检索结果-内蒙古大学图书馆

IEEE Transactions on intelligent Vehicles 2024年第9期9卷 1-8页

作者： Chen, Shiyu Li, Yanjie Lou, Yunjiang Lin, Ke Wu, Xinyu Department of Control Science and Engineering Harbin Institute of Technology Shenzhen and Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics Shenzhen China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

With the increasing requirement for agile and efficient controllers in safety-critical scenarios, controllers that exhibit both agility and safety are attracting attention, especially in the aerial robotics domain. This paper focuses on the safety issue of Reinforcement Learning (RL)-based control for agile quadrotor flight in restricted environments. To this end, we propose a unified Adaptive Safety Predictive Corrector (ASPC) to certify each output action of the RL-based controller in real-time, ensuring its safety while maintaining agility. Specifically, we develop the ASPC as a finite-horizon optimal control problem, formulated by a variant of Model Predictive control (MPC). Given the safety constraints determined by the restricted environment, the objective of minimizing loss of agility can be optimized by reducing the difference between the actions of RL and ASPC. As the safety constraints are decoupled from the RL-based control policy, the ASPC is plug-and-play and can be incorporated into any potentially unsafe controllers. Furthermore, an online adaptive regulator is presented to adjust the safety bounds of the state constraints with respect to the environment changes, extending the proposed ASPC to different restricted environments. Finally, simulations and real-world experiments are demonstrated in various restricted environments to validate the effectiveness of the proposed ASPC. IEEE

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Level Robotic Pouring Using Offline Reinforcement Learning

Multi-Level Robotic Pouring Using Offline Reinforcement Lear...

引用

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Zhang, Xiaoxiong Liu, Junwei Zhang, Wei School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen Key Laboratory of Control Theory and Intelligent Systems Shenzhen518055 China

ISBN: (纸本)9781665481090

This paper presents a novel learning-based method for a robotic manipulator to achieve liquid pouring across different liquid levels using only visual sensors. Previous works have relied on either online reinforcement learning or imitation learning, which are limited by sim-to-real gaps or data efficiency. In this paper, we propose to combine supervised learning and offline reinforcement learning, utilizing a human demonstration dataset containing only successful pouring at the highest level. Specifically, our approach employs supervised learning for a visual classifier, transforming the visual input into a categorical distribution over liquid levels. The offline reinforcement learning method is applied to a binary-conditioned control policy, which takes a binary signal and the robot's proprioception as inputs to determine the action. The binary signal indicates whether the desired liquid level has been reached based on the target liquid level. Through experiments, our method demonstrates superior effectiveness compared to a state-of-the-art imitation learning algorithm. Moreover, tests in unseen scenarios and multiple liquid level commands verify the generalization and transferability of our approach. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Compression Format and Systolic Array Structure Co-design for Accelerating Sparse Matrix Multiplication in DNNs 24th

Compression Format and Systolic Array Structure Co-design f...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Cao, Yongxiang Jiang, Jixiang Zhao, Guocheng Wang, Wei Jiang, Hongxu Song, Yanfei School of Computer Science and Engineering Beihang University Beijing China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (纸本)9789819615445

The systolic array (SA) architecture is widely used in accelerator/AI chip design due to its excellent matrix multiplication acceleration effect. However, the mismatch between the traditional sparse matrix compression format and the SA architecture results in poor SA performance in computing sparse matrices. To solve the problem, we propose a method for co-designing the sparse compression format and SA architecture. This work proposes the Vector Group Compressed Coordinate (VGCC) data stream compression format and designs a sparse SA architecture based on hardware encoding and decoding. VGCC can handle data streams of any size without increasing the index bit width. The VGCC compression size is significantly smaller than general sparse compression formats such as COO/CSR. In a sparse matrix with a sparsity of 90%, it saves 67.13% of storage space compared to the state-of-the-art ECOO data stream compression format and achieves an average acceleration of 1.54 times. We also propose a VGCC-friendly SA architecture. Our SA architecture engine reduces logic consumption by 51.6% compared to Sparse TPU while achieving a 3.23x speedup. To mitigate the issue of high no-load rates in systolic arrays, we introduce a Data Transmission Priority (DTP) data matching algorithm. With sparsity levels ranging from 50% to 90%, the algorithm’s calculation speed is enhanced by 1.124x to 1.991x. We implemented a sparse DNN accelerator on an FPGA Zynq UltraScale+MPSoC ZCU102, utilizing the VGCC compression format proposed in this study for compressing input data. When compared to the S2 Engine, the accelerator achieved a 3.37x speed improvement in matrix multiplication with 75% sparsity, significantly enhancing the speed of sparse matrix multiplication. The accelerator achieved an average throughput of 1079.33GOP/s when inferencing DNNs. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Systolic arrays

来源：评论

学校读者我要写书评

暂无评论

EPM-Net: A better way for optical and infrared scene matching via edge point 12

EPM-Net: A better way for optical and infrared scene matchin...

