检索结果-内蒙古大学图书馆

2017 IEEE International Conference on robotics and Automation, ICRA 2017

作者： Liao, Yiyi Huang, Lichao Wang, Yue Kodagoda, Sarath Yu, Yinan Liu, Yong State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Zhejiang310027 China Horizon Robotics Inc. Beijing and Shenzhen China University of Technology Sydney Australia

ISBN: (纸本)9781509046331

Many standard robotic platforms are equipped with at least a fixed 2D laser range finder and a monocular camera. Although those platforms do not have sensors for 3D depth sensing capability, knowledge of depth is an essential part in many robotics activities. Therefore, recently, there is an increasing interest in depth estimation using monocular images. As this task is inherently ambiguous, the data-driven estimated depth might be unreliable in robotics applications. In this paper, we have attempted to improve the precision of monocular depth estimation by introducing 2D planar observation from the remaining laser range finder without extra cost. Specifically, we construct a dense reference map from the sparse laser range data, redefining the depth estimation task as estimating the distance between the real and the reference depth. To solve the problem, we construct a novel residual of residual neural network, and tightly combine the classification and regression losses for continuous depth estimation. Experimental results suggest that our method achieves considerable promotion compared to the state-of-the-art methods on both NYUD2 and KITTI, validating the effectiveness of our method on leveraging the additional sensory information. We further demonstrate the potential usage of our method in obstacle avoidance where our methodology provides comprehensive depth information compared to the solution using monocular camera or 2D laser range finder alone. © 2017 IEEE.

关键词： robotics

来源：评论

学校读者我要写书评

暂无评论

Visual Place Recognition in Long-term and Large-scale Environment based on CNN Feature

Visual Place Recognition in Long-term and Large-scale Enviro...

引用

IEEE Intelligent Vehicles Symposium

作者： Jianliang Zhu Yunfeng Ai Bin Tian Dongpu Cao Sebastian Scherer School of Artificial Intelligence University of Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Department of Mechanical & Mechatronics Engineering University of Waterloo Robotics Institute Carnegie Mellon University

ISBN: (纸本)9781538644539

With the universal application of camera in intelligent vehicles, visual place recognition has become a major problem in intelligent vehicle localization. The traditional solution is to make visual description of place images using hand-crafted feature for matching places, but this description method is not very good for extreme variability, especially for seasonal transformation. In this paper, we propose a new method based on convolutional neural network (CNN), by putting images into the pre-trained network model to get automatically learned image descriptors, and through some operations of pooling, fusion and binarization to optimize them, then the similarity result of place recognition is presented with the Hamming distance of the place sequence. In the experimental part, we compare our method with some state-of-the-art algorithms, FABMAP, ABLE-M and SeqSLAM, to illustrate its advantages. The experimental results show that our method based on CNN achieves better performance than other methods on the representative public datasets.

关键词： Hamming distance Intelligent vehicles binarization Recognition (Psychology) Visualization network model Cameras images

来源：评论

学校读者我要写书评

暂无评论

Research on the optimal dispatch of wind power consumption based on combined heat and power with thermal energy storage

引用

Energy Procedia 2018年 152卷 978-983页

作者： Ding Liu Chuanzhi Zang Peng Zeng Shenyang Institute of Automation Chinese Academy of Sciences Shenyang 110016 P.R. China Key Laboratory of Networked Control Systems Chinese Academy of Sicences Shenyang 110016 P.R. China University of Chinese Academy of Sciences Beijing 100049 P.R. China

In this paper, a hierarchical scheduling framework is proposed to dispatch electricity and thermal in CHP system with thermal energy storage for the consumption of wind power. An optimization mathematical model is proposed to demonstrate the characteristics of the whole system. The modified PSO algorithm is used to solve the coordinated dispatching problem. The traditional way of working between electricity and thermal is independent while the proposed mathematical model combined electricity and thermal, it’s more accurate to take the relationship between electricity and thermal into consideration. This model has good performance in solving the cross coupling problem. The simulation results indicate that the proposed optimization mathematical model has good dispatching performance on reducing coal consumption. The most important contribution of this paper are accelerating the consumption of wind power in Northern China and saving coal consumption, which can save plenty of money and prevent air pollution. Further work will be reflected in the demonstration project.

