基于自适应机制改进蚁群算法的移动机器人全局路径规划

针对基本蚁群算法在二维静态栅格地图下进行移动机器人路径规划时出现的搜索效率低下、收敛速度缓慢、局部最优解等问题,提出一种自适应机制改进蚁群算法,用于移动机器人在二维栅格地图下的路径规划.首先采用伪随机状态转移规则进行路径选择,定义一种动态选择因子以自适应更新选择比例,引入距离参数计算转移概率,提高算法的全局搜索能力以及搜索效率;然后基于最大最小蚂蚁模型和精英蚂蚁模型,提出一种奖励惩罚机制更新信息素增量,提高算法收敛速度;最后定义一种信息素自适应挥发因子,限制信息素浓度的上下限,提高算法全局性的同时提高算法的收敛速度.在不同规格的二维静态栅格地图下进行移动机器人全局路径规划对比实验,实验结果表明自适应机制改进蚁群算法具有较快的收敛速度,搜索效率明显提高且具有较好的全局搜索能力,验证了所提算法的实用性和优越性.

Global path planning of mobile robot based on adaptive mechanism improved ant colony algorithm

Aiming at the problems of low search efficiency, slow convergence rate, and local optimal solution when a basic ant colony algorithm is applied to mobile robot path planning under a 2D static grid map, an adaptive mechanism improved ant colony algorithm for the path planning of mobile robots under the two-dimensional grid map environment is proposed. Firstly, pseudo-random state transition rules are used. For path selection, a dynamic selection factor is defined to adaptively update the selection ratio and a distance parameter is introduced to calculate the transition probability. Hence, the global search ability and search efficiency of the algorithm is improved. Then, based on the maximum and minimum ant model and the elite ant model, a reward and punishment mechanism is proposed to update the pheromone increment. Finally, a pheromone dynamic volatilization factor is defined to limit the upper and lower range of the pheromone concentration to improve the convergence speed of the algorithm and the global search ability. The global path planning comparison experiments of the mobile robot are carried out under two-dimensional static grid maps of different specifications, and the experimental results show that the adaptive mechanism improved ant colony algorithm has a faster convergence speed and significantly improved search efficiency, and it has a better global search ability, which verifies the effectiveness and superiority of the algorithm.