A Hierarchical Task Network Planner for Pathfinding in Real-Time Strategy Games

In this paper, we propose an automatic mechanism of Hierarchical Task Networks (HTNs) creation for solving the problem of real-time path planning in Real-Time Strategy (RTS) Games. HTNs are created using an abstraction of the game map. A real-time heuristic search approach called Learning Real-Time A* (LRTA) is applied to execute the primitive tasks of the HTNs. The main purpose of using a HTN based real-time path planner is to restrict the real-time search to a shorter part of the problem space while keeping it in the direction of the actual goal position. Results show that the hierarchical approach reduces the
suboptimality of the LRTA and speeds up the convergence process.