检索结果-内蒙古大学图书馆

International Conference on Guidance, Navigation and control, ICGNC 2022

作者： Han, Xiao Zhou, Lifan Ma, Guangfu Chen, Xixuan Department of Control Science and Engineering Harbin Institute of Technology Harbin150001 China School of Control Science and Engineering Shandong University Jinan250061 China

ISBN: (纸本)9789811966125

This paper proposes a finite-time control method for the attitude of combined spacecraft without system parameter identification, avoiding the problems of long identification time and low identification accuracy of the combined spacecraft parameters. The method designs an auxiliary system based on the features of the model, combines the Linear Extended State Observer (LESO) and non-singular terminal sliding mode control(SMC), and achieves the finite-time attitude control of the combined spacecraft. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Spacecraft

来源：评论

学校读者我要写书评

暂无评论

Aggressive and robust low-level control and trajectory tracking for quadrotors with deep reinforcement learning

引用

Neural Computing and Applications 2025年第3期37卷 1223-1240页

作者： Chen, Shiyu Li, Yanjie Lou, Yunjiang Lin, Ke Department of Control Science and Engineering Harbin Institute of Technology Shenzhen Shenzhen518055 China Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics Shenzhen518055 China

Executing accurate trajectory tracking tasks using a high-performance low-level controller is crucial for quadrotors to be applied in various scenarios, especially those involving uncertain disturbances. However, due to the uncertainties in disturbed environments, developing effective low-level controllers with traditional model-based control schemes is challenging. This paper presents an aggressive and robust reinforcement learning (RL)-based low-level control policy for quadrotors. The policy maps the observed quadrotor state directly to motor thrust commands, without requiring the quadrotor dynamics. Additionally, a trajectory generation pipeline is developed to improve the accuracy of trajectory tracking tasks based on differential flatness. With the learned low-level control policy, extensive simulations and real-world experiments are implemented to validate the performance of the policy. The results indicate that our RL-based low-level control policy outperforms traditional proportional–integral–derivative (PID) control methods and related learning-based policies in terms of accuracy and robustness, particularly in environments with uncertain disturbances. Furthermore, the proposed RL-based control policy exhibits an aggressive response in trajectory tracking, even when the speed of the desired trajectory is increased to 6 m/s. Moreover, the learned policy demonstrates strong vibration suppression capabilities and enables the quadrotor to recover to a hovering state from random initial conditions with shorter response time. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A NTSMCLF Attitude Tracking controller for the Satellite with Flexible Accessories Based on the Stewart platform 42

A NTSMCLF Attitude Tracking Controller for the Satellite wit...

引用

42nd Chinese control Conference, CCC 2023

作者： Chen, Xixuan Zhu, He Yin, Junxiong Han, Yumeng Guo, Yanning Harbin Institute of Technology Department of Control Science and Engineering Harbin150001 China Shanghai Academy of Spaceflight Technology China

ISBN: (纸本)9789887581543

In this paper, a novel class of finite-time high precision satellites attitude tracking controller based on nonsingular terminal sliding mode control Lyapunov function (NTSMCLF) with the Stewart platform active vibration isolation is proposed. An active vibration algorithm for Stewart platform is designed to isolate the micro-vibration, which uses sliding mode variable Structure control (SMC) method. In order to suppress the influence of vibration on satellite, the dynamical model of Stewart platform considering the physical constraints, noise immunity and robustness of passive vibration isolation mechanical structures is designed. Considering the controller accuracy and infinite time convergence, the finite-time control Lyapunov function (CLF) high-precision attitude tracking control algorithm based on nonsingular terminal sliding mode (NTSM) is provided. The finite-time stability of the system is guaranteed. Numerical simulation results are provided to validate the effectiveness of proposed control method. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

Infrared Target Generation based on Conditional Diffusion Inpainting

Infrared Target Generation based on Conditional Diffusion In...

引用

2024 Conference on Spectral technology and Applications, CSTA 2024

作者： Dong, Bo Liu, Xiuhua Wang, Peng Xu, Xiaoyu Department of Control Science and Engineering Harbin Institute of Technology Harbin China Intelligent Science and Technology Academy Limited of CASIC Beijing China Tangshan Workers' Hospital Tangshan China

ISBN: (纸本)9781510683082

A novel method for generating infrared targets is proposed, based on conditional diffusion inpainting. Firstly, we introduce a transformation framework designed to translate detection annotations from text to image, serving as the conditional input for the diffusion inpainting convolutional neural network. Secondly, a novel multi-scale image-condition Unet is designed as the mainframe of diffusion model. Finally, we conduct numerous direct and indirect evaluation experiments to assess the proposed algorithm. Experimental results demonstrate that the proposed algorithm generates high-quality infrared targets. Furthermore, as an augmentation, the generated images significantly enhance the detection accuracy of few-shot thermal infrared targets. © 2024 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Fixed-Time Convergence Sliding Mode Observer Based Model-Free Predictive Current control for PMSMs 49

