检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Chai, Jiajun Li, Weifan Zhu, Yuanheng Zhao, Dongbin Ma, Zhe Sun, Kewu Ding, Jishiyu State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Xlab The Second Academy of CASIC Beijing100854 China

Multi-agent reinforcement learning methods such as VDN, QMIX, and QTRAN that adopt centralized training with decentralized execution (CTDE) framework have shown promising results in cooperation and competition. However, in some multi-agent scenarios, the number of agents and the size of action set actually vary over time. We call these unshaped scenarios, and the methods mentioned above fail in performing satisfyingly. In this paper, we propose a new method called Unshaped Networks for Multi-Agent systems (UNMAS) that adapts to the number and size changes in multi-agent systems. We propose the self-weighting mixing network to factorize the joint action-value. Its adaption to the change in agent number is attributed to the nonlinear mapping from each-agent Q value to the joint action-value with individual weights. Besides, in order to address the change in action set, each agent constructs an individual action-value network that is composed of two streams to evaluate the constant environment-oriented subset and the varying unit-oriented subset. We evaluate UNMAS on various StarCraft II micro-management scenarios and compare the results with several state-of-the-art MARL algorithms. The superiority of UNMAS is demonstrated by its highest winning rates especially on the most difficult scenario 3s5z-vs-3s6z. The agents learn to perform effectively cooperative behaviors while other MARL algorithms fail in. Copyright © 2022, The Authors. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Data-Based Online Optimal control for Multi-player Nonlinear Non-zero-Sum Games Using Recursive Least Squares

Data-Based Online Optimal Control for Multi-player Nonlinear...

引用

Chinese automation Congress (CAC)

作者： Gaofu Yang Ruizhuo Song Qinglai Wei School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665426480

In this paper, optimal control of nonlinear systems for non-zero-sum games is solved with a data-based and recursive least square. The new adjustment law is similar to experience replay algorithm which refer history data and the covariance matrix is introduced for storing historical data, which can avoid the waste of space and time caused by storing a large amount of historical data and collecting data. In tuning process, we use a discount factor which shows how trust to the collected data to guide adjustment law to update the weight. Meanwhile, discount factor can avoid the covariance matrix tending to zero due to accumulation of data. After that, the convergence of the weight is analyzed. Finally, using a simulation to verify the effectiveness of the tuning law.

关键词： automation Optimal control Games Reinforcement learning History Nonlinear systems Covariance matrices

来源：评论

学校读者我要写书评

暂无评论

Development and path planning of a novel unmanned surface vehicle system and its application to exploitation of Qarhan Salt Lake

引用

Science China(Information Sciences) 2019年第8期62卷 195-197页

作者： Zhibin XUE Jincun LIU Zhengxing WU Sheng DU Shihan KONG Junzhi YU College of Chemical Engineering Qinghai University State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences University of Chinese Academy of Sciences

Qarhan Salt Lake is rich in mineral resources, such as sodium chloride, potassium, and magnesium [1].At present, liquid mine exploiting is the main exploitation form for the Qarhan Salt Lake. Salt mining ships with mining equipments are widely used to exploit carnallite which is located at the bottom of pools. Conventionally, workmen utilize rude ferric sampler to collect carnallite samples

关键词： USV simulation Development and path planning of a novel unmanned surface vehicle system and its application to exploitation of Qarhan Salt Lake

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning Benchmark for Autonomous Driving in Intersection Scenarios

A Reinforcement Learning Benchmark for Autonomous Driving in...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Yuqi Liu Qichao Zhang Dongbin Zhao The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781728190495

In recent years, control under urban intersection scenarios has become an emerging research topic. In such scenarios, the autonomous vehicle confronts complicated situations since it must deal with the interaction with social vehicles timely while obeying the traffic rules. Generally, the autonomous vehicle is supposed to avoid collisions while pursuing better efficiency. The existing work fails to provide a framework that emphasizes the integrity of the scenarios while deploying and testing reinforcement learning(RL) methods. Specifically, we propose a benchmark for training and testing RL-based autonomous driving agents in complex intersection scenarios, which is called RL-CIS. Then, a set of baselines consisting various algorithms are deployed. The test benchmark and baselines provide a fair and comprehensive training and testing platform for the study of RL for autonomous driving in the intersection scenario, advancing RL-based methods for autonomous driving control. The code of our proposed framework can be found at https://***/liuyufi123/complexUrbanScenarios.

