Best-First Search with Genetic Algorithm for Space Optimization in Pathfinding Problems

This paper presents a novel method to optimize the process of finding paths using a model based on Genetic Algorithms and Best-First-Search for real time systems, such as video games and virtual reality environments. The proposed solution uses obstacle pattern detection based at online training system to guarantee the memory economy. The architecture named Patterned based Pathfinding with Genetic Algorithm (PPGA) uses a learning technique in order to create an agent adapted to the environment that is able to optimize the search for paths even in the presence of obstacles. We demonstrate that the PPGA architecture performs better than classic A* and Best-First-Search algorithms in patterned environment.