检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Li, Depeng Wang, Tianqi Xu, Bingrong Kawaguchi, Kenji Zeng, Zhigang Suganthan, Ponnuthurai Nagaratnam The School of Artificial Intelligence and Automation The Institute of Artificial Intelligence Huazhong University of Science and Technology The Key Laboratory of Image Processing and Intelligent Control Education Ministry of China Wuhan430074 China The School of Automation Wuhan University of Technology Wuhan430070 China The School of Computing National University of Singapore 117417 Singapore The School of Electrical and Electronic Engineering Nanyang Technological University Singapore639798 Singapore The KINDI Center for Computing Research College of Engineering Qatar University Doha Qatar

Continual learning can incrementally absorb new concepts without interfering with previously learned knowledge. Motivated by the characteristics of neural networks, in which information is stored in weights on connections, we investigated how to design an Innately Forgetting-Free Network (IF2Net) for continual learning context. This study proposed a straightforward yet effective learning paradigm by ingeniously keeping the weights relative to each seen task untouched before and after learning a new task. We first presented the novel representation-level learning on task sequences with random weights. This technique refers to tweaking the drifted representations caused by randomization back to their separate task-optimal working states, but the involved weights are frozen and reused (opposite to well-known layer-wise updates of weights). Then, sequential decision-making without forgetting can be achieved by projecting the output weight updates into the parsimonious orthogonal space, making the adaptations not disturb old knowledge while maintaining model plasticity. IF2Net allows a single network to inherently learn unlimited mapping rules without telling task identities at test time by integrating the respective strengths of randomization and orthogonalization. We validated the effectiveness of our approach in the extensive theoretical analysis and empirical study. Copyright © 2023, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

End-to-end Driving in High-Interaction Traffic Scenarios with Reinforcement Learning

arXiv

引用

arXiv 2024年

作者： Li, Yueyuan Jiang, Mingyang Zhang, Songan Yuan, Wei Wang, Chunxiang Yang, Ming The Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China The Global Institute of Future Technology Shanghai Jiao Tong University Shanghai200240 China The Innovation Center of Intelligent Connected Vehicles Global Institute of Future Technology Shanghai Jiao Tong University Shanghai200240 China

Dynamic and interactive traffic scenarios pose significant challenges for autonomous driving systems. Reinforcement learning (RL) offers a promising approach by enabling the exploration of driving policies beyond the constraints of pre-collected datasets and predefined conditions, particularly in complex environments. However, a critical challenge lies in effectively extracting spatial and temporal features from sequences of high-dimensional, multi-modal observations while minimizing the accumulation of errors over time. Additionally, efficiently guiding large-scale RL models to converge on optimal driving policies without frequent failures during the training process remains tricky. We propose an end-to-end model-based RL algorithm named Ramble to address these issues. Ramble processes multi-view RGB images and LiDAR point clouds into low-dimensional latent features to capture the context of traffic scenarios at each time step. A transformer-based architecture is then employed to model temporal dependencies and predict future states. By learning a dynamics model of the environment, Ramble can foresee upcoming traffic events and make more informed, strategic decisions. Our implementation demonstrates that prior experience in feature extraction and decision-making plays a pivotal role in accelerating the convergence of RL models toward optimal driving policies. Ramble achieves state-of-the-art performance regarding route completion rate and driving score on the CARLA Leaderboard 2.0, showcasing its effectiveness in managing complex and dynamic traffic situations. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Model Predictive control for A Three-Phase Inverter with Output LC Filter

Event-Triggered Model Predictive Control for A Three-Phase I...

