Jason Jianjun Gu

Learn More
This paper proposes a computationally efficient method for traffic sign recognition (TSR). This proposed method consists of two modules: 1) extraction of histogram of oriented gradient variant (HOGv) feature and 2) a single classifier trained by extreme learning machine (ELM) algorithm. The presented HOGv feature keeps a good balance between redundancy and(More)
Autonomous vehicle navigation with standard IMU and differential GPS has been widely used for aviation and military applications. Our research interesting is focused on using some low-cost off-the-shelf sensors, such as strap-down IMU, inexpensive single GPS receiver. In this paper, we present an autonomous vehicle navigation method by integrating the(More)
Kinematics is the study of motion without regard to the forces that create it. Generally, kinematics for robot manipulators includes two problems, forward kinematics problem and inverse kinematics problem. Because of the complexity of inverse kinematics, it is difficult to find the solutions for it. This paper applies a self-configuration fuzzy system to(More)
We address the problem of globally consistent estimation of the trajectory of a robot arm moving in three dimensional space based on a sequence of binocular stereo images from a stereo camera mounted on the tip of the arm. Correspondence between 3D points from successive stereo camera positions is established through matching of 2D SIFT features in the(More)
For Internet-based tele-robotic systems (Intemet robots). the most challenging and distinct dzflculties are associated with Internet transmission delays, delay jitter and not-guaranteed bandwidth availability, which might lead to dramatic perjormance degradation or even instabilip. In this paper, a new approach fa dealing with these problems is explored and(More)
The problem of image Gaussian noise filtering in the framework of Pulse Coupled Neural Network (PCNN) time matrix is addressed. The time matrix, generated by PCNN, contains useful information related to spatial structure of the image under processing. It is a mapping from image spatial information to time sequence. Through time matrix, Gaussian noisy pixels(More)
Firstly, dynamic programming is employed in the development of an optimal torque controller for sinusoidal permanent magnet synchronous motors (PMSM). In particular, a solution that can handle non-zero state tracking is of interest. Secondly, it is shown that the resulting optimal control solution converges to that of linear quadratic regulators (LQR). An(More)
This paper studies the problem of asymptotic stability for a class of high-order dynamic neural networks with time delays. Several useful lemmas are proved in this paper first. After that, the sufficient conditions for the asymptotic stability of the system with constant time delays are introduced, and also this asymptotic stability problem for the system(More)
We consider the control of Port-Controlled Hamiltonian (PCH) systems, which are a generalization of Euler-Lagrange Systems. A new matching equation for PCH systems is developed so that Interconnection Damping Assignment Passivity-Based Control (IDA-PBC) can be extended to the regulation of some underactuated PCH systems whose kinetic energy must be(More)