Machine Ethics: Ethical Challenges and Strategies In Artificial Intelligent and Superintelligence

Artificial intelligence, from the beginning, was looking for simulating human behavior for machine, by following the human pattern. With the increasing development of this field of science and its success in simulation of some specific human behavior, even by removing some certain restrictions in the human pattern, the feasibility of simulating comprehensive human behavior, is increased and the emergence of new generation of machines is predisposed. This new generation of machine that has human capabilities comprehensively and acts more intellectually than humans, is addressed as "superintelligence". In principle delegation of any task to an intelligent agent needs to explain some questions, like degree of its autonomy of action and decision, and the degree of trust which can be vested in the outcomes it achieves. The intellectual superiority of this machine is a decisive reason in order to consider its ethical issues. In order to achieving an intelligent agent which is able to meet all expected goals in a safe manner, it would be necessary to create architecture towards the choice machine.