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Benfei WANG Jingjing HUANG Jose RODRIGUEZ Cristian GARCIA Guodong FENG School of Intelligent Systems Engineering Sun Yat-sen University Guangdong China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai China School of Electronic and Information Engineering Xi’an Jiaotong University Xi’an China Engineering School Universidad Andrés Bello Santiago Chile Engineering Faculty Universidad de Talca Curico Chile

ISBN: (数字)9781728151694

ISBN: (纸本)9781728151700

This paper proposes an event-triggered model predictive control (ET-MPC) method for the three-phase inverter with output LC filter. The proposed method is developed by combining the conventional finite-control-set MPC (FCS-MPC) method and the ET control strategy. The ET control strategy incorporates a preset triggering condition based on the requirement of the regulation performance for the three-phase inverter. When the state of the three-phase inverter activates the triggering condition, FCS-MPC is triggered with the updated state so that the optimal control actions can be generated when it is necessary. If the state of the inverter is within the preset triggering condition, FCS-MPC is suspended and the control actions are held as constant. Consequently, the unnecessary online prediction, online optimization, and the corresponding control actions can be avoided. Therefore, with the tolerate regulation performance, the proposed ET-MPC can reduce the computational burden of the conventional FCS-MPC. The various simulation studies of the three-phase inverter are conducted and discussed to demonstrate the effectiveness of the proposed ET-MPC method.

关键词： Computational modeling Simulation Switches Inverters Regulation Optimization Predictive control

来源：评论

学校读者我要写书评

暂无评论

Quantum gyroscopes based on double-mode surface-acoustic-wave cavities

arXiv

引用

arXiv 2024年

作者： Zhu, Yuting Xue, Shibei Ju, Fangfang Yuan, Haidong Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Shatin Hong Kong School of Physics and Electronics Hunan Normal University Changsha410081 China

Recent progress shows that a surface-acoustic-wave (SAW) cavity can not only induce quantum acoustic dynamics but also can form optomechanical-like systems. Its operating frequencies in the microwave band make it resistant to the thermal noise of surrounding environments, while its radiation-pressure couplings make it susceptible to weak forces. Based on these advantages, we propose a gyroscope comprising coupled microwave-SAW cavities. In this paper, we systematically consider the three indices including range, signal-to-noise ratio, and sensitivity, which are the most important to gyroscopes but only partially considered in existing works. Additionally, we establish the fundamental limits of sensitivity when the quantum input is in the vacuum state and the squeezed vacuum state. We find that squeezing improves sensitivity and can surpass the standard quantum limit. However, this improvement can only reach up to √2/2 even as the squeezed parameter approaches infinity, which is rarely noted in recent works. Finally, we also offer analytical constraints for cooperativity and squeezed parameters. These constraints can be utilized to design gyroscopes based on coupled cavities in experiments. Copyright © 2024, The Authors. All rights reserved.

关键词： Gyroscopes

来源：评论

学校读者我要写书评

暂无评论

Unequal Error Protection Rateless Codes for Spatial Audio Transmission

Unequal Error Protection Rateless Codes for Spatial Audio Tr...

引用

International Conference on Communication Technology (ICCT)

作者： Junpeng Yin Yusun Fu Haobo Huang Jinhui Tang Ningbo Artificial Intelligence Institute Shanghai Jiao Tong University Ningbo China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China School of Electronic Information and Electrical Engineering the Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350363760

ISBN: (纸本)9798350363777

Spatial audio is an important component of the metaverse. With the rapid increase of the spatial resolution and the number of objects, the data volume of the spatial side information has grown larger. However, the low bit rate transmission of spatial side information in the object-based audio coding methods leads to the low-quality reconstruction of spatial side information with limited bandwidth. To address this issue, this paper constructs a cascade design of spatial audio coding and unequal error protection (UEP) rateless codes. Furthermore, the further protection of specific spatial side information is proposed for different scenarios, which effectively addresses the limitation of traditional spatial audio coding in side information protection. For the situation where the code length K of different importance levels is different, we propose an adaptive degree distribution (ADD), adding K to the selection probability as an influencing factor, which has better performance than other degree distribution for short code length. ADD is used to replace the multiple degree distribution strategy of the traditional unequal error protection scheme, and the block error rate (BER) is reduced nearly 10 times compared with the traditional scheme.

