检索结果-内蒙古大学图书馆

Characteristic model-based control of aerial manipulator for improved interaction stability

Science China(Technological Sciences) 2025年第4期68卷 166-178页

作者： Bingkai XIU Zhan LI Yipeng YANG Huijun GAO Research Institute of Intelligent Control and Systems Harbin Institute of TechnologyHarbin150001China State Key Laboratory of Robotics and Systems(HIT) Harbin Institute of TechnologyHarbin150001China

Maintaining contact stability is crucial when the aerial manipulator interacts with the surrounding environment. In this paper, a novel output feedback framework based on a characteristic model is proposed to improve the contact stability of the aerial manipulator. First, only position measurements of the aerial manipulator are introduced to design the practical finite-time command filter-based force observer. Second, an attitude control architecture including characteristic modeling and controller design is presented. In the modeling part, input-output data is utilized to build the characteristic model with fewer parameters and a simpler structure than the traditional dynamic model. Different from conventional control methods, fewer feedback values,namely only angle information, are required for designing the controller in the controller part. In addition, the convergence of force estimation and the stability of the attitude control system are proved by the Lyapunov analysis. Numerical simulation comparisons are conducted to validate the effectiveness of the attitude controller and force observer. The comparative results demonstrate that the tracking error of x and θ channels decreases at least 10.62% and 10.53% under disturbances and the force estimation precision increases at least 45.19% in the different environmental stiffness. Finally, physical flight experiments are conducted to validate the effectiveness of the proposed framework by a self-built aerial manipulator platform.

关键词： aerial manipulator interaction stability contact force observer characteristic model

来源：评论

学校读者我要写书评

暂无评论

Social Self-Attention Generative Adversarial Networks for Human Trajectory Prediction

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第4期5卷 1805-1815页

作者： Yang, Changzhi Pan, Huihui Sun, Weichao Gao, Huijun Harbin Institute of Technology Research Institute of Intelligent Control and Systems Harbin150001 China

Predicting accurate human future trajectories is of critical importance for self-driving vehicles if they are to navigate complex scenarios. Trajectories of humans are not only dependent on the humans themselves, but also the interactions with surrounding agents. Previous works mainly model interactions among agents by using a diversity of polymerization methods that integrate various learned agent states hit or miss. In this article, we propose social self-attention generative adversarial networks (Social SAGAN), which generate socially acceptable multimodal trajectory predictions. Social SAGAN incorporates a generator that predicts future trajectories of pedestrians, a discriminator that classifies trajectory predictions as real or fake, and a social self-attention mechanism that selectively refines the most interactive information and helps the overall model to capture what to pay attention to. Through extensive experiments, we demonstrate that our model achieves competitive prediction accuracy and computational complexity compared with previous state-of-the-art methods on all trajectory forecasting benchmarks. © 2020 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

TOGA-Based Fuzzy Grey Cognitive Map for Spacecraft Debris Avoidance

引用

IEEE Transactions on Fuzzy systems 2025年第6期33卷 1793-1802页

作者： Qin, Chenhui Liu, Yuanshi Wang, Tong Qiu, Jianbin Li, Min Harbin Institute of Technology Research Institute of Intelligent Control and Systems Harbin150080 China Beijing Institute of Control Engineering Beijing100094 China

The optimization of fuzzy grey cognitive map (FGCM) can enhance the decision quality of the system in managing uncertainties and incomplete information. Addressing this issue requires a method that effectively balances the competing demands of the speed and precision in the optimization process. Therefore, a trade-off genetic algorithm (TOGA) is proposed to refine the FGCM optimization process in this paper. Firstly, a modified fitness function with a penalty term is designed to improve the convergence rate, which can drive the FGCM population to obtain the optimal solution during the evolutionary process. Secondly, an adaptive genetic mechanism based on horizontal comparison and longitudinal assessment, is designed to strike a balance between accelerating convergence and avoiding the dilemma of falling into local optima. Finally, in the simulation section, the effectiveness of the proposed method is validated by optimizing FGCM using synthetic datasets and applying to spacecraft debris threat avoidance scenario. © 1993-2012 IEEE.

关键词： Space debris

来源：评论

学校读者我要写书评

暂无评论

A Multi-agent Deep Reinforcement Learning Approach for Multiple AGVs Scheduling in Automated Container Terminals

A Multi-agent Deep Reinforcement Learning Approach for Multi...

