Motived by that clustering by fast search and find of density peaks algorithm (CFSFDP) could not select the cluster center automatically, an improved CFSFDP algorithm was presented. The improved method uses the weight...
详细信息
Motived by that clustering by fast search and find of density peaks algorithm (CFSFDP) could not select the cluster center automatically, an improved CFSFDP algorithm was presented. The improved method uses the weighted average method and calculates the weighted averages of center weight for each point as the screening indices of cluster center. The data point will be selected as cluster center if its center weight is greater than the calculated weighted average. With aforesaid method, the improved algorithm could select the cluster center automatically, and effectively avoid the err by human made according to the decision graph. Simulation experiments comparing with K-means and CFSFDP on 4 kinds of UCI datasets are shown that the improved algorithm could retain the accurate and fast characteristics of CFSFDP and select the cluster center automatically.
In this paper, we propose and investigate a new Eulerprecision 3-node g-proportional finite difference formula [also named Zhang finite difference(ZFD) formula 3 NgPFDG], which achieves an error patte
ISBN:
(纸本)9781467389808
In this paper, we propose and investigate a new Eulerprecision 3-node g-proportional finite difference formula [also named Zhang finite difference(ZFD) formula 3 NgPFDG], which achieves an error patte
Ordinary differential equations(ODEs) are commonly used in physical system and automation researches,describing the relationship among *** there are practical significances to discuss and to research the solutions of ...
详细信息
Ordinary differential equations(ODEs) are commonly used in physical system and automation researches,describing the relationship among *** there are practical significances to discuss and to research the solutions of *** initial value problem(IVP) is one of the important parts,and we usually use traditional methods,*** method,to obtain the *** this paper,we propose a new method named ZFD(Zhang finite difference) 4IgSFD
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 e...
详细信息
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.
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 entertain...
详细信息
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.
This paper studies the problem of image-based leader-follower formation control for mobile robots, where the controller is designed independently of the leader's motion. An adaptive control scheme, which is suitab...
详细信息
This paper studies the problem of image-based leader-follower formation control for mobile robots, where the controller is designed independently of the leader's motion. An adaptive control scheme, which is suitable for both omnidirectional and perspective cameras, is proposed. The proposed approach avoids the need for accurate calibration of the extrinsic parameters of the omnidirectional camera as well as the intrinsic and extrinsic parameters of perspective camera. Additionally, the coefficients of the plane where the feature point moves relative to the camera frame can be uncertain. These uncertain constant parameters are estimated using an adaptive estimator. Uniform Semi-global Practical Asymptotic Stability (USPAS) of the system is shown using the Lyapunov approach. Experimental results are presented to demonstrate the effectiveness of the proposed control scheme.
In modern engineering researches, dynamics of systems are often studied by well-design computer simulations,and these dynamics are usually depicted in the form of vectoror matrix-valued ordinary differential equation(...
详细信息
ISBN:
(纸本)9781509013463
In modern engineering researches, dynamics of systems are often studied by well-design computer simulations,and these dynamics are usually depicted in the form of vectoror matrix-valued ordinary differential equation(ODE) systems.A common approach for solution of matrix-valued ODE in MATLAB is to use the Kronecker product and vectorization technique. However, the vectorization procedure may be troublesome, and it can be difficult if not impossible to vectorize a complicated matrix-valued ODE(especially when it is nonlinear).Differing from the traditional approach, this paper proposes an elegant, compact and effective tool(named MatrixO DE)for solving a matrix-valued ODE with arbitrary right hand side. As a complement and extension of the built-in solvers in MATLAB, the proposed MatrixO DE tool allows solving a matrix-valued ODE using matrix language directly, i.e., users do not need to perform matrix-vector transformations. Application of the proposed MatrixO DE tool to online time-varying matrix inversion further substantiates its effectiveness for matrix-valued ODE solving.
This paper investigates the output-tracking control of time-varying linear（TVL） *** that the input is always limited in a range due to actuator physical constraints or energy-saving *** combining the Zhang dynamics...
详细信息
ISBN:
(纸本)9781509009107
This paper investigates the output-tracking control of time-varying linear（TVL） *** that the input is always limited in a range due to actuator physical constraints or energy-saving *** combining the Zhang dynamics（ZD） and the sigmoid function,an effective controller,termed sigmoid function aided ZD（SFAZD） controller,is designed for tracking the TVL *** verifications substantiate that the proposed SFAZD controller can achieve accurate tracking results,and limit the input in the range during the tracking process.
By applying the gradient dynamics(GD) and Zhang dynamics(ZD) to the motion planning and control for redundant robot manipulators at the joint-jerk level,three novel types of inverse-free solutions,namely Z2G1 type,Z1G...
详细信息
ISBN:
(纸本)9781509009107
By applying the gradient dynamics(GD) and Zhang dynamics(ZD) to the motion planning and control for redundant robot manipulators at the joint-jerk level,three novel types of inverse-free solutions,namely Z2G1 type,Z1G2 type and Z0G3 type,are thus proposed,developed and investigated in this *** solutions only need to calculate the transpose of Jacobian matrix rather than the complex pseudo-inverse of Jacobian matrix,more efficiently resolving the complicated time-varying inverse-kinematics(IK) problem for robot ***,the path-tracking applications based on a 4-link robot manipulator show that the manipulator's motion is pretty smooth,fully illustrating the effectiveness,accuracy and superiority of such inverse-free ***,it is the first time for the researchers to propose a relatively complete inverse-free solution framework at the joint-jerk *** proposed approaches can provide effective solutions to the motion planning and control at different levels(e.g.,the joint-velocity,joint-acceleration and joint-jerk levels),having a wider application range and also obtaining a perfect tracking performance for redundant robot manipulators.
The future of control in cyberspace of parallel worlds is discussed. It argues for the coming age of control 5.0,the control technology for the new IT capable of dealing with artificial worlds with VR, AR, AI and robo...
详细信息
The future of control in cyberspace of parallel worlds is discussed. It argues for the coming age of control 5.0,the control technology for the new IT capable of dealing with artificial worlds with VR, AR, AI and robotics. The discipline of automation needs a new interpretation of its core knowledge and skill set of modeling, analysis, and control for cyber-socialphysical systems, and a paradigm shift from Newtonian systems with Newton's Laws or Big Laws with Small Data to Mertonian systems with Merton's Laws or Small Laws with Big Data.
暂无评论