检索结果-内蒙古大学图书馆

Robust optimization for quantum reinforcement learning control using partial observations

Physical Review A 2022年第6期105卷 062443-062443页

作者： Chen Jiang Yu Pan Zheng-Guang Wu Qing Gao Daoyi Dong State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control College of Control Science and Engineering Zhejiang University Hangzhou 310027 China The School of Automation Science and Electrical Engineering and Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing 100191 China The School of Engineering and Information Technology University of New South Wales Canberra Australian Capital Territory 2600 Australia

The current quantum reinforcement learning control models often assume that the quantum states are known a priori for control optimization. However, full observation of the quantum state is experimentally infeasible due to the exponential scaling of the number of required quantum measurements on the number of qubits. In this paper, we investigate a robust reinforcement learning method using partial observations to overcome this difficulty. This control scheme is compatible with near-term quantum devices, where the noise is prevalent and predetermining the dynamics of the quantum state is practically impossible. We show that this simplified control scheme can achieve similar or even better performance when compared to the conventional methods relying on full observation. We demonstrate the effectiveness of this scheme on examples of quantum state control and the quantum approximate optimization algorithm (QAOA). It has been shown that high-fidelity state control can be achieved even if the noise amplitude is at the same level as the control amplitude. Besides, an acceptable level of optimization accuracy can be achieved for a QAOA with a noisy control Hamiltonian. This robust control optimization model can be trained to compensate for the uncertainties in practical quantum computing.

关键词： Machine learning Quantum control Quantum engineering

来源：评论

学校读者我要写书评

暂无评论

A Tracking control Method based on Event-Triggered Adaptive Dynamic Programming 38

A Tracking Control Method based on Event-Triggered Adaptive ...

引用

第三十八届中国控制会议

作者： Ziyang Wang Qinglai Wei Derong Liu School of Automation and Electrical Engineering University of Science and Technology Beijing The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences School of Automation Guangdong University of Technology

ISBN: (纸本)9781728123295;9789881563972

In this paper, an event-triggered adaptive dynamic programming(ADP) algorithm is developed to solve optimal tracking control problems. The event-triggered control law will be updated only when the triggering conditions are ***, the computational cost can be reduced and the celerity of tracking can be improved. Compared to existing works,novel triggering conditions are designed in this paper. Besides, the stability is guaranteed with less assumption. Neural networks are used to implement the tracking control algorithm. Finally, an example is employed to show the effectiveness of the algorithm.

关键词： Adaptive dynamic programming event-triggered control optimal tracking control

来源：评论

学校读者我要写书评

暂无评论

Efficient Planar Pose Estimation via UWB Measurements

arXiv

引用

arXiv 2022年

作者： Jiang, Haodong Wang, Wentao Shen, Yuan Li, Xinghan Ren, Xiaoqiang Mu, Biqiang Wu, Junfeng China School of Data Science The Chinese University of HongKong Shenzhen China College of Control Science and Engineering The State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China School of Electronic and Optical Engineering Nanjing University of Science and Technology Nanjing China School of Mechatronic Engineering and Automation Shanghai University Shanghai China Key Laboratory of Systems and Control Institute of Systems Science Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China

state estimation is an essential part of autonomous systems. Integrating the Ultra-Wideband (UWB) technique has been shown to correct the long-term estimation drift and bypass the complexity of loop closure detection. However, few works on robotics treat UWB as a stand-alone state estimation solution. The primary purpose of this work is to investigate planar pose estimation using only UWB range measurements. We prove the excellent property of a two-step scheme, which says we can refine a consistent estimator to be asymptotically efficient by one step of Gauss-Newton iteration. Grounded on this result, we design the GN-ULS estimator, which reduces the computation time significantly compared to previous methods and presents the possibility of using only UWB for real-time state estimation. Copyright © 2022, The Authors. All rights reserved.