引用

SPIE 12th International Symposium on Multispectral Image Processing and Pattern Recognition, MIPPR 2023

作者： Huang, Shixiang Chi, Longyun Fu, Wenxing Tian, Jinwen National Key Laboratory of Multispectral Information Intelligent Processing Technology Huazhong University of Science and Technology Wuhan China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (数字)9781510674943

ISBN: (纸本)9781510674936

As a crucial auxiliary technique in inertial navigation, scene matching has been widely applied in aircraft navigation and guidance. To enhance the adaptability and efficiency of scene matching algorithms in complex environments, existing approaches have gradually shifted towards heterogeneous scene matching, such as optical/ infrared scene matching based on deep learning features, with a focus on point features. However, due to the complex and diverse nonlinear distortions between optical and infrared images, the matching accuracy often fails to meet the practical requirements of navigation and positioning. In view of this problem, an EPM-Net algorithm based on edge features is proposed to improve matching performance by extracting more stable and discriminative edge point descriptors. Experimental results on infrared datasets demonstrate that this method achieves an average matching accuracy improvement of more than four times compared to traditional and existing deep learning methods. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Distributed Cooperative Search Based on DRH-NSGA Under Communication Constraint

Distributed Cooperative Search Based on DRH-NSGA Under Commu...

引用

International Conference on Guidance, Navigation and control, ICGNC 2022

作者： Si, Jia Shuai Cheng, Jin Hao, Ming Rui Liu, Zhen Chang Science and Technology On Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (纸本)9789811966125

For unmanned aerial vehicle (UAV) cooperative search mission under communication distance limitation environment, considering that the computation scale of rolling time domain optimization increases exponentially with the change of predicted steps and the problem that searching performance metrics are difficult to be selected, the distributed receding horizon non-dominated sorting genetic algorithm (DRH-NSGA) is proposed, and the distributed receding horizon (DRH) process is optimized by non-dominated sorting genetic algorithm (NSGA),and the cooperative search problem in dynamic environment is solved. Firstly, the motion and sensor models of UAV are established. Considering the possibility of interference or communication interruption during UAV communication, the communication interruption probability is added based on the communication distance constraint. In this paper, the environment awareness map is constructed, considering the motion characteristics of time-sensitive targets, and based on the updating of target probability by using Bayesian theory, the updating of time-sensitive target prediction transition probability is added to improve the accuracy of moving target existence probability map. Finally, the search performance index is designed reasonably, and the RH framework is used to optimize the search path. The simulation results show that the distributed cooperative search algorithm based on DRH-NSGA can shorten the single step planning time while ensuring the convergence speed and ensure the real-time decision-making of UAV search. At the same time, it can effectively take into account the search of moving targets after covering the search area. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Multi-UAV Cooperative Path-Planning under Complex Threat Environment 42

Multi-UAV Cooperative Path-Planning under Complex Threat Env...

引用

42nd Chinese control Conference, CCC 2023

作者： Liu, Zhenchang Liu, Yuting Zhao, Hongyin Lu, Hanchen Hao, Mingrui Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (纸本)9789887581543

This paper proposes a cooperative path-planning method based on multi-Dubins path segments to meet the penetration requirements of UAVs in a complex threat environment. A pruning strategy is used in path-planning to sift path segments, and the diversity of threat avoidance paths is considered under a reasonable calculation amount. A threat intrusion strategy is designed for no safety path condition, which makes the cooperative path-planning method have excellent robustness. A cooperative path optimization method based on particle swarm optimization is adopted for the path length and collision avoidance requirements. The simulation results show that the UAV cooperative paths can avoid the threat area under any starting and ending points, and path lengths are close to the expected length. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Research Status and Application of Mission Assignment Method and Cooperative Positioning and Navigation for Cluster Aircraft

Research Status and Application of Mission Assignment Method...

引用

International Conference on Guidance, Navigation and control, ICGNC 2022

作者： Danting, Sheng Mingrui, Hao Science and Technology On Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (纸本)9789811966125

In order to solve the problem of multi-aircraft cluster cooperative combat, this paper tries to classify and sum up the existing achievements on task assignment method and cooperative positioning and navigation. Among the distributed methods of task allocation, the contract net-based method of task allocation and the distributed method of simulating the complex and orderly collective behavior of social creatures are briefly described. According to the method of cooperative positioning of swarm aircraft, it is divided into measuring the relative distance of aircraft, measuring the relative angle of aircraft and layered cooperative navigation system. Combining with the classical research and application, this paper analyzes and summarizes the existing task allocation methods and the achievements of cooperative positioning and navigation, and forecasts the future engineering application in this field. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Aircraft

来源：评论

学校读者我要写书评

暂无评论

Design and simulation of a two-stage linear inverted pendulum control system based on fuzzy LQR control 7

Design and simulation of a two-stage linear inverted pendulu...

