Over a decade, the evolutionary and social inspired computing techniques have revolutionarised the nonlinear problem-solving methods with their efficiency in searching for the global optimum solutions. Several engineering problems are dealt with such nature-inspired techniques. In the recent past, the evolutionary computing and socio-inspired algorithms have been applied to antenna array synthesis problems. In this chapter, the novel social group optimization algorithm (SGOA) is used for the antenna array synthesis. Three different and potential pattern synthesis problems like sidelobe level (SLL) optimization, null positioning, and failure compensation are dealt for demonstrating the effectiveness of the SGOA over the conventional uniform patterns. In all the cases, the simulation-based experimentation is repeated for 20-element and 28-element linear array. The robustness of the algorithm to deal with the constrained objectives of antenna array synthesis is discussed with relevant outcomes from the simulations in terms of the convergence plots.