关键词： combined heat power wind power consumption thermal energy storage optimal dispatch PSO algorithm

来源：评论

学校读者我要写书评

暂无评论

An Infinite-Dimensional Luenberger-like Observer for Water Waves

An Infinite-Dimensional Luenberger-like Observer for Water W...

引用

第37届中国控制会议

作者： Yang YU Hai-Long PEI Cheng-Zhong XU Key Laboratory of Autonomous Systems and Networked Control Ministry of EducationUnmanned Aerial Vehicle Systems Engineering Technology Research Center of GuangdongCollege of Automation Science and EngineeringSouth China University of Technology LAGEP Batiment CPEUniversity Claude Bernard-Lyon 1

The paper deals with the observation problem by using an infinite dimensional observer for the water wave system governed by linearized water wave partial differential *** consider that the water wave system evolves in some infinitedimensional Hilbert *** output measurement of dynamical system is supposed to be the water wave surface *** infinite-dimensional exponentially convergent Luenberger-like observer is proposed to estimate the states of water water system:water velocity potential and surface *** simulations by the finite difference scheme are carried out to validate the proposed observer.

关键词： infinite dimension system observer convergence finite difference method

来源：评论

学校读者我要写书评

暂无评论

Real-time 3D human tracking for mobile robots with multisensors

Real-time 3D human tracking for mobile robots with multisens...

引用

2017 IEEE International Conference on robotics and Automation, ICRA 2017

作者： Wang, Mengmeng Su, Daobilige Shi, Lei Liu, Yong Miro, Jaime Valls State Key Laboratory Institute of Cyber-Systems and Control Zhejiang University Zhejiang310027 China University of Technology Sydney Australia

ISBN: (纸本)9781509046331

Acquiring the accurate 3-D position of a target person around a robot provides fundamental and valuable information that is applicable to a wide range of robotic tasks, including home service, navigation and entertainment. This paper presents a real-time robotic 3-D human tracking system which combines a monocular camera with an ultrasonic sensor by the extended Kalman filter (EKF). The proposed system consists of three sub-modules: monocular camera sensor tracking model, ultrasonic sensor tracking model and multi-sensor fusion. An improved visual tracking algorithm is presented to provide partial location estimation (2-D). The algorithm is designed to overcome severe occlusions, scale variation, target missing and achieve robust re-detection. The scale accuracy is further enhanced by the estimated 3-D information. An ultrasonic sensor array is employed to provide the range information from the target person to the robot and Gaussian Process Regression is used for partial location estimation (2-D). EKF is adopted to sequentially process multiple, heterogeneous measurements arriving in an asynchronous order from the vision sensor and the ultrasonic sensor separately. In the experiments, the proposed tracking system is tested in both simulation platform and actual mobile robot for various indoor and outdoor scenes. The experimental results show the superior performance of the 3-D tracking system in terms of both the accuracy and robustness. © 2017 IEEE.

关键词： Ultrasonic sensors

来源：评论

学校读者我要写书评

暂无评论

Composite Learning for Trajectory Tracking control of Robot Manipulators with Output Constraints

Composite Learning for Trajectory Tracking Control of Robot ...

引用

International Conference on Information Science and Technology (ICIST)

作者： Dianye Huang Chenguang Yang Yongping Pan Shilu Dai Zhaojie Ju Key Laboratory of Autonomous Systems and Networked Control College of Automation Science and Engineering South China University of Technology Guangzhou China Department of Biomedical Engineering National University of Singapore Singapore Singapore School of Computing University of Portsmouth Portsmouth UK

In this paper, a trajectory tracking scheme for robot manipulators with unknown dynamics is investigated, with the consideration of output constraints as well as small bounded external disturbances. Firstly, a modified backstepping control scheme is employed to control the robot manipulators where in the first step of the design a tan-type barrier Lyapunov candidate is chosen in order to tackle the constraint problem. Secondly, the philosophy of dynamic surface control is incorporated to implement the calculation of prediction errors, which can also reduce “explosion of complexity” of the backstepping scheme. In addition, composite learning is introduced for a better estimation of unknown parameters, and for canceling out the uncertainties of the robot manipulators. Stability analysis shows that the proposed control scheme guarantees a small bounded tracking error with parameter convergence in the absence of the stringent persistent excitation condition. Finally, a simulation is conducted and the results demonstrate the superiority of the proposed controller in the aspects of tracking capability and parameter estimation.

