Making soccer kicks better: a study in particle swarm optimization and evolution strategies

Biomechanics is a science of examining the internal and external forces on the human body. In biomechanics, forward dynamics simulation models can be used to study optimal control of the human musculoskeletal system. An example application is the soccer kick, where the optimal recruitment pattern of the muscles of the lower extremity can result in a high speed shot on net. We used evolutionary algorithms - particle swarm optimizers and evolution strategies - to adjust muscle control parameters for a soccer kick. In this paper we describe our implementation of the soccer kick project, optimization experiments performed with the soccer kick and comparing the results from particle swarm optimization and evolution strategies.