The paper describes an approach for automated crystal structure solution from powder diffraction data using the multi-population genetic algorithm (MPGA). The advantage of using co-evolution with the best individual exchange, compared with the using of the evolution with a single genetic algorithm without interpopulation exchange, is shown. As an example, the paper describes the use of MPGA for solving the [Pt(NH3)5Cl]Br3 crystal structure, having the tetragonal I41/a space group [a = 17.2587(5) Å, c = 15.1164(3) Å, Z = 16, unit-cell volume V = 4502.61(10) Å3]. The MPGA convergence charts and the atomic positions distribution maps of the MPGA populations are given. The description of the final structure solution is also shown.