This work addresses the active planning of robot navigation tasks for 3D scene exploration. 3D scene exploration is an old and difficult task in robotics. In this paper, we present a strategy to guide a mobile autonom...
详细信息
This work addresses the active planning of robot navigation tasks for 3D scene exploration. 3D scene exploration is an old and difficult task in robotics. In this paper, we present a strategy to guide a mobile autonomous robot equipped with a camera in order to autonomously explore the unknown 3D scene. By merging the particle filter into 3D scene exploration, we address the robot navigation problem in a heuristic way, and generate a sequence of camera poses to coverage the unknown 3D scene. First, we randomly generate a bunch of potential camera pose vectors. Then, we select the vectors through our criteria. After determining the first camera pose vector, we generate the next group of vectors based on the former one. We select the new camera pose vector and thereafter. We verify the algorithm theoretically and show the good performance in the simulation environment.
Amplitude calibration of the quartz tuning fork (QTF) sensor includes the measurement of the sensitivity factor (αTF). We propose, AFM based methods (cantilever tracking and z-servo tracking of the QTF's amplitud...
详细信息
Based on backstepping control technique,a novel adaptive integrated guidance and control(IGC) law is presented for missile intercepting maneuvering target with input *** deal with the uncertainties in the IGC system,a...
详细信息
ISBN:
(纸本)9781538629185
Based on backstepping control technique,a novel adaptive integrated guidance and control(IGC) law is presented for missile intercepting maneuvering target with input *** deal with the uncertainties in the IGC system,adaptive control technique is utilized to estimate the upper bounds of the ***,an auxiliary system is designed to cope with the input *** state of the auxiliary system is used in the IGC law design and stability *** detailed stability analysis of the closed-loop IGC system is carried out based on the Lyapunov ***,the effectiveness of the proposed adaptive IGC law is verified by the nonlinear numerical simulation results.
Detecting and grasping objects in unstructured environments is an important yet difficult task. Fortunately, the breakthroughs from deep convolutional networks stimulate the development of object detection and graspin...
详细信息
Rail fasteners, a key component of a railway track, are used to connect the rail and the sub-rail foundation together with the required degree of elasticity. Severely loose or failed fasteners may lead to serious safe...
详细信息
ISBN:
(纸本)9781538694091;9781538694084
Rail fasteners, a key component of a railway track, are used to connect the rail and the sub-rail foundation together with the required degree of elasticity. Severely loose or failed fasteners may lead to serious safety hazards for rail transportation. However, current strategies for determining fastener looseness are mainly implemented manually, which is labor-intensive, inefficient and less-than-objective. In this paper, we propose a system that uses a MEMS acceleration meter and a wireless data transmission technique to detect railway fasteners. Vibration was generated by hitting the rail with a hammer. Then the acceleration data was transmitted to the cloud by the Global System for Mobile Communications (GSM) technique. The fastener looseness was analyzed using power spectrum entropy and frequency domain analysis. Results from the field experiments show that our method can identify the fastener's loosening state accurately and automatically. This wireless, low-cost fastener inspection system is expected to provide an effective approach to improving the efficiency of regular railway maintenance..
This paper reports a novel electrochemical method for the detection of insulin in ultra-pure water. A screen printed electrode (SPE) modified by Nickel hydroxide was used as the working electrode, one with good activi...
详细信息
ISBN:
(纸本)9781538694091;9781538694084
This paper reports a novel electrochemical method for the detection of insulin in ultra-pure water. A screen printed electrode (SPE) modified by Nickel hydroxide was used as the working electrode, one with good activity of electro-catalytic oxidation-reduction for insulin. The SPE was modified by Nickel hydroxide using the electrodeposition method. The results showed that Nickel hydroxide was homogeneously electrodeposited on the surface of the working electrode. A coin-size electrolytic tank was fabricated with PDMS, which only requires 0.3ml of sample for the detection. The concentration of insulin was analyzed using the methods of Cyclic voltammetry (CV), Electrochemical impedance spectroscopy (EIS) and Chronoamperometry (i-t). The Nickel hydroxide used for detecting insulin showed good analytical characteristics, such as a high sensitivity of 14.797μA·μM -1 , a good linear detection range of 100nM-5μM, and a low detection limit of 93nM. This nickel hydroxide modified SPE electrode has a much smaller size and is easier to fabricate than traditional electrodes, making it a much more promising candidate for an insulin sensor.
The development of machine learning in complex system is hindered by two problems *** first problem is the inefficiency of exploration in state and action space,which leads to the data-hungry of some state-of-art data...
详细信息
The development of machine learning in complex system is hindered by two problems *** first problem is the inefficiency of exploration in state and action space,which leads to the data-hungry of some state-of-art data-driven *** second problem is the lack of a general theory which can be used to analyze and implement a complex learning *** this paper,we proposed a general methods that can address both two *** combine the concepts of descriptive learning,predictive learning,and prescriptive learning into a uniform framework,so as to build a parallel system allowing learning system improved by *** a new perspective of data,knowledge and action,we provide a new methodology called parallel learning to design machine learning system for real-world problems.
Many algorithms of mobile robot SLAM(Simultaneous Localization and Mapping) have been researched at present,however,the SLAM algorithm of mobile robot based on probability is often used in the unknown *** this paper,t...
详细信息
ISBN:
(纸本)9781509065769;9781509065752
Many algorithms of mobile robot SLAM(Simultaneous Localization and Mapping) have been researched at present,however,the SLAM algorithm of mobile robot based on probability is often used in the unknown *** this paper,two kinds of SLAM algorithms based on probability are analyzed and *** kind is the SLAM algorithm based on Kalman filter: extended Kalman filter SLAM(EKF-SLAM)and unscented Kalman filter SLAM algorithm(UKF-SLAM).Another kind is the SLAM algorithm based on Particle filter:Fast SLAM and unscented Fast SLAM(UFast SLAM) *** difference from the four algorithms of SLAM is illustrated in terms of principle and calculation ***,the simulation results show that the UFast SLAM algorithm is superior to other algorithms in robot path and landmark estimation.
This paper investigates the robustness issue of stochastic nonlinear network controlsystems (NCSs) with network-induced delays and packet dropouts. Firstly, the controller for the nominal system (without network-indu...
详细信息
This paper presents a back propagation (BP) neural network method to identify fault types and phases in the smart grid with renewable sources. A fault classification method based on the BP neural network is used to id...
详细信息
This paper presents a back propagation (BP) neural network method to identify fault types and phases in the smart grid with renewable sources. A fault classification method based on the BP neural network is used to identify patterns of voltage and current measured with phasor measurement unit (PMU). The voltage and current values are decomposed, and then they are used as the input matrix of the BP neural network, which identifies the fault type and fault phasor. All the common short-circuit faults occurred are analyzed, BP neural network method is proposed for fault classification in a power active distribution network. Simulation results show feasibility and usefulness of the BP neural network method, which provides good classification performances.
暂无评论