Multi-scale Map Path Planning Based on Fuzzy Logic Genetic Ant Colony Optimization

Path planning is a core to improve the autonomy of Unmanned Ground Vehicle (UGV). In autonomous navigation applications, the use of Ant Colony Optimization (ACO) in solving the path planning problem is difficult to obtain the global optimal solution, which make the waste of resources. Focus on fast optimization search, this paper proposes Fuzzy Logic Genetic Ant Colony Optimization (FLGACO), which adopt crossover and mutation operations in genetic algorithms. By using the fuzzy logic system, dynamic adjustment for pheromone and heuristic values can be realized. Simulation experiments on path planning for fast arrival were conducted using ACO,GA and FLGACO under the same map. The results show that FLGACO reduces the path length by 15% compared to ACO and 9% compared to genetic algorithm, which can effectively reduce the energy consumption and verify the feasibility and effectiveness of the improved method.