At the dawn of civil aviation, pilots resolved conflicts themselves because they always flew in good weather conditions with low speed aircrafts. Nowadays, pilots must be helped by an air traffic controller on the ground who has a global view of the current traffic distribution in the airspace and can give indications to the pilots to avoid collisions. Solutions to conflicts are empirical, controllers are trained to react to certain types of conflicts and are limited by a workload. It is clear that if the ATC is overloaded, the sky is not. Conflict resolution is a trajectory optimization problem under constraints the complexity of which is so important that it has not been solved yet. Many attempts have been made to solve this problem with classical methods, such as gradient methods, reactive technics, expert systems, but most of them failed. In this paper, we show how genetic algorithms can be used to solve en-route aircrafts conflict automatically to increase Air Traffic Control capacity in high density areas. Our main purpose is to find out the global optimum and not only a suitable solution, in a real time situation, with conflict free trajectories that respect both plane and pilot performances.