A Fixed-Time Convergence Sliding Mode Observer Based Model-F...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Lin, Xinpo Luo, Yiang Gao, Yabin Liu, Jianxing Peretti, Luca Harbin Institute of Technology Department of Control Science and Engineering Harbin China Kth Royal Institute of Technology Department of Electrical Engineering Stockholm Sweden

ISBN: (纸本)9798350331820

This paper presents a model-free predictive current controller for permanent magnet synchronous motors. The dynamic model of the motor currents is represented using an ultra-local model, where all system parameters, nonlinear terms, and other unmodeled dynamics are encapsulated into two lumped functions. These functions are estimated online using a second-order fixed-time sliding mode observer, allowing for system model estimation without requiring exact knowledge of the system parameters in advance. Subsequently, a predictive controller is designed by taking into consideration the inherent one-step delay. Simulation results are presented to showcase the effectiveness and efficacy of the proposed approach. © 2023 IEEE.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Trajectory Planning Strategy for Intelligent Vehicles with Collision Avoidance 41

A Hybrid Trajectory Planning Strategy for Intelligent Vehicl...

引用

第41届中国控制会议

作者： Yufa You Linhui Zhao Haifeng Liu Zhiyuan Liu Department of Control Science and Engineering Harbin Institute of Technology

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper presents a hybrid trajectory planning strategy with interpolation curve optimization method under the constraints of collision avoidance and vehicle *** an objective function consisting of a weighted sum of comfort and efficiency,the cubic polynomial curve is firstly optimized under the initial state and the terminal state constraints to generate a reference ***,in order to generate collision-free trajectory,lateral and longitudinal turning factors are introduced to cluster the reference *** to the dimension relationship between vehicle and road,the maximum lane change distance and the maximum turning curvature,the number of trajectories in the cluster is ***,an algorithm is designed to detect the collision of the *** priority of the trajectories is defined to determine the optimal ***,a lateral vehicle dynamic model is *** judge the feasibility,under the condition of dynamic constraints,the reference trajectory is tracked with optimal control signal and judged by the tracking *** this way,the collision risk is eliminated,and the trajectory performance is *** results show that the trajectory planning strategy is effective in different scenarios.

关键词： Intelligent vehicles trajectory planning collision avoidance vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Exploring Adversarial Robustness of Deep State Space Models 38

Exploring Adversarial Robustness of Deep State Space Models

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Qi, Biqing Luo, Yiang Gao, Junqi Li, Pengfei Tian, Kai Ma, Zhiyuan Zhou, Bowen Department of Electronic Engineering Tsinghua University China Shanghai Artificial Intelligence Laboratory China Department of Control Science and Engineering Harbin Institute of Technology China School of Mathematics Harbin Institute of Technology China

Deep State Space Models (SSMs) have proven effective in numerous task scenarios but face significant security challenges due to Adversarial Perturbations (APs) in real-world deployments. Adversarial Training (AT) is a mainst.eam approach to enhancing Adversarial Robustness (AR) and has been validated on various traditional DNN architectures. However, its effectiveness in improving the AR of SSMs remains unclear. While many enhancements in SSM components, such as integrating Attention mechanisms and expanding to data-dependent SSM parameterizations, have brought significant gains in Standard Training (ST) settings, their potential benefits in AT remain unexplored. To investigate this, we evaluate existing structural variants of SSMs with AT to assess their AR performance. We observe that pure SSM structures struggle to benefit from AT, whereas incorporating Attention yields a markedly better trade-off between robustness and generalization for SSMs in AT compared to other components. Nonetheless, the integration of Attention also leads to Robust Overfitting (RO) issues. To understand these phenomena, we empirically and theoretically analyze the output error of SSMs under AP. We find that fixed-parameterized SSMs have output error bounds strictly related to their parameters, limiting their AT benefits, while input-dependent SSMs may face the problem of error explosion. Furthermore, we show that the Attention component effectively scales the output error of SSMs during training, enabling them to benefit more from AT, but at the cost of introducing RO due to its high model complexity. Inspired by this, we propose a simple and effective Adaptive Scaling (AdS) mechanism that brings AT performance close to Attention-integrated SSMs without introducing the issue of RO. Our code is available at Robustness-of-SSM. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Spatial-Temporal Graph U-Net for Skeleton-Based Human Motion Infilling 25

Spatial-Temporal Graph U-Net for Skeleton-Based Human Motion...