关键词： Manipulator dynamics Backstepping Uncertainty control systems Convergence

来源：评论

学校读者我要写书评

暂无评论

Adaptive control of a Marine Vessel Based on Reinforcement Learning

Adaptive Control of a Marine Vessel Based on Reinforcement L...

引用

第37届中国控制会议

作者： Zhao Yin Wei He Changyin Sun Guang Li Chenguang Yang School of Automation and Electrical Engineering University of Science and Technology Beijing School of Automation Southeast University Queen Mary University of London Key Laboratory of Autonomous Systems and Networked Control College of Automation Science and Engineering South China University of Technology

In this paper, our main goal is to solve optimal control problem by using reinforcement learning（RL） algorithm for marine surface vessel system with known dynamic. And this algorithm is an optimal control algorithm based on policy iteration（PI）, and it can obtain the suitable approximations of cost function and the optimized control policy. There are two neural networks（NNs）, where critic NN aims to estimate the cost-to-go and actor NN is utilized to design suitable input controller and minimize the tracking error. A novel tuning method is given for critic NN and actor NN. The stability and convergence are proven by Lyapunov’s direct method. Finally, the numerical simulations are conducted to demonstrate the feasibility and superiority of presented algorithm.

关键词： Reinforcement Learning Critic Neural Networks Actor Neural Networks Lyapunov Method Marine Vessel

来源：评论

学校读者我要写书评

暂无评论

Euler-precision formula ZD3NgyP-Z applied to discrete control simulation of agitation tank

Euler-precision formula ZD3NgyP-Z applied to discrete contro...

引用

2017 Chinese Automation Congress, CAC 2017

作者： Zhang, Yunong Zhang, Jianxin Ding, Yaqiong Gong, Huihui Li, Jian Guangzhou510006 China Key Laboratory of Autonomous Systems and Networked Control Ministry of Education Guangzhou510640 China SYSU-CMU Shunde International Joint Reseach Institute Foshan528300 China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou510006 China

ISBN: (纸本)9781538635247

In this paper, a new type of Euler-precision 3-node g-proportional (3NgP) formula is proposed and investigated in the general framework of Zhang discretization (ZD), which is named formula ZD3NgPZ with subtype Z corresponding to the second (as well as student) coauthor. By Taylor expansion, we prove that formula ZD3NgPZ approximating the fst-order derivative can achieve an error pattern of O(g). Numerical experiments of approximation are conducted to show the efficacy of the formula. In the meanwhile, formula ZD3NgPZ is used in the discrete control and simulation of agitation tank system. Finally, numerical experiments of discretization are conducted and analyzed to illustrate the efficacy and accuracy of formula ZD3NgPZ applied to agitation tank system. © 2017 IEEE.

关键词： Tanks (containers)

来源：评论

学校读者我要写书评

暂无评论

Two-Layer Predictive control of the Copper Smelting Process Blowed by Enriched Oxygen at Bottom 7

Two-Layer Predictive Control of the Copper Smelting Process ...

引用

7th IEEE Annual International Conference on CYBER Technology in Automation, control, and Intelligent systems, CYBER 2017

作者： Bin, Wang Zhuo, Wang Haibin, Yu Yang, Jia Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China

ISBN: (纸本)9781538604892

Due to the nonlinearity, coupling, and delay during the copper smelting process blowed by enriched oxygen at bottom, a novel two-layer predictive control scheme is presented. The objective of the scheme is to minimize the cost of the material. The two-layer predictive control method achieves the steady-state optimal setpoints and resolves the multivariable dynamic control problems synchronously. Industrial test results show that the two-layer predictive control strategy leads to a significant improvement of control performance, as compared to manual controller within a multiloop framework. © 2017 IEEE.

关键词： Oxygen

来源：评论

学校读者我要写书评

暂无评论

Visual Place Recognition in Long-term and Large-scale Environment based on CNN Feature

Visual Place Recognition in Long-term and Large-scale Enviro...

引用

2018 IEEE Intelligent Vehicles Symposium, IV 2018

作者： Zhu, Jianliang Ai, Yunfeng Tian, Bin Cao, Dongpu Scherer, Sebastian School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100190 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Cloud Computing Center Chinese Academy of Sciences Dongguan523808 China Department of Mechanical and Mechatronics Engineering University of Waterloo WaterlooONN2L 3G1 Canada Robotics Institute Carnegie Mellon University PittsburghPA15213 United States

ISBN: (纸本)9781538644522

关键词： Hamming distance

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：