关键词： state estimation

来源：评论

学校读者我要写书评

暂无评论

Polsar Image Feature Extraction Based on Co-Regularization

Polsar Image Feature Extraction Based on Co-Regularization

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Xiayuan Huang Xiangli Nie Hong Qiao State Key Lab of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728163741

ISBN: (纸本)9781728163758

Wishart distance of covariance matrices and Euclidean distance of polarimetric features are two important similarity measurements for polarimetric synthetic aperture radar (Pol-SAR) image classification. This paper proposes a feature extraction method by combing the two distances for Pol-SAR image classification. Firstly, two weight graphs are constructed based on the two distances to represent the local information of the data. Specifically, the neighbouring samples are sought in a local region to reduce the computation burden and utilize the spatial information. Then the dimensionality reduction model is constructed based on the two weight graphs and co-regularization. The co-regularization aims to minimize the dissimilarity of low-dimensional features corresponding to two graphs. Finally, the obtained low-dimensional features are used for PolSAR image classification. Experimental results on real PolSAR datasets demonstrate the effectiveness and superiority of the proposed method.

关键词： Feature extraction Radar polarimetry Covariance matrices Euclidean distance Dimensionality reduction Measurement Matrix decomposition

来源：评论

学校读者我要写书评

暂无评论

Path Planning Based on Segmented Bezier Curves and A* Algorithm for Mobile Robot

Path Planning Based on Segmented Bezier Curves and A* Algori...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Xiangrui Meng Shuang Liang Zhiqiang Cao Zhonghui Li Shuo Wang State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Information Science Academy China Electronics Technology Group Corporation Beijing China Beijing Engo Technology Co. Ltd Beijing China

ISBN: (纸本)9781665405362

Path planning is an important problem for mobile robot in complex environments. In this paper, an optimized path planning method based on segmented Bezier curves and A* algorithm is proposed. The result of A* algorithm is used to guide the direction of segmented Bezier curves, which fit the A* path. The segmented Bezier curves are generated to meet the requirements of fitting index with the consideration of constraints from the environment and robot itself. The set of the optimized Bezier curves for each segmented A* path is connected end to end and regarded as the result of path planning for the mobile robot. The effectiveness of the proposed method is verified through the experiments.

关键词： Smoothing methods Conferences Biomimetics Fitting Path planning Mobile robots Indexes

来源：评论

学校读者我要写书评

暂无评论

Learning Individual Features to Decompose state Space for Robotic Skill Learning

Learning Individual Features to Decompose State Space for Ro...

引用

Chinese control and Decision Conference, CCDC

作者： Fengyi Zhang Fangzhou Xiong Zhiyong Liu State Key Lab of Management and Control for Complex Systems Institute of Automation Chinese Academy of Science Beijing China

ISBN: (数字)9781728158556

ISBN: (纸本)9781728158563

Due to suffering from the diversity and complexity of robotic tasks in continuous domains, robotic skill learning is the most challenging issue in this area, especially for robots with high-dimensional state spaces. To learn structured policies for continuous control, the graph neural networks (GNN) was previously applied to incorporate explicitly the robot structure into the policy network. In this work, we tackle the problem of robotic skill learning in high-dimensional state space with the help of graph neural networks. Instead of utilizing a general purpose multi-layer perceptron (MLP) as a unified controller to output actions for all joints of the robot, we construct a separate controller for each joint of the robot by using the individual features that have been extracted by GNN model. Empirical results on simulated continuous systems, including applications to PR2 task and Centipede task, demonstrate that the proposed framework can achieve satisfactory learning performance, and more importantly, it significantly reduces the parameters of the policy network.