引用

2024 China Automation Congress, CAC 2024

作者： Wang, Fei Ding, Pansheng Bi, Yannan Qiu, Jianbin Research Institute of Intelligent Control and Systems Harbin Institute of Technology Harbin China

ISBN: (纸本)9798350368604

The equipment scheduling method of automated container terminals is gradually evolving towards intelligence and automation. In this paper, a novel multi-agent deep reinforcement learning algorithm called Coupling Deep Q-network (C-DQN) is proposed to address the automated guided vehicles (AGV) scheduling problem. Specifically, the sparse reward problem of the proposed algorithm model is solved by a mask. The convergence of the model is accelerated by changing the greedy rate with a fixed step size. The shape of samples in the experience replay buffer is also improved through the methods of the centralized training and decentralized execution. Furthermore, the scheduling conflict problem caused by the cooperative game is reduced, and the overall efficiency of the scheduling task is also improved. Finally, the scenario of multi-AGV scheduling is designed to verify the effectiveness and efficiency of the proposed C-DQN algorithm. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Fuzzy Secure Consensus control of Nonlinear Multi-Agent systems Under Deception Attacks

Adaptive Fuzzy Secure Consensus Control of Nonlinear Multi-A...

引用

2024 International Conference on Fuzzy Theory and Its Applications, iFUZZY 2024

作者： Bi, Yannan Ding, Pansheng Wang, Fei Wang, Tong Qiu, Jianbin Research Institute of Intelligent Control and Systems Harbin Institute of Technology Harbin150001 China

ISBN: (纸本)9798350352788

This paper investigates the secure consensus control problem for nonlinear multi-agent systems (MASs) under de-ception attacks. The main characteristic of the proposed secure consensus control method is its ability to mitigate undesirable system behaviors caused by deception attacks at the communication links among different agents. In particular, the relationship between the compromised signals and the output signals of MASs is analyzed. Furthermore, a novel Nussbaum function and an adaptive fuzzy law are respectively proposed to tackle the unknown control direction and to estimate the unknown terms caused by deception attacks. Simulation results are presented to demonstrate the validity of the proposed adaptive consensus secure control method. © 2024 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Learning-based multi-view profilometry for a telecentric structured light imaging system

引用

Optics Letters 2025年第10期50卷 3385-3388页

作者： Jia, Zhixiang Yu, Jinyong Liu, Weihua Yuan, Chenhao Yu, Xinghu Yang, Xianqiang Research Institute of Intelligent Control and Systems Harbin Institute of Technology Heilongjiang Harbin150001 China Yongjiang Laboratory Ningbo315202 China Ningbo Institute of Intelligent Equipment Technology Company Ltd. Ningbo315200 China

Deep learning techniques have been widely applied in fringe projection profilometry. However, existing methods focus on single-view measurements. This Letter introduces, for the first time to our knowledge, an end-to-end multi-view fringe projection profilometry (MVFPP) learning framework. It treats the decoding process as a deep feature correlation, enabling adaptation to a wide range of patterns and views of input using a feature transfer algorithm, which is guided by global spatial consistency constraints. Compared with traditional multi-stage MVFPP methods, our method more stably recovers dense surface representations, even under conditions of low coding bits, low reflectivity, and shadow occlusion. To better evaluate our method, a dataset of industrial electronics scenarios has been collected. Experimental results demonstrate that the proposed method can achieve state-of-the-art results with flexible coding patterns and coding bits. © 2025 Optica Publishing Group. All rights are reserved.

关键词： Deep learning Distortion Imaging systems Neural networks Profilometry Structured light

来源：评论

学校读者我要写书评

暂无评论

Formation control and path planning of multi-robot systems via large language models

引用

Science China(Information Sciences) 2025年第5期68卷 72-88页

作者： Dong XUE Xuanjie ZHOU Ming WANG Fangzhou LIU Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of EducationEast China University of Science and Technology Research Institute of Intelligent Control and Systems School of Astronautics Harbin Institute of Technology

Existing path planning and coordination control methods for multi-robot systems(MRS) typically rely on predefined rules and rudimentary algorithms. However, these methods often struggle to adapt flexibly to complex environments and to adjust motion targets appropriately. To address this challenge, this study presents a large language model(LLM)-assisted framework. By integrating textual descriptions of complex motion constraints, robot information, and local environmental data as inputs, LLMs generate motion objectives and translate them into executable control commands for the robots, thereby achieving coordinated control and path planning. This framework facilitates the generation, maintenance, and reshaping of formations in MRSs during path planning, applicable to both obstacle-free and obstacle-avoidance environments. Simulation results demonstrate that LLM-based control strategies enhance the autonomy, adaptability, flexibility, and robustness of MRS by processing complex information, making intelligent decisions, adapting to environmental changes, and handling disturbances and uncertainties.

