamics,system structure,and behavioral switching thresholds.

关键词： Best-response dynamics Complex networks Game theory Equilibrium analysis

来源：评论

学校读者我要写书评

暂无评论

Depth-Aware Fusion Method Based on Image and 4D Radar Spectrum for 3D Object Detection

Depth-Aware Fusion Method Based on Image and 4D Radar Spectr...

引用

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Sun, Yue Qian, Yeqiang Wang, Chunxiang Yang, Ming The Global Institute of Future Technology Shanghai Jiao Tong University Shanghai200240 China Shanghai Jiao Tong University The Department of Automation Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China

ISBN: (纸本)9781665481090

Safety and reliability are crucial for the public acceptance of autonomous driving. To ensure accurate and reliable environmental perception, intelligent vehicles must exhibit accuracy and robustness in various environments. Millimeter-wave radar, known for its high penetration capability, can operate effectively in adverse weather conditions such as rain, snow, and fog. Traditional 3D millimeter-wave radars can only provide range, Doppler, and azimuth information for objects. Although the recent emergence of 4D millimeter-wave radars has added elevation resolution, the radar point clouds remain sparse due to Constant False Alarm Rate (CFAR) operations. In contrast, cameras offer rich semantic details but are sensitive to lighting and weather conditions. Hence, this paper leverages these two highly complementary and cost-effective sensors, 4D millimeter-wave radar and camera. By integrating 4D radar spectra with depth-aware camera images and employing attention mech-anisms, we fuse texture-rich images with depth-rich radar data in the Bird's Eye View (BEV) perspective, enhancing 3D object detection. Additionally, we propose using GAN-based networks to generate depth images from radar spectra in the absence of depth sensors, further improving detection accuracy. © 2024 IEEE.

关键词： Radar imaging

来源：评论

学校读者我要写书评

暂无评论

3D Machine Vision Enabled Shrinkage Pin Detection of Aviation Connectors in the Aircraft EWIS

3D Machine Vision Enabled Shrinkage Pin Detection of Aviatio...

引用

第43届中国控制会议

作者： Yao Wang Cheng Ren Jiaxin Xu Cailian Chen Xinping Guan Department of Automation Shanghai Jiao Tong Universityand Key Laboratory of System Control and Information ProcessingMinistry of Education of China

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Aviation connectors are responsible for information and energy transmission in the aircraft electrical wiring interconnection system(EWIS).Even a tiny shrinkage of any connector pin may lead to a critical impact on the reliability and stability of the ***,the current detection method of connector pin shrinkage mainly relies on manual visual inspection,which is prone to missed and false ***,traditional 2D machine vision methods face challenges in dealing with fine pins and deep calibers of *** address this issue,this paper designs a defect detection device and proposes a 3D-enabled shrinkage pin detection(3D-SPD) *** the device,a 4-degree-of-freedom(4-DOF) support mechanism is designed to collect the connector point cloud based on the imaging principle of a 3D structured light ***,a preprocessed method is presented to extract defective regions from the raw point ***,3D-SPD algorithm can automatically select the reference plane and detect the pin position,enabling online detection of connector shrinkage *** results show that 3D-SPD algorithm is effective in detecting shrinkage pin defects on various types of aviation connectors,with an accuracy rate of 98.62%and a shrinkage pin detection rate of 100%.

关键词： Aviation Connector EWIS 3D Machine Vision Defect Detection Shrinkage Pin

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Dynamic AGV Scheduling Method Based on Deep Reinforcement Learning

Multi-objective Dynamic AGV Scheduling Method Based on Deep ...

引用

Asian control Conference

作者： Gaoshang Wang Yuanyuan Zou Shaoyuan Li Department of Automation Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Ministry of Education Shanghai

ISBN: (数字)9789887581598

ISBN: (纸本)9798331540845

In industrial production, automated guided vehicles (AGVs) are widely used for material transfer and workpiece transportation to improve production efficiency. The growing demands of dynamic orders and switching production bring great challenges to the dynamic scheduling problem of AGV systems. To address the dynamic tasks with different optimization objective weight factors, a self-attention based multi-objective reinforcement learning (SAMORL) AGV dynamic scheduling method is proposed in this paper. At each rescheduling point, the self-attention based multi-objective deep dueling double Q-network (SAMOD3QN) is utilized to estimate the Q-values of task allocation actions on each objective respectively. Then in the action choosing process, the Q-values on different objectives are weighted according to the given weight factors. In this way, the task allocation policy achieves quick adjustment to different optimization objectives. Furthermore, the beam search algorithm is utilized to expand the search space of the optimal action trajectory according to the cumulative reward and estimated Q-value. The effectiveness and adaptability of the proposed dynamic scheduling method is illustrated by test examples based on stochastically inserted tasks.

