The overview presents the development and application of Hierarchical Temporal Memory (HTM). HTM is a new machine learning method which was proposed by Jeff Hawkins in 2005. It is a biologically inspired cognitive met...
详细信息
作者:
Chen, ChaoDuan, Xing-GuangWang, Xing-TaoZhu, Xiang-YuLi, MengIntelligent Robotics Institute
Key Laboratory of Biomimetic Robots and Systems Ministry of Education State Key Laboratory of Intelligent Control and Decision of Complex System School of Mechatronical Engineering Beijing Institute of Technology #5Zhongguancun South Street Haidian Beijing China China
As the complex anatomical structure of the maxillofacial region, the surgery in this area is high risk and difficult to implement. Then, a multi-arm medical robot assisted maxillofacial surgery using optical navigatio...
详细信息
Synchronization and pinning control of complex networks is to regulate the agents' behavior and improve network performance. In this article, we review some recent developments in pinning control. Stability algori...
详细信息
Aiming at the problems of registration error and synthetic movement ghost which are caused by moving objects in image mosaicing, a mosaicing algorithm for dynamic scene using multi-scale pyramid histogram of oriented ...
详细信息
Aiming at the problems of registration error and synthetic movement ghost which are caused by moving objects in image mosaicing, a mosaicing algorithm for dynamic scene using multi-scale pyramid histogram of oriented gradients (PHOG) and optimal seam is proposed. Firstly, a new feature, multi-scaled PHOG, is generated by introducing PHOG to multi-scale space corner detections. The feature is used to align images for avoiding the local impact caused by moving objects in image registration. Then, an optimal seam, guaranteeing the minimum difference in geometry and gray value, is searched by graph cut algorithm through constructing an energy function to remove the movement ghost. The experimental results show that the proposed algorithm is efficient in dealing with the problems of image mosaicing with moving objects, and the mosaicing results are satisfactory with high precision.
A new concept of word-cell is introduced. It evolves from the concepts of footprint of uncertainty (FOU) of interval type-2 fuzzy set and sets-as-points geometric view of fuzzy sets. The word-cell can be graphically i...
详细信息
Compared with the traditional two-dimensional (2D) deployment form, three-dimensional (3D) deployment of sensor network has greater research significance and practical potential to satisfy the detecting needs of targe...
详细信息
Compared with the traditional two-dimensional (2D) deployment form, three-dimensional (3D) deployment of sensor network has greater research significance and practical potential to satisfy the detecting needs of targets with complex properties. In this paper, a method for 3D deployment optimization of sensor network based on an improved Particle Swarm Optimization (PSO) algorithm is proposed. Many factors such as coverage scale, detection probability and resource utilization are synthetically considered to optimize the sensor network's overall detection performance. To evaluate the network's performance, four indexes are presented and the 3D deployment space is divided into different height levels. Accordingly, the mathematical model is formulated by weighting the performance indexes and height levels due to their importance degrees. In order to solve the optimization problem, an algorithm called WCPSO is carried out, which has a dynamic inertia weight and adaptable acceleration constants. Verified by the simulation results, the presented 3D deployment optimization method effectively improves the sensor network's detection performance. The method in this paper can provide guidance and technical reference in future application of relevant research.
A small humanoid robot with a teleoperation system using 3G communication network is present in this paper. Considering the requirement of dynamic environment and hardware limitations of small humanoid, the teleoperat...
详细信息
ISBN:
(纸本)9781467321259
A small humanoid robot with a teleoperation system using 3G communication network is present in this paper. Considering the requirement of dynamic environment and hardware limitations of small humanoid, the teleoperation system was designed using 3G communication network, which has a good performance both on the long-distance operation and the communication speed. Then an improved walking planning method is explored on this robot. Most of conventional walking planning methods can not fit to the low computation performance of small humanoid nor the real-time teleoperation requirement. In order to solve this problem, an online walking planning method with has been presented in this paper. There are two primary advantages compared with conventional walking planning methods. First, the new online walking planning can realize walking based on real-time tasks due to its short control period. Secondly, the reduced computation and walking data can fit to the hardware limit of the small humanoid. The effectiveness of the proposed walking planning method was confirmed by experiments.
作者:
Zhongjing MaSchool of Automation
Beijing Institute of Technology (BIT) and the Key Laboratory of Complex System Intelligent Control and Decision (BIT) Ministry of Education
Optimal charging control of large-population autonomous plug-in electric vehicles (PEVs) in power grid can be formulated as a class of constrained non-linear timevariant optimization problems. To overcome the computat...
详细信息
Optimal charging control of large-population autonomous plug-in electric vehicles (PEVs) in power grid can be formulated as a class of constrained non-linear timevariant optimization problems. To overcome the computational complexity of this class of optimization problems, the author and his collaborators proposed a game-based decentralized control method such that individual agents update their best charging strategies simultaneously with respect to a common electricity price signal which is determined by the total demand in the grid. Due to the heterogeneity of individual PEVs, the game systems converge to a nearly valley-fill NE strategy with nontrivial deviation costs due to the heterogeneity property of individual PEV charging characteristics. In this paper the author proposed a novel algorithm to implement the optimal decentralized valley fill strategies for the charging problems of the PEV population which is composed of disjoint homogeneous subpopulations. The author introduces a cost which penalizes against the deviation of strategy of individual agent in a subpopulation from the average value of the subpopulation. It can be shown that in case that the update algorithm converges, the system reaches the optimal valley-fill equilibrium strategy where the introduced agent deviation cost vanishes. Simulation examples are used to illustrate the results developed in this paper.
—In this paper, a synchronization of discrete multi-agent systems with random network delays was studied. By employing the graph and matrix theory, a model based predictive control algorithm is proposed to achieve le...
详细信息
—In this paper, a synchronization of discrete multi-agent systems with random network delays was studied. By employing the graph and matrix theory, a model based predictive control algorithm is proposed to achieve leader-following consensus in a network of agents. Furthermore, a consensus protocol is developed based on this strategy. Numerical simulation examples are provided to illustrate the effectiveness of the theoretical results.
Networked air defense fire control simulation system featured with complicated interactions, varied system structure etc, and is usually faced with some difficulties in its development, such as the low capability of m...
详细信息
Networked air defense fire control simulation system featured with complicated interactions, varied system structure etc, and is usually faced with some difficulties in its development, such as the low capability of model reuse, the lack of regulations for model development and inflexible modification of federation. To overcome the difficulties, a framework in hierarchy of networked air defense fire control simulation system is constructed according to BOM development standard, and the component method for designing the basic model, compound model and federate is proposed, which effectively improved the efficiency of system development and the capability of model reuse. This method is not only applicable to the design of networked air defense fire controlsystem, but also to the design of other simulation system with polytropic structure.
暂无评论