首页> 美国卫生研究院文献>Computational Intelligence and Neuroscience >Mobile Robot Path Planning Using Ant Colony Algorithm and Improved Potential Field Method
【2h】

Mobile Robot Path Planning Using Ant Colony Algorithm and Improved Potential Field Method

机译:基于蚁群算法和改进势场法的移动机器人路径规划

代理获取
本网站仅为用户提供外文OA文献查询和代理获取服务,本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文,但由于OA文献来源多样且变更频繁,仍可能出现获取不到、文献不完整或与标题不符等情况,如果获取不到我们将提供退款服务。请知悉。

摘要

For the problem of mobile robot's path planning under the known environment, a path planning method of mixed artificial potential field (APF) and ant colony optimization (ACO) based on grid map is proposed. First, based on the grid model, APF is improved in three ways: the attraction field, the direction of resultant force, and jumping out the infinite loop. Then, the hybrid strategy combined global updating with local updating is developed to design updating method of the ACO pheromone. The process of optimization of ACO is divided into two phases. In the prophase, the direction of the resultant force obtained by the improved APF is used as the inspired factors, which leads ant colony to move in a directional manner. In the anaphase, the inspired factors are canceled, and ant colony transition is completely based on pheromone updating, which can overcome the inertia of the ant colony and force them to explore a new and better path. Finally, some simulation experiments and mobile robot environment experiments are done. The experiment results verify that the method has stronger stability and environmental adaptability.
机译:针对已知环境下移动机器人的路径规划问题,提出了一种基于网格图的混合人工势场(APF)和蚁群优化(ACO)路径规划方法。首先,基于网格模型,APF通过三种方式进行了改进:吸引力场,合力的方向以及跳出无限循环。然后,提出了将全局更新与局部更新相结合的混合策略,以设计ACO信息素的更新方法。 ACO的优化过程分为两个阶段。在前期,将通过改进的APF获得的合力的方向用作启发因素,从而导致蚁群以定向方式运动。在后期,消除了启发性因素,完全基于信息素更新蚁群过渡,可以克服蚁群的惯性,迫使他们探索新的更好的道路。最后,完成了一些仿真实验和移动机器人环境实验。实验结果证明该方法具有较强的稳定性和环境适应性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
代理获取

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号