关键词： Remotely guided vehicles Job shop scheduling Transportation Production Switches Dynamic scheduling Trajectory

来源：评论

学校读者我要写书评

暂无评论

Prediction of NOx Emission in SCR system of Thermal Power Plant Using Machine Learning Approaches

Prediction of NOx Emission in SCR System of Thermal Power Pl...

引用

第35届中国过程控制会议

作者： Sai Saing Lin Jingcheng Wang Shunyu Wu Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China

Effective prediction of Nitrogen Oxides(NOx) emissions in thermal power plants is essential for addressing environmental pollution control. The Selective Catalytic Reduction(SCR) system plays a pivotal role in mitigating NOx output, yet its performance can vary significantly due to operational conditions. This study investigates the prediction of NOx emissions in Selective Catalytic Reduction(SCR) systems within thermal power plants. Time delay mechanism is an essential factor for accurate modeling and prediction. Therefore, we incorporate a time delay of 120 samples into our feature engineering and analysis. Six predictive models, including five regression models and one Long Short-Term Memory(LSTM) neural network, are employed to analyze the temporal dynamics of NOx emissions. The regression models were selected for their varied methodologies and strengths in handling different types of data distributions and features, whereas the LSTM model was specifically utilized for its proficiency in processing sequential data, capturing long-term dependencies crucial for time-series forecasting. The performance of these models was evaluated using three statistical metrics: Root Mean Squared Error(RMSE), Mean Absolute Error(MAE), and the coefficient of determination(R2). Among the models, the Extra Trees regression model demonstrated superior accuracy in predicting NOx emissions, outperforming other models.

关键词： Thermal power plant Nitrogen Oxides emission SCR system Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Unlock the flexibility for cooperative operation of hydrogen providers under transportation delay

引用

Applied Energy 2025年 394卷

作者： Yang, Xu Yang, Bo Wang, Zhaojian Liu, Sicheng Guan, Xinping Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory for System Control and Information Processing Ministry of Education of China Shanghai200240 China

Hydrogen provides a pathway to the clean transition of the future energy mix, rendering hydrogen energy service providers (HESPs) an important role in hydrogen supply. Additionally, collaborative operation through vehicle-based hydrogen transportation exhibits great potential for mitigating source–load fluctuations of HESPs. However, current collaborations on hydrogen transportation primarily focus on route selection while neglecting delay risks, which may precipitate abrupt energy deficits during the scheduling of energy receivers. This work proposes a multi-HESP cooperative game that considers a deadline assignment mechanism to ensure the robustness of hydrogen delivery while fully unlocking the scheduling flexibility supported by the road network. Considering the transportation-time uncertainty, the distributionally robust joint chance constraint (DRJCC) is introduced to model delay uncertainties effectively and improve hydrogen delivery reliability. A customized approximation method is proposed to reformulate the DRJCC model into a tractable approximation with low conservatism while enhancing flexibility in decision-making under transportation delay uncertainty. Case studies verify that the proposed framework can improve the flexibility and enthusiasm of multi-HESP cooperation under the electricity–hydrogen transmission network. © 2025 Elsevier Ltd

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

SPARC: Prediction-Based Safe control for Coupled controllable and Uncontrollable Agents with Conformal Predictions

arXiv

引用

arXiv 2024年

作者： Wang, Shuqi Wang, Siqi Li, Shaoyuan Yin, Xiang Department of Automation Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai200240 China

We investigate the problem of safe control synthesis for autonomous systems operating in environments with uncontrollable agents whose dynamics are unknown but coupled with those of the controlled system. This scenario naturally arises in various applications, such as autonomous driving and human-robot collaboration, where the behavior of uncontrollable agents, such as pedestrians or human operators, cannot be directly controlled but is influenced by the actions or the states of the autonomous vehicle or robot. In this paper, we present SPARC (Safe Prediction-Based Robust controller for Coupled Agents), a new framework designed to ensure safe control in the presence of uncontrollable agents that are coupled with the controlled system. Particularly, we introduce a joint distribution-based approach to account for the coupled dynamics of the controlled system and uncontrollable agents. Then, SPARC leverages conformal prediction to quantify the uncertainty in data-driven prediction of the agent behavior. By integrating the control barrier function (CBF), SPARC provides provable safety guarantees at a high confidence level. We illustrate our framework with a case study of an autonomous driving scenario with walking pedestrians. Copyright © 2024, The Authors. All rights reserved.

关键词： Human robot interaction

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：