Aiming at the problems of ant colony algorithm in path planning

dead-end trapping of ants algorithm stagnation

and redundant including frequent point in the optimal path

an ant colony algorithm based on adaptive system is proposed.To reduce the probability of ants getting trapped in dead end

the global map information is traversed before the algorithm runs

and the U-shaped obstacle occupancy value is reassigned.To improve the efficiency of the algorithm and obtain the shortest path

the angle heuristic function is introduced to judge the angle difference between the ant’s current position and the target position to evaluate the path

so as to improve the search speed and path quality.Based on the obtained path set

the algorithm checks whether it is stagnated

and then the weights of related parameters such as heuristic factor and pheromone volatilization coefficient are adjusted adaptively

which ensures the convergence speed and improves the global performance of the algorithm.The improved pruning strategy is used to remove redundant points and smooth corners of cubic b-spline curves

and the motion efficiency of the robot in actual environment is improved.Grid method is used for modeling of 2D environment.The experimental results demonstrate the feasibility and efficiency of the improved ant colony algorithm.