关键词： Training Codes Stochastic processes Reinforcement learning Benchmark testing Sampling methods Concrete

来源：评论

学校读者我要写书评

暂无评论

Double deep Q-learning for anti-saturation attack problem of warship group 1

Double deep Q-learning for anti-saturation attack problem of...

引用

1st IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2021

作者： Li, Wei Xiong, Gang Tao, Hao Han, Yunjun Wang, Fang Dong, Xisong Shen, Zhen Institute of Automation Chinese Academy of Sciences State Key Laboratory for Management and Control of Complex Systems China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences China China Ship Development and Design Center Wuhan430064 China Shandong University Jinan China

ISBN: (纸本)9781665433372

Anti-saturation attack (ASA) strategy is vital for the survival of a warship group, and attracts the focus of many researchers. In this paper, the dynamics of ASA is formulated as a Markov Decision Process (MDP) with an enhanced states space since those characters are involved, such as the formation and detection and interception areas of warship group. A reinforcement learning method (Double Deep Q-leaning, DDQN) is developed to solve the problem and deal with the curse of dimensionality whereby the cost-to-go value is calculated by a marine engagement simulation system. A heuristic defense algorithm guided by field expert knowledge is designed for comparison. The experimental results show that the DDQN method performs better in anti-saturation attack scenarios. © 2021 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

MixedFusion: 6D Object Pose Estimation from Decoupled RGB-Depth Features

MixedFusion: 6D Object Pose Estimation from Decoupled RGB-De...

引用

International Conference on Pattern Recognition

作者： Hangtao Feng Lu Zhang Xu Yang Zhiyong Liu The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences

Estimating the 6D pose of objects is an important process for intelligent systems to achieve interaction with the real-world. As the RGB-D sensors become more accessible, the fusion-based methods have prevailed, since the point clouds provide complementary geometric information with RGB values. However, due to the difference in feature space between color image and depth image, the network structures that directly perform point-to-point matching fusion do not effectively fuse the features of the two. In this paper, we propose a simple but effective approach, named MixedFusion. Different from the prior works, we argue that the spatial correspondence of color and point clouds could be decoupled and reconnected, thus enabling a more flexible fusion scheme. By performing the proposed method, more informative points can be mixed and fused with rich color features. Extensive experiments are conducted on the challenging LineMod and YCB-Video datasets, which shows that our method significantly boosts the performance without introducing extra overheads. Furthermore, when the minimum tolerance of metric narrows, the proposed approach performs better for the high-precision demands.

关键词： Measurement Three-dimensional displays Image color analysis Fuses Pose estimation Color Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A reinforcement learning benchmark for autonomous driving in intersection scenarios

arXiv

引用

arXiv 2021年

作者： Liu, Yuqi Zhang, Qichao Zhao, Dongbin The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

In recent years, control under urban intersection scenarios becomes an emerging research topic. In such scenarios, the autonomous vehicle confronts complicated situations since it must deal with the interaction with social vehicles timely while obeying the traffic rules. Generally, the autonomous vehicle is supposed to avoid collisions while pursuing better efficiency. The existing work fails to provide a framework that emphasizes the integrity of the scenarios while being able to deploy and test reinforcement learning(RL) methods. Specifically, we propose a benchmark for training and testing RL-based autonomous driving agents in complex intersection scenarios, which is called RL-CIS. Then, a set of baselines are deployed consists of various algorithms. The test benchmark and baselines are to provide a fair and comprehensive training and testing platform for the study of RL for autonomous driving in the intersection scenario, advancing the progress of RL-based methods for intersection autonomous driving control. The code of our proposed framework can be found at https://***/liuyuqi123/complexUrbanScenarios. Copyright © 2021, 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

Knowledge-Enhanced Natural Language Inference Based on Knowledge Graphs 28

Knowledge-Enhanced Natural Language Inference Based on Knowl...