关键词： Codes Error analysis Metaverse Distribution strategy Spatial audio Bit rate Symbols Communications technology Protection Spatial resolution

来源：评论

学校读者我要写书评

暂无评论

Lite-HRPE: A 6DoF Object Pose Estimation Method for Resource-Limited Platforms

Lite-HRPE: A 6DoF Object Pose Estimation Method for Resource...

引用

International Conference on control and Automation (ICCA)

作者： Xin Liu Qi Guan Shibei Xue Dezong Zhao Department of Automation Shanghai Jiao Tong University Shanghai P. R. China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai P. R. China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai P. R. China James Watt School of Engineering University of Glasgow Glasgow U.K.

ISBN: (数字)9798350354409

ISBN: (纸本)9798350354416

Accurately estimating the six-degree-of-freedom pose of objects is essential for intelligent robotics. Although significant progress has been made in this area, most studies fail to account for specific hardware limitations for model deployment, which remains a major challenge for resource-constrained scenarios. To address this issue, we propose Lite-HRPE, a lightweight RGB-based pose estimation method, which leverages a multi-branch parallel structure to extract spatial and semantic information of key points for pose estimation. Additionally, Lite-HRPE adopts the G-block and G-neck modular structure and streamlines the original feature extraction network to realize a compact network structure. This allows Lite-HRPE to strike a balance between pose estimation accuracy, parameter count, computational load, and runtime speed. Our evaluation on public datasets shows that Lite-HRPE achieves a 95.7% accuracy with only 10.8% of the number of parameters and 11.8% of the FLOPs compared to Hybridpose.

关键词： Training Accuracy Runtime Pose estimation Semantics Feature extraction Real-time systems

来源：评论

学校读者我要写书评

暂无评论

A New Island Genetic Algorithm for Path Planning Problems *

A New Island Genetic Algorithm for Path Planning Problems *

引用

IEEE International Conference on Real-time Computing and Robotics (RCAR)

作者： Jinghao Zhang Zhe Chen Ning Li Department of Automation Shanghai Jiao Tong University Shanghai P. R. China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai P. R. China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai P. R. China Department of Automation Tsinghua University Beijing P. R. China

Genetic algorithm (GA) is an effective method for path planning problems. As a powerful variant of GA, island genetic algorithm (IGA) has considerable improvement in performance. In this paper, a new island model of GA is proposed to avoid the premature phenomenon and achieve better efficiency. First, a new method of creating subpopulations is presented based on K-means to expand the searching area for the optima. Meanwhile, recombining subpopulations is proposed as a new strategy to improve the diversity of populations and save computational time. Moreover, a method is designed based on Monte Carlo sampling to handle the uncertainty of maps. Comparative experiments are presented to verify the efficiency of the proposed algorithm. Then, a proper number of samples is found by simulation to balance the accuracy and the time cost of Monte Carlo sampling.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Federated Multi-Agent Deep Reinforcement Learning Approach via Physics-Informed Reward for Multi-Microgrid Energy Management

arXiv

引用

arXiv 2022年

作者： Li, Yuanzheng He, Shangyang Li, Yang Shi, Yang Zeng, Zhigang School of Artificial Intelligence and Automation Key Laboratory on Image Information Processing and Intelligent Control of Ministry of Education Huazhong University of Science and Technology Wuhan430074 China China-Belt and Road Joint Laboratory on Measurement and Control Technology Wuhan430074 China China-EU Institute for Clean and Renewable Energy Huazhong University of Science and Technology Wuhan430074 China School of Electrical Engineering Northeast Electric Power University Jilin132012 China The Department of Mechanical Engineering University of Victoria VictoriaBC V8P 5C2 Canada

