Sharif Digital Repository

In the present work, trajectory optimization of the Dual-Arm Cam-Lock robot considering kinematic and dynamic redundancy is performed. First, the optimal control problem is solved only considering kinematic redundancy and then is solved considering dynamic redundancy. General form of the dynamic model for the system is developed using Lagrangian relations. Global optimization method is used for redundancy resolution problem. A performance index is defined based on the consumed kinetic energy and is minimized through a desired trajectory using the global optimization method. Formulations of optimal control problem are derived and initial boundary problem is changed to two point boundary value... 

Nowadays, methods based on deep learning networks are the most effective artificial in­ telligence methods. Although they have achieved success in various fields (such as machine vision and object recognition), practical and experimental cases show the fragility of deep learning networks against perturbations and unwanted changes of the input pattern. All these perturbations must be in a way that the main class of the perturbed input pattern can be rec­ ognized by human, but the network makes a mistake in recognizing its correct class. This thesis seeks a more accurate evaluation by designing adversarial attacks such that the main class of the adversarial pattern is detectable by human...