Conflict resolution based on cooperative coevolutionary with dynamic grouping strategy for multi-aircraft

Conflict resolution problem (CRP) plays a crucial role in the guarantee of safety. This paper formulates CRP as a multi-agent path planning problem which aims to find optimal paths for aircrafts. An algorithm named CCDG is proposed to tackle it based on cooperative coevolutionary (CC) with a dynamic grouping strategy for aircraft. CCDG makes aircraft divided into several equal sub-groups according to the dynamic grouping strategy. Each sub-group can adopt an evolutionary algorithm (EA) to optimize the aircrafts' paths fully distributed and in parallel. Optimal solution is obtained through cooperation and coordination with all sub-populations. Empirical studies using extremely scenario adopted by previous research show that CCDG outperformed the existing approach (fast GA), and the popular path planner that each aircraft uses an EA. Moreover, CCDG succeed to improve the airspace safety and reduce cost for CR.