检索结果-内蒙古大学图书馆

6th International Conference on Electronic engineering and Informatics, EEI 2024

作者： Chen, Yucheng Zhu, Yupeng Zhu, Hongming Zhang, Quanqi Wu, Chengwei Harbin Institute of Technology Department of Control Science and Engineering Harbin China

ISBN: (纸本)9798350353594

This paper employs Gaussian Processes (GPs) to estimate uncertainty dynamics inherent in nonlinear systems. A control policy ensuring the system satisfies initial stability constraints is derived using linear quadratic regulator (LQR). By modeling the Lyapunov function based on uncertain dynamics as GPs, the stability of the system dynamics in the Lyapunov sense is ensured. To discretize the Lyapunov function with Lipschitz continuity, a finite number of discrete points are chosen to represent the properties of the function. The region of attraction (RoA) based on Lyapunov function is widely utilized as a safe constraint in the field of control. Additionally, the maximum uncertainty dynamics are chosen as the boundary for exploration to expand the evaluation of the RoA. Finally, a simulation example is provided to demonstrate the effectiveness of the proposed approach. © 2024 IEEE.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Network with In-Betweening for Fine-Grained Skeleton-Based Action Generation 50

Generative Adversarial Network with In-Betweening for Fine-G...

引用

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

作者： Qi, Xiangyuan He, Zhen Wang, Qiang Department of Control Science and Engineering Harbin Institute of Technology Harbin China

ISBN: (纸本)9781665464543

Human action generation has shown critical value in both industry application and academic research, especially fine-grained skeleton-based action generation. At present, there are several main ways to achieve fine-grained skeleton-based action generation. In this work, we utilize a generative adversarial network with in-betweening, in order to generate natural and continuous skeleton sequences and better capture complex motion details. In-betweening can be viewed as a prediction task based on the past and future context. Besides, it is convenient to control the result in a personalized way and combine the framework with other network structures to further improve the performance. In particular, two simple discriminators are applied on different timescales and LSTM serves as the foundation of the action generator because of its capability of effectively capturing long-term dependencies and processing sequence data of different lengths. The target noise added to the input of the generator can contribute to the robustness of the system and further improve the performance. Moreover, a novel Tai Chi dataset composed of fine-grained skeleton-based action data is created using high quality motion capture technology. The model is evaluated on two fine-grained skeleton-based datasets, LaFAN1 and Tai Chi, which contain common daily actions and professional sports actions respectively, and it achieves superior performance both qualitatively and quantitatively. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Friction Modeling and control Compensation for Electromechanical Braking Systems 8

Friction Modeling and Control Compensation for Electromechan...

引用

8th CAA International Conference on Vehicular control and Intelligence, CVCI 2024

作者： Houhua, Jing Qinggan, Lin Mingqi, Liu Harbin Institute of Technology Department of Control Science and Engineering Harbin China

ISBN: (纸本)9798331504892

Influenced by the electrification and intelligence of automobile chassis, electromechanical braking has become the future brake-by-wire trend choice by virtue of its simpler mechanism and faster servo performance, while system friction, as a key factor of its servo control, must be handled properly. This work studies the system friction modeling of electromechanical braking system and the corresponding control compensation approach. First, by evaluating the structure and working principle of the electromechanical braking system, the system model is produced, the braking control test rig is built and the system characteristic test is carried out. Then, the friction model parameters were identified from the experimental data based on the examination of system features. Finally, the brake control performance after friction compensation was experimentally validated by the physical rig, which verified the effectiveness of the friction model and its control compensation. © 2024 IEEE.

关键词： Braking performance

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter Optimization of Object Detection Networks Based on Large Language Models 50

Hyperparameter Optimization of Object Detection Networks Bas...

