Application of improved ant colony optimization in mobile robot trajectory planning

Abstract

Under the condition of known static environment and dynamic environment, an improved ant colony optimization is proposed to solve the problem of slow convergence, easily falling into local optimal solution, deadlock phenomenon and other issues when the ant colony optimization is constructed. Based on the traditional ant colony optimization, the ant colony search ability at the initial moment is strengthened and the range is expanded to avoid falling into the local optimal solution by adaptively changing the volatility coefficient. Secondly, the roulette operation is used in the state transition rule which improves the quality of the solution and the convergence speed of the algorithm effectively. Finally, through the elite selection and the node crossover operation of the better path, the global search efficiency and convergence speed of the algorithm are effectively improved. Several experimental results have also been obtained by applying the improved ant colony optimization to obstacle avoidance. The experimental results demonstrate the feasibility and effectiveness of the algorithm.