The utilization of large-scale distributed renewable energy promotes the development of the multi-microgrid (MMG), which raises the need of developing an effective energy management method to minimize economic costs and keep self energy-sufficiency. The multi-agent deep reinforcement learning (MADRL) has been widely used for the energy management problem because of its real-time scheduling ability. However, its training requires massive energy operation data of microgrids (MGs), while gathering these data from different MGs would threaten their privacy and data security. Therefore, this paper tackles this practical yet challenging issue by proposing a federated multi-agent deep reinforcement learning (F-MADRL) algorithm via the physics-informed reward. In this algorithm, the federated learning (FL) mechanism is introduced to train the F-MADRL algorithm thus ensures the privacy and the security of data. In addition, a decentralized MMG model is built, and the energy of each participated MG is managed by an agent, which aims to minimize economic costs and keep self energy-sufficiency according to the physics-informed reward. At first, MGs individually execute the self-training based on local energy operation data to train their local agent models. Then, these local models are periodically uploaded to a server and their parameters are aggregated to build a global agent, which will be broadcasted to MGs and replace their local agents. In this way, the experience of each MG agent can be shared and the energy operation data is not explicitly transmitted, thus protecting the privacy and ensuring data security. Finally, experiments are conducted on Oak Ridge national laboratory distributed energy control communication lab microgrid (ORNL-MG) test system, and the comparisons are carried out to verify the effectiveness of introducing the FL mechanism and the outperformance of our proposed F-MADRL. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

image retrieval based on color features integrated with anisotropic directionality

引用

Journal of Systems Engineering and Electronics 2010年第1期000卷

作者： Jing Bai Xiaohua Wang and Licheng Jiao key laboratory of intelligent Perception and image Understanding of ministry of education of China Institute of intelligent Information processing Xidian University Xi’an 710071 P. R. China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Institute of Intelligent Information Processing Xidian UniversityXi'an 710071P. R. China

A novel image retrieval approach based on color features and anisotropic directional information is proposed for content based image retrieval systems (CBIR). The color feature is described by the color histogram (CH), which is translation and rotation invariant. However, the CH does not contain spatial information which is very important for the image retrieval. To overcome this shortcoming, the subband energy of the lifting directionlet transform (L-DT) is proposed to describe the directional information, in which L-DT is characterized by multi-direction and anisotropic basis functions compared with the wavelet transform. A global similarity measure is designed to implement the fusion of both color feature and anisotropic directionality for the retrieval process. The retrieval experiments using a set of COREL images demonstrate that the higher query precision and better visual effect can be achieved.

关键词： image retrieval color histogram directionlet transform anisotropic similarity

来源：评论

学校读者我要写书评

暂无评论

A unified leader-follower scheme for mobile robots with uncalibrated on-board camera

A unified leader-follower scheme for mobile robots with unca...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Dejun Guo Hesheng Wang Weidong Chen Ming Liu Zeyang Xia Kam K. Leang DARC (Design Automation Robotics & Control) Lab University of Utah Robotics Center Salt Lake City Utah USA State Key Laboratory of Robotics and System (HIT) Key Laboratory of System Control and Information Processing Ministry of Education of China Department of Automation Shanghai Jiao Tong University Shanghai China Department of Electronics and Computer Engineering Hong Kong University of Science and Technology Hong Kong China Institute of Biomedical and Health Engineering Chinese Academy of Sciences Shenzhen China

This paper studies the problem of image-based leader-follower formation control for mobile robots, where the controller is designed independently of the leader's motion. An adaptive control scheme, which is suitable for both omnidirectional and perspective cameras, is proposed. The proposed approach avoids the need for accurate calibration of the extrinsic parameters of the omnidirectional camera as well as the intrinsic and extrinsic parameters of perspective camera. Additionally, the coefficients of the plane where the feature point moves relative to the camera frame can be uncertain. These uncertain constant parameters are estimated using an adaptive estimator. Uniform Semi-global Practical Asymptotic Stability (USPAS) of the system is shown using the Lyapunov approach. Experimental results are presented to demonstrate the effectiveness of the proposed control scheme.

关键词： Cameras Robot vision systems Kinematics Mobile robots Calibration Automation

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：