1、?Baseline as environment for the Reinforcement Learning approach1.Data input processing(airspace,all the flights within area of interest)2.Initial point generation,recommendation starting point3.Given 4 waypoints from the initial point,3 possible direct routes are considered,looking for the most opt
2、imized(cost effective)*Blocked DCTs are not considered here.?*Conflict considered when two aircrafts are approaching within 5 NM3.1.Cross-check against other aircraft trajectories and their possible DCTs starting from the most cost-effective one while assuring independency3.2.Computing efficiency regarding distance,time and fuel relative to the trajectory3.3.Global optimization variable considering these criteria?