引用

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

作者： Hu, Yushuo Wang, Qiang Department of Control Science and Engineering Harbin Institute of Technology Harbin China

ISBN: (纸本)9781665464543

Since the emergence of deep learning, the configuration of hyperparameters has been one of the most significant problems that people have paid attention to. However, traditional hyperparameter optimization techniques typically have drawbacks such as expensive calculation consumption and lengthy training time. With the development of large language models (LLMs), particularly models such as generative pretrained transformer (GPT), it is achievable to utilize the models’ analysis ability to guide parameter space search. This paper investigates the use of LLMs for hyperparameter optimization in machine learning problems. To evaluate the effectiveness of this strategy, four object detection models, including YOLOv5, YOLOv8, Faster R-CNN, and R-FCN, were used to conduct experiments. At the same time, we compared the distinctions between this approach and traditional ways. The experimental results indicate that combining LLMs with the hyperparameter optimization process can perform comparably or better than conventional methods. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Steering Torque Feedback System for Steer-by-Wire Vehicles 43

Design and Implementation of Steering Torque Feedback System...

引用

43rd Chinese control Conference, CCC 2024

作者： Ma, Chao Zhao, Linhui Harbin Institute of Technology Department of Control Science and Engineering Harbin150001 China

ISBN: (纸本)9789887581581

Steer-by-wire (SBW) is an advanced technology of great significance for the intelligent driving. To implement the function of the road feeling feedback for SBW, this paper presents a design of the road feeling feedback system, including the mechanical structure and the control algorithm. The target feedback torque is planned by the method of function fitting, and the controller is designed to track the target torque by combining the feedback control and the feedforward control. This paper designs an experimental bench and validates the performance of the system by hardware in-loop (HIL) experiment. The results show that the system can provide an approximate feedback torque and a comfortable driving experience. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Feedback control

来源：评论

学校读者我要写书评

暂无评论

High-Precision control of Humanoid Muscle-skeleton Robotic Arm Using Reinforcement Learning and Large Language Models 50

High-Precision Control of Humanoid Muscle-skeleton Robotic A...

引用

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

作者： Wang, Yan Wang, Qiang Fan, Jianyin Department of Control Science and Engineering Harbin Institute of Technology Harbin150001 China

ISBN: (纸本)9781665464543

In recent years, humanoid robotics have achieved significant advancements, including those embodied by muscle-skeleton robots. Due to the nonlinear characteristics of these robots, reinforcement learning is a popular method for muscle-skeleton robot control. However, the design of the reward function and the adjustment of hyper parameters is a difficult task when using reinforcement learning. In this paper, we combine reinforcement learning with a large language model to achieve precise control of a humanoid muscle-skeleton robotic arm. We first tell the large language model task, states, and hyper parameters, and then continuously feedback the training results. We can finally get a controller that can control the robot to complete the target-tracking task. The experimental results show that the large language model can propose a suitable reward function based on experience, and adjust the hyper parameters to better training results within several questions and answers. © 2024 IEEE.

关键词： Musculoskeletal system

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning Solution to the Nonlinear Spacecraft Pursuit-Evasion Game Problem 14

A Reinforcement Learning Solution to the Nonlinear Spacecraf...

引用

14th IEEE International Conference on Cyber technology in Automation, control, and Intelligent Systems, CYBER 2024

作者： Huang, Haoqi Ran, Guangtao Lyu, Yueyong Ma, Guangfu Harbin Institute of Technology Department of Control Science and Engineering Harbin150001 China

ISBN: (纸本)9798331506056

The pursuit-evasion game of non-cooperative spacecrafts under nonlinear dynamics is currently a hot topic in orbital gaming. We describe the above pursuit-evasion game model using differential game theory, transforming the gaming problem into a bilateral optimal control problem. Using elliptical orbit line-of-sight (LOS) dynamics with simple field-of-view constrains as the system model, we solve the Nash equilibrium solution for the two-body pursuit-evasion under the assumption of complete information. Due to the difficulty in obtaining analytical solutions for the Nash equilibrium, we adopt a reinforcement learning (RL)-based adaptive dynamic programming method. We obtain the approximate Nash equilibrium solution with RL method eventually and provide a successful simulation example. © 2024 IEEE.