引用

25th IEEE International Conference on Industrial technology, ICIT 2024

作者： Xu, Leiyang Wang, Qiang Yang, Chenguang Harbin Institute Of Technology Department Of Control Science And Engineering Harbin China University Of Liverpool Department Of Computer Science LiverpoolL69 3BX United Kingdom

ISBN: (纸本)9798350340266

Motion infilling is a fundamental and challenging research field in human motion modeling and analysis, which aims to generate natural and visually coherent transitions to fill in missing motion frames based on the start and end motion sequences. However, most current methods ignore the spatial structure formed by joints, which may lose some spatial information. This work proposes a novel spatiotemporal graph U-Net that supports flexible inputs for skeleton-based motion infilling. We apply spatiotemporal graph convolutional layers, skeleton pooling layers, and skeleton unpooling layers to extract spatial and temporal features in the motion sequence. At the same time, we use the U-Net structure to integrate the information in the start and end motion sequences. In addition, the generative adversarial mechanism is introduced to ensure the generated skeleton poses are smooth and natural. We conduct experiments on two motion datasets, including one large-scale public dataset and one self-built dataset. The model inputs are joint quaternions or joint coordinates. Experimental results show that our method can improve the performance of skeleton-based motion infilling and achieve state-of-the-art results when using joint coordinates as model input. © 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

Facial Expression Recognition based on Convolutional Neural Network with Sparse Representation 8

Facial Expression Recognition based on Convolutional Neural ...

引用

8th International Conference on Systems and Informatics, ICSAI 2022

作者： Liu, Xuan Ma, Jiachen Wang, Qiang Harbin Institute of Technology Department of Control Science and Engineering Harbin China Harbin Institute of Technology Department of Control Science and Engineering Weihai China

ISBN: (纸本)9781665474481

Facial Expression Recognition (FER) in the wild using Convolutional Neural Networks (CNNs) has been a challenge for years because of the significant intra-class variances and interclass similarities. In contrast, facial expression recognition in the wild is vital for human-computer interactions and has numerous applications. Enhancing the discriminative features extraction ability is one approach to solving this issue. In this work, a sparse transform is used to improve a CNN's ability to extract features without adding to the network's computational load. We use a sparse representation layer that is built by the Haar wavelet transform or shearlet transform prior to the convolutional layers of a standard CNN. With the proposed sparse representation layers, we introduce a VGGNet and an AlexNet architecture and conduct experiments on the FER2013 dataset without the use of additional training data. The experimental results demonstrated that the wavelet transform's sparse representation layer can improve FER performance without increasing an excessive computational burden. We achieved testing accuracy of 73.25 percent on the FER2013 dataset using VGGNet paired with a sparse representation layer built inside a wavelet transform, which is among the best results for a single network. © 2022 IEEE.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Channel and Spatial Attention Mechanism-based Yolo Network for Target Detection of the Lung Ultrasound Scanning Robot 9

Channel and Spatial Attention Mechanism-based Yolo Network f...

引用

9th International Conference on control science and Systems engineering, ICCSSE 2023

作者： Zhang, Boheng Xu, Kun Cong, Haibo Sun, Mingjian Harbin Institute of Technology Department of Control Science and Engineering Harbin China School of Information Science and Engineering Harbin Institute of Technology Weihai China Shandong First Medical University Department of Orthopedics Jinan China

ISBN: (纸本)9798350339055

Ultrasonography is the preferred method for detecting lung lesions, which has been widely recognized and adopted. In order to reduce the work stress and risk of infection for health care workers, lung ultrasound (LUS) scanning robots can be used to perform this task inst.ad of doctors. For the LUS scanning robot, the first critical step is the detection of the scanned areas of the patient's lungs. The algorithms using computer vision and deep learning have made significant progress in the field of target detection, which are being applied more and more frequently to robotic autonomous decision-making. However, some of the performance of the traditional convolutional neural networks (CNN) still needs to be improved due to the more stringent requirements for real-Time, accuracy and hardware cost of LUS scanning robots. The effectiveness of CNN combined with computer vision for detecting scanned sites in LUS scanning robots is explored and a lightweight Yolo network based on the attention mechanism is proposed. We use Yolo V4-Tiny model as the backbone network. Then the depth feature information of the feature layer output from the backbone network are extracted by adding space and channel attention mechanism, and the prediction results are output by using Yolo head model. Meanwhile, we also optimize the loss function of the network to further improve the performance of the network. Compared to several classical algorithms, the proposed method improves the target detection performance of the LUS scanning robot, which achieves 98.83% average precision, 96.87% precision, and 91.00% F1 score. We apply the proposed algorithm to the designed LUS scanning robot system and conduct clinical experiments. The results have shown that the proposed method has a 3D localization accuracy of 7.53 ± 0.37mm for the lung scanned sites, which has the potential to be applied to the target detection of the LUS scanning robot. © 2023 IEEE.

关键词： Ultrasonic applications

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：