Optimized road maintenance planning seeks for solutions that can minimize the life-cycle cost of a road network and concurrently maximize pavement condition. Aiming at proposing an optimal set of road maintenance solutions, robust meta-heuristic algorithms are used in research. Two main optimization techniques are applied including single-objective and multi-objective optimization. Genetic algorithms(GA), particle swarm optimization(PSO), and combination of genetic algorithm and particle swarm optimization(GAPSO) as single-objective techniques are used, while the non-domination sorting genetic algorithm II(NSGAII) and multi-objective particle swarm optimization(MOPSO) which are sufficient for solving computationally complex large-size optimization problems as multi-objective techniques are applied and compared. A real case study from the rural transportation network of Iran is employed to illustrate the sufficiency of the optimum algorithm. The formulation of the optimization model is carried out in such a way that a cost-effective maintenance strategy is reached by preserving the performance level of the road network at a desirable level. So, the objective functions are pavement performance maximization and maintenance cost minimization. It is concluded that multi-objective algorithms including non-domination sorting genetic algorithm II(NSGAII) and multi-objective particle swarm optimization performed better than the single objective algorithms due to the capability to balance between both objectives. And between multi-objective algorithms the NSGAII provides the optimum solution for the road maintenance planning. Optimized road maintenance planning seeks for solutions that can minimize the life-cycle cost of a road network and concurrently maximize pavement condition. Aiming at proposing an optimal set of road maintenance solutions, robust meta-heuristic algorithms are used in research. Two main optimization techniques Genetic algorithms (GA), particle swarm optimization (PSO), and combination of genetic algorithm and particle swarm optimization (GAPSO) as single-objective techniques are used, while the non-domination sorting genetic algorithm II (NSGAII) and multi-objective particle swarm optimization (MOPSO) which are sufficient for solving computationally complex large-size optimization problems as multi-objective techniques are applied and compared. A real case study from the rural transportation network of Iran is employed to illustrate the sufficiency of the optimum algorithm. The formulation of the optimization model is carried out in such a way that a cost-effective maintenance strategy is reached by preserving the performance level of the road network at a desirable level. So, the objective functions are pavement performance maximization and maintenance cost minimization. It is noted that multi-objective algorithms including non-domination sorting genetic algorithm II (NSGAII) and multi-objective particle swarm optimization performing better than the single objective algorithms due to the capability to balance between both objectives. And between multi-objective algorithms the NSGAII provides the optimum solution for the road maintenance planning.