Research Of Robot Path Planning Based On Improved Ant Colony Algorithm

The rapid development of robotics has made path-planning technology a significant research area.Traditional path planning algorithms in robot path planning suffer from issues like poor search randomness and easy stagnation.Hence,introducing a fusion algorithm that combines improved ant colony algorithm and artificial potential field method is proposed to address these problems and plan a near-optimal path in complex environments.To address the issue of imbalance between population diversity and convergence speed,a fallback strategy is introduced along with the dynamic adjustment of heuristic function parameters in the ant colony optimization(ACO)algorithm.Furthermore,optimizing the pheromone update mechanism by updating the pheromone concentration differently and adding constraints to the robot’s movement mode is executed to prevent collision accidents.To solve the problem of local path planning,artificial potential field method(APF)is introduced,and a repulsive potential field function is added to overcome the target unreachability and local minima problems along with a distance parameter.Based on the improved ant colony algorithm and the artificial potential field method,this paper combines their respective features and advantages to fuse the two algorithms.The fusion algorithm relies on the construction of the potential field force heuristic function,combined with the state transfer formula,to find the optimal path.It can solve path-planning problems in complex environments.In order to further optimize the path,the path planned by the fusion algorithm is smoothed using the B-spline curve smoothing technique to reduce the number of rotation angles of the robot and improve its flexibility.Finally,an approximately optimal path is obtained.Simulation experiments show that the fusion algorithm can enable the robot to avoid obstacles and reach the target point in a complex environment with fast convergence and good optimality finding.