—The contemporary trend in science and society consists of searching for solutions to enhance people life, safety, economy, and health while protecting environment. In recent years, we have witnessed the arrival of complex machines with structures similar to humans known as humanoids robots. The combination of these technologies and optimization technics may result in robust, safe, reliable, and flexible machines that can substitute humans in multiple difficult tasks. In order to contribute to this topic, we propose tow new evolutionary algorithms based on the selfish gene theory and elitism strategies. Therefore, permanent elitism-based selfish gene algorithm (peSGA) and nonpermanent elitism based selfish gene algorithm (neSGA) are proposed. In order to validate and to evaluate the performance peSGA and neSGA, a numerical experiment is performed using IEEE CEC 2014 functions. the The obtained results show that the proposed algorithms are very competitive. Furthermore, evomutionary optimization of a walking robot is formulated. The proposed algorithm are applied to the generation and control of optimal motion of a humanoid robot.