关键词： Orbits

来源：评论

学校读者我要写书评

暂无评论

Dual Spatial-Temporal Feature Pyramid With Decoupled Temporal Mining for Video Semantic Segmentation

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-12页

作者： Hong, Yuanduo Pan, Huihui Sun, Weichao Wang, Yulei Bian, Ning Gao, Huijun Research Institute of Intelligent Control and Systems Harbin Institute of Technology Harbin China Department of Control Science and Engineering Tongji University Shanghai China Dongfeng Motor Corporation Wuhan China

Semantic segmentation plays a pivotal role in environmental perception for autonomous driving. Video semantic segmentation (VSS) further takes temporal information into consideration for better scene parsing and temporal consistency. Previous research on VSS is mostly dedicated to developing new techniques (e.g. optical flows, attention) to better mine temporal information. In this work, we contribute from a different angle by efficiently incorporating multi-scale temporal information. The dual spatial-temporal feature pyramid is proposed to enable the direct enhancement of multi-scale features for target frames and unlash the design of temporal information mining modules. It contains a spatial feature pyramid from a target frame and a spatial-temporal feature pyramid from multiple reference frames. Building on the dual feature pyramid, we further propose to decouple motional contexts and static contexts to fully leverage temporal information. Specifically, multi-scale motional contexts are mined with the introduced dedicated module and static contexts are enhanced by making temporally fused category-level representations interact with the target frame feature. The final segmentation maps are obtained by regarding the enhanced category-level representations as powerful feature classifiers to classify the target frame feature of rich motional contexts. Experimental results on two popular VSS benchmarks demonstrate that the proposed method with decent parameter and inference efficiency clearly outperforms previous advanced methods. IEEE

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Deep attention convolutional neural network-based adaptive multi-source information fusion for accurate short-term photovoltaic power forecast

Deep attention convolutional neural network-based adaptive m...

引用

2023 IEEE PES Innovative Smart Grid Technologies Europe, ISGT EUROPE 2023

作者： Bai, Mingliang Chen, Yunxiao Zhou, Zhihao Long, Zhenhua Liu, Jinfu Yu, Daren Department of Control Science and Engineering Harbin Institute of Technology Harbin China School of Energy Science and Engineering Harbin Institute of Technology Harbin China Department of Control Science and Engineering School of Energy Science and Engineering Harbin Institute of Technology Harbin China

ISBN: (纸本)9798350396782

Solar energy is one of the most important renewable energy sources. Photovoltaic (PV) power generation is currently one of the most important ways to utilize solar energy. PV power has strong uncertainties and is adverse to the stability of the electricity grid. PV power forecast is an important method to tackle this issue. Conventional methods only use historical PV power data. This paper proposes a new method that uses deep Convolutional Neural Networks (CNN)-based multivariable information fusions for PV forecast. Multiple variables including global horizontal irradiation (GHI), relative humidity, air temperature, cloud thickness, wind speed, etc. are used for PV forecast. Meanwhile, clear-sky GHI estimated by McClear clear-sky models are used as physical prior knowledge. Through the attention mechanism, these variables are adaptively fused with the historical PV power data to realize an accurate PV power forecast. Forecast experiments in three-year (2017-2019) actual data of Brussels PV power stations verify the significant superiority of the proposed method over conventional forecast methods. © 2023 IEEE.

关键词： attention mechanism convolutional neural network photovoltaic power forecast solar energy

来源：评论

学校读者我要写书评

暂无评论

Dynamic Parallel Feedforward Compensator-based Generalized Negative Imaginary Synthesis Allowing Poles At The Origin 26

Dynamic Parallel Feedforward Compensator-based Generalized N...

引用

26th International Conference on Industrial technology, ICIT 2025

作者： Cheng, Zhining He, Zhen Meng, Fanwei Zhou, Di Harbin Institute of Technology Department of Control Science and Engineering Harbin China School of Control Engineering Northeastern University at Qinhuangdao Qinhuangdao China

ISBN: (纸本)9798331521950

This paper presents a new negative imaginary(NI) synthesis method for a linear-time-invariant(LTI) system with up to two poles at the origin. A dynamic parallel feedforward compensator(DPFC) is added to the controlled plant, which ensures that the augmented system exhibits generalized negative imaginary(GNI) property. And a set of linear matrix inequalities(LMIs) conditions are derived, leading to easy application of this scheme. The augmented system could be stabilized by any SNI controllers only if satisfying the DC loop gain condition. As an application of these results, an example of stabilizing a flexible satellite is carried out to verify the effectiveness of the proposed method. © 2025 IEEE.

关键词： Linear matrix inequalities

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：