Abstract: In this work a software simulation model has been
proposed for two driven wheels mobile robot path planning; that can
navigate in dynamic environment with static distributed obstacles.
The work involves utilizing Bezier curve method in a proposed N
order matrix form; for engineering the mobile robot path. The Bezier
curve drawbacks in this field have been diagnosed. Two directions:
Up and Right function has been proposed; Probability Recursive
Function (PRF) to overcome those drawbacks.
PRF functionality has been developed through a proposed;
obstacle detection function, optimization function which has the
capability of prediction the optimum path without comparison
between all feasible paths, and N order Bezier curve function that
ensures the drawing of the obtained path.
The simulation results that have been taken showed; the mobile
robot travels successfully from starting point and reaching its goal
point. All obstacles that are located in its way have been avoided.
This navigation is being done successfully using the proposed PRF
techniques.
Abstract: This work explores blind image deconvolution by recursive function approximation based on supervised learning of neural networks, under the assumption that a degraded image is linear convolution of an original source image through a linear shift-invariant (LSI) blurring matrix. Supervised learning of neural networks of radial basis functions (RBF) is employed to construct an embedded recursive function within a blurring image, try to extract non-deterministic component of an original source image, and use them to estimate hyper parameters of a linear image degradation model. Based on the estimated blurring matrix, reconstruction of an original source image from a blurred image is further resolved by an annealed Hopfield neural network. By numerical simulations, the proposed novel method is shown effective for faithful estimation of an unknown blurring matrix and restoration of an original source image.