关键词： multi-robot systems formation control path planning obstacle avoidance large language models

来源：评论

学校读者我要写书评

暂无评论

Robust actuator fault detection for half-car active suspension with external disturbances and measurement noises 22

Robust actuator fault detection for half-car active suspensi...

引用

22nd IEEE International Conference on Industrial Informatics, INDIN 2024

作者： Guo, Xuejie Wang, Jue Sun, Weichao Research Institute of Intelligent Control and Systems Harbin Institute of Technology Harbin China Ningbo Institute of Intelligent Equipment Technology Company Ltd Harbin Institute of Technology Harbin China

ISBN: (纸本)9798331527471

To improve the operational reliability of active suspension system, this paper develops a robust fault detection (FD) method for half-car active suspension system, which is robust to external disturbances and measurement noises. The proposed fault detection approach is developed with the help of a filtering technique. Firstly, the fault detection observer is applied to obtain estimation errors used for actuator fault detection. Then, the residual and detection threshold signals are obtained by filtering estimation errors within a specified frequency range. Specifically, when designing detection thresholds, the filtering technique is introduced to suppress the influence of external disturbances and measurement noises, which helps to reduce the conservatism of detection threshold, resulting in enhancing the ability of fault detection. In addition, the condition of fault detectability, which can quantitatively describe the class of detectable faults, is strictly established. Simulation example is conducted to verify the effectiveness of the proposed robust fault detection method. © 2024 IEEE.

关键词： Active suspension systems

来源：评论

学校读者我要写书评

暂无评论

Robust Data-driven Attitude control for the Hovering Flight of Aerial Manipulator

Robust Data-driven Attitude Control for the Hovering Flight ...

引用

2024 China Automation Congress, CAC 2024

作者： Pang, Bo Li, Zhan Xiu, Bingkai Yang, Yipeng School of Astronautics Harbin Institute of Technology Harbin China Research Institute of Intelligent Control and Systems Harbin Institute of Technology Harbin China

ISBN: (纸本)9798350368604

Coupling disturbances, caused by onboard manipulator’s motion, would bring non-negligible influence to unmanned aerial vehicle. To tackle this problem, this paper introduces an adaptive data-driven attitude architecture that includes dynamic modeling and controller design to achieve the hovering flight of the aerial manipulator. In the modeling part, only input-output data of system is required to identify the dynamics, which reduces the complexity effectively compared to traditional modeling method. In the controller part, a robust attitude control law is designed utilizing identified model to resist coupling disturbances, wherein the disturbances are not supposed to be estimated by additional methods, such as observers. Moreover, the stability of the attitude control system is validated through the Lyapunov criterion. Furthermore, comparative simulations are carried out to showcase the effectiveness of the proposed method. Finally, real-world experiments are tested using our self-built platform. Experimental results demonstrate our method could improve the coupling disturbances suppressing capability effectively. © 2024 IEEE.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

Feature-aided pose estimation approach based on variational auto-encoder structure for spacecrafts

引用

Chinese Journal of Aeronautics 2024年第8期37卷 329-341页

作者： Yanfang LIU Rui ZHOU Desong DU Shuqing CAO Naiming QI Department of Aerospace Engineering Harbin Institute of TechnologyHarbin 150001China Suzhou Research Institute of HIT Suzhou 215104China Shanghai Institute of Spaceflight Control Technology Shanghai 201109China Shanghai Key Laboratory of Aerospace Intelligent Control Technology Shanghai 201109China

Real-time 6 Degree-of-Freedom(DoF)pose estimation is of paramount importance for various on-orbit *** from the development of deep learning,Convolutional Neural Networks(CNNs)in feature extraction has yielded impressive achievements for spacecraft pose *** improve the robustness and interpretability of CNNs,this paper proposes a Pose Estimation approach based on Variational Auto-Encoder structure(PE-VAE)and a Feature-Aided pose estimation approach based on Variational Auto-Encoder structure(FA-VAE),which aim to accurately estimate the 6 DoF pose of a target *** methods treat the pose vector as latent variables,employing an encoder-decoder network with a Variational Auto-Encoder(VAE)*** enhance the precision of pose estimation,PE-VAE uses the VAE structure to introduce reconstruction mechanism with the whole ***,FA-VAE enforces feature shape constraints by exclusively reconstructing the segment of the target spacecraft with the desired *** evaluation against leading methods on public datasets reveals similar accuracy with a threefold improvement in processing speed,showcasing the significant contribution of VAE structures to accuracy enhancement,and the additional benefit of incorporating global shape prior features.

关键词： Pose estimation Variational auto-encoder Feature-aided Pose Estimation Approach On-orbit measurement tasks Simulated and experimental dataset

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：