%A LI Erchao∗ (李二超), QI Kuankuan (齐款款)
%T Ant Colony Algorithm Path Planning Based on Grid Feature Point Extraction
%0 Journal Article
%D 2023
%J J Shanghai Jiaotong Univ Sci
%R 10.1007/s12204-023-2572-4
%P 86-99
%V 28
%N 1
%U {https://xuebao.sjtu.edu.cn/sjtu_en/CN/abstract/article_46476.shtml}
%8 2023-01-28
%X Aimed at the problems of a traditional ant colony algorithm, such as the path search direction and
field of view, an inability to find the shortest path, a propensity toward deadlock and an unsmooth path, an ant
colony algorithm for use in a new environment is proposed. First, the feature points of an obstacle are extracted
to preprocess the grid map environment, which can avoid entering a trap and solve the deadlock problem. Second,
these feature points are used as pathfinding access nodes to reduce the node access, with more moving directions
to be selected, and the locations of the feature points to be selected determine the range of the pathfinding field
of view. Then, based on the feature points, an unequal distribution of pheromones and a two-way parallel path
search are used to improve the construction efficiency of the solution, an improved heuristic function is used to
enhance the guiding role of the path search, and the pheromone volatilization coefficient is dynamically adjusted
to avoid a premature convergence of the algorithm. Third, a Bezier curve is used to smooth the shortest path
obtained. Finally, using grid maps with a different complexity and different scales, a simulation comparing the
results of the proposed algorithm with those of traditional and other improved ant colony algorithms verifies its
feasibility and superiority.