Evolution of digital modulation schemes for radio systems

We apply an evolutionary strategies (ES) algorithm to the problem of designing modulation schemes used in wireless communication systems. The ES is used to optimize the digital symbol to analog signal mapping, called a constellation. Typical human-designed constellations are compared to the constellations produced by our algorithms in a simulated radio environment with noise and multipath, in terms of bit error rate. We conclude that the algorithm, with diversity maintenance, find solutions that equal or outperform conventional ones in a given radio channel model, especially for those with higher number of symbols in the constellation (arity).