引用

7th International Symposium on Autonomous systems, ISAS 2024

作者： Peng, Siting Ren, Jun Li, Lei Ma, Yichao Song, Zhichao The Beijing Electro-Mechanical Engineering Institute Science and Technology On Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (纸本)9798350363173

This paper introduces in detail the origin of the development of automatic control methods, applications and current research hotspots. It also introduces some control methods commonly used in industrial and agricultural production, and expounds the current application hotspots and new advanced control methods that are developing rapidly. The background, current situation and classification of the inverted pendulum platform are introduced in detail. In the first chapter, the LQR method in modern control theory is introduced in detail. The influence of parameters is analyzed through simulink space modeling and simulation control experiment. At the same time, the real-time experiment is also done in combination with the hardware platform. In the second chapter, the fuzzy control theory in intelligent control is introduced in detail. By combining fuzzy control with LQR method, suitable LQR parameters are calculated by pole assignment. After proper adjustment, reasonable fuzzy rules are adopted and adaptive fuzzy control principle is applied to adjust the control situation in real time. Using simulink space modeling, a good simulation control effect is obtained. Finally, the summary is made. © 2024 IEEE.

关键词： Fuzzy control

来源：评论

学校读者我要写书评

暂无评论

Vibration-Based Fault Diagnosis for Railway Point Machines Using VMD and Multiscale Fluctuation-Based Dispersion Entropy

引用

Chinese Journal of Electronics 2024年第3期33卷 803-813页

作者： Yongkui SUN Yuan CAO Peng LI Guo XIE Tao WEN Shuai SU National Engineering Research Center of Rail Transportation Operation and Control System Beijing Jiaotong University School of Electronic and Information Engineering Beijing Jiaotong University Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Frontiers Science Center for Smart High-speed Railway System Beijing Jiaotong University

As one of the most important railway signaling equipment,railway point machines undertake the major task of ensuring train operation *** fault diagnosis for railway point machines becomes a hot *** the advantage of the anti-interference characteristics of vibration signals,this paper proposes an novel intelligent fault diagnosis method for railway point machines based on vibration signals.A feature extraction method combining variational mode decomposition(VMD) and multiscale fluctuation-based dispersion entropy is developed,which is verified a more effective tool for feature ***,a two-stage feature selection method based on Fisher discrimination and ReliefF is proposed,which is validated more powerful than single feature selection ***,support vector machine is utilized for fault *** comparisons show that the proposed method performs *** diagnosis accuracies of normal-reverse and reverse-normal switching processes reach 100% and 96.57% ***,it is a try to use new means for fault diagnosis on railway point machines,which can also provide references for similar fields.

关键词： Fault diagnosis Railway point machine Vibration signal Variational mode decomposition Two-stage feature selection

来源：评论

学校读者我要写书评

暂无评论

Low-carbon Economic Dispatch of Integrated Energy systems Considering Extended Carbon Emission Flow

引用

Journal of Modern Power systems and Clean Energy 2024年第6期12卷 1798-1809页

作者： Yumin Zhang Pengkai Sun Xingquan Ji Fushuan Wen Ming Yang Pingfeng Ye Shandong University of Science and Technology Qingdao 266590China Hainan Institute Zhejiang UniversitySanya 572000China School of Electrical Engineering Zhejiang UniversityHangzhou 310027China Key Laboratory of Power System Intelligent Dispatch and Control Shandong UniversityJinan 250061China

Carbon capture and storage(CCS)systems can provide sufficient carbon raw materials for power-to-gas(P2G)systems to reduce the carbon emission of traditional coal-fired units,which helps to achieve low-carbon dispatch of integrated energy systems(IESs).In this study,an extended carbon-emis-sion flow model that integrates CCS-P2G coordinated operation and low-carbon characteristics of an energy storage system(ESS)is *** the energy supply side,the coupling rela-tionship between CCS and P2G systems is established to realize the low-carbon economic operation of P2G *** the en-ergy storage side,the concept of"state of carbon"is introduced to describe the carbon emission characteristics of the ESS to ex-ploit the potential of coordinated low-carbon dispatch in terms of both energy production and *** addition,a low-car-bon economic dispatch model that considers multiple uncertain-ties,including wind power output,electricity price,and load de-mands,is *** solve the model efficiently,a parallel multidimensional approximate dynamic programming algo-rithm is adopted,while the solution efficiency is significantly im-proved over that of stochastic optimization without losing solu-tion accuracy under a multilayer parallel loop nesting *** low-carbon economic dispatch method of IESs is composed of the extended carbon emission flow model,low-car-bon economic dispatch model,and the parallel multidimension-al approximate dynamic programming *** effective-ness of the proposed method is verified on E14-H6-G6 and E57-H12-G12 systems.

关键词： Low-carbon economic dispatch carbon emission flow state of carbon parallel multidimensional approximate dynamic programming integrated energy system(IES)

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：