关键词： Robots Task analysis Aerospace electronics Feature extraction Training Biological neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient Planar Pose Estimation via UWB Measurements

Efficient Planar Pose Estimation via UWB Measurements

引用

IEEE International Conference on Robotics and automation (ICRA)

作者： Haodong Jiang Wentao Wang Yuan Shen Xinghan Li Xiaoqiang Ren Biqiang Mu Junfeng Wu Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS) School of Data Science the Chinese University of HongKong Shenzhen P. R. China College of Control Science and Engineering and the State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou P. R. China School of Electronic and Optical Engineering Nanjing University of Science and Technology Nanjing P. R. China School of Mechatronic Engineering and Automation Shanghai University Shanghai P. R. China Key Laboratory of Systems and Control Institute of Systems Science Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing P. R. China

关键词：

来源：评论

学校读者我要写书评

暂无评论

K-9 Artificial Intelligence Education in Qingdao: Issues, Challenges and Suggestions

K-9 Artificial Intelligence Education in Qingdao: Issues, Ch...

引用

2020 IEEE International Conference on Networking, Sensing and control, ICNSC 2020

作者： Gong, Xiaoyan Tang, Ying Liu, Xiwei Jing, Sifeng Cui, Wei Liang, Joleen Wang, Fei-Yue State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100084 China Institute of Smart Education Systems Qingdao Academy of Intelligent Industries Qingdao266044 China Department of Electrical and Computer Engineering Rowan University GlassboroNJ08028 United States Squirrel Ai Learning Shanghai200030 China

ISBN: (纸本)9781728168531

Nowadays, AI education from Kindergarten to 9th grade(K-9) is in full swing in China, but many challenges exist, such as fragmented AI curricula, ineffective teaching tools, and uneven educational resources in urban and rural areas, etc. So this paper presents an in-depth study of the current status of K-9 AI education in Qingdao area through questionnaires, expert discussions, and field visits to sort out existing problems and then put forward corresponding advice and suggestions. Collected data is then analyzed from the perspectives of government, schools, teachers, students and parents, respectively. Results show that AI-related educational activities have been carried out in Qingdao area to improve students' AI literacy. But efforts are still needed to make such education more systematic, standardized, and personalized. Finally the paper made a list of recommendations corresponding to these needed efforts. © 2020 IEEE.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

A Parallel Framework for Scene Understanding

A Parallel Framework for Scene Understanding

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Wenwen Zhang Jiangong Wang Kunfeng Wang School of Software Engineering Xi'an Jiaotong University Xi'an China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China College of Information Science and Technology Beijing University of Chemical Technology Beijing China

Different related computer vision tasks make it possible to understand and analyze the scene totally. However, there is no useful framework combining different tasks for scene understanding. In this paper, we investigate the current state of scene understanding from different aspects relying on different computer vision tasks and propose an effective framework based on the theory of parallel vision to combine different tasks for scene understanding. With the maintained artificial scene throughout time from the proposed framework, we can understand the scene in an elegant way. To explain our proposed framework, a case study is given.

关键词： Computer vision Digital twin Conferences Task analysis

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Learning from Demonstrations for Long-Horizon Tasks

Hierarchical Learning from Demonstrations for Long-Horizon T...

引用

IEEE International Conference on Robotics and automation (ICRA)

作者： Boyao Li Jiayi Li Tao Lu Yinghao Cai Shuo Wang China Academy of Launch Vehicle Technology Beijing China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai China

Although reinforcement learning (RL) has achieved great success in robotic manipulation skills learning, it is still challenging for long-horizon tasks. Combining RL with demonstrations is an effective solution. In this paper, we propose a novel hierarchical learning from demonstrations method for long-horizon tasks, which leverages (i) object-centered segmentation of demonstrations to automatically segment the teaching trajectories into episodes. (ii) a bi-level hierarchical imitation learning method with a parallel training mechanism to train the two-level policies simultaneously. Experimental results on three challenging long-horizon tasks with sparse rewards show that our proposed method significantly outperforms state-of-art approaches in terms of both sample-efficiency and success rate. Moreover, our method is the only one which achieves satisfactory performance in tasks of multi-object stack and multi-object push&stack.

关键词： Deep learning Training Learning systems automation Conferences Reinforcement learning Trajectory

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：