引用

28th International Conference on Computational Linguistics, COLING 2020

作者： Wang, Zikang Li, Linjing Zeng, Daniel State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Shenzhen China

ISBN: (纸本)9781952148279

Natural Language Inference (NLI) is a vital task in natural language processing. It aims to identify the logical relationship between two sentences. Most of the existing approaches make such inference based on semantic knowledge obtained through training corpus. The adoption of background knowledge is rarely seen or limited to a few specific types. In this paper, we propose a novel Knowledge Graph-enhanced NLI (KGNLI) model to leverage the usage of background knowledge stored in knowledge graphs in the field of NLI. KGNLI model consists of three components: a semantic-relation representation module, a knowledge-relation representation module, and a label prediction module. Different from previous methods, various kinds of background knowledge can be flexibly combined in the proposed KGNLI model. Experiments on four benchmarks, SNLI, MultiNLI, SciTail, and BNLI, validate the effectiveness of our model. © 2020 COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Adaptive Fusional Localization for Robot Fish Based on Dynamic-weight Fuzzy Inference

Adaptive Fusional Localization for Robot Fish Based on Dynam...

引用

Chinese automation Congress (CAC)

作者： Yuzhuo Fu Xiaocun Liao Ben Lu Qianqian Zou Zhuoliang Zhang Yaming Ou Chao Zhou State Key Laboratory of Management and Control for Complex Systems Institute of Automation CAS Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665426480

Accurate localization of robots in a specific environment often requires the cooperation of multiple sensors, and how to establish a more general data fusion model is always a difficult problem. For the localization of robot fish in an indoor pool environment, this paper proposes an adaptive fusional algorithm based on fuzzy inference of dynamic weights. This paper firstly constructs a confidence probability table of sensors’ signals based on the calibration data sets of BLE and UWB nodes at different distances, as the basis for updating the weights of the BLE or UWB nodes; secondly, the data obtained by each node in a single sampling period in the robot fish movement is vectorized to form a judgment matrix, and then the estimated distance is obtained by fuzzy inference together with the sensor weight; finally, the coordinates are calculated by the four-point positioning method. In this paper, more than 40 sets of experiments have been carried out with a simplified carangidae-like robot fish. The results show that the average positioning error is about 0.189m, which is 88.3% and 31.8% lower than that of using BLE only and using UWB only. In this paper, the fusional positioning method based on statistics combines the advantages of different sensors to reduce the data scale and achieve data denoising while fusing sensor data, which provides a reference for indoor positioning of robot fish and multi-sensor data fusion.

关键词： Location awareness Fuzzy logic Robot kinematics Heuristic algorithms Data integration Sensor fusion Probability

来源：评论

学校读者我要写书评

暂无评论

A Prototype-Based Generalized Zero-Shot Learning Framework for Hand Gesture Recognition

A Prototype-Based Generalized Zero-Shot Learning Framework f...

引用

International Conference on Pattern Recognition

作者： Jinting Wu Yujia Zhang Xiaoguang Zhao School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences

Hand gesture recognition plays a significant role in human-computer interaction for understanding various human gestures and their intent. However, most prior works can only recognize gestures of limited labeled classes and fail to adapt to new categories. The task of Generalized Zero-Shot Learning (GZSL) for hand gesture recognition aims to address the above issue by leveraging semantic representations and detecting both seen and unseen class samples. In this paper, we propose an end-to-end prototype-based GZSL framework for hand gesture recognition which consists of two branches. The first branch is a prototype-based detector that learns gesture representations and determines whether an input sample belongs to a seen or unseen category. The second branch is a zero-shot label predictor which takes the features of unseen classes as input and outputs predictions through a learned mapping mechanism between the feature and the semantic space. We further establish a hand gesture dataset that specifically targets this GZSL task, and comprehensive experiments on this dataset demonstrate the effectiveness of our proposed approach on recognizing both seen and unseen gestures.

关键词： Human computer interaction Target recognition Semantics Prototypes Human-robot interaction Gesture recognition Detectors

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：