基于势场蚁群算法的机器人路径规划

提出了一种未知环境下机器人路径规划的势场蚁群算法。该算法利用人工势场力和机器人与目标之间的距离构造机器人避障和移动的综合启发信息，并利用蚁群搜索机制在未知环境中寻找机器人从起始位置至目标位置的全局最优路径。所提出的算法将蚁群算法和人工势场法进行有效的结合，提高了常规蚁群算法对最优路径的搜索效率。通过仿真实验表明了所提出的算法用于机器人路径规划的有效性。

Ant colony optimization with potential field heuristic for robot path planning

A kind of ant colony optimization with potential field (ACOPF) heuristic, is proposed for path planning of a mobile robot in unknown environment. In the ACOPF, the potential field resultant and the distance between the robot and the goal are utilized to construct the comprehensive heuristic of robot for obstacle avoidance and moving. With this heuristic, an ant colony optimization (ACO) mechanism is used to search a global optimal path from the start point to the end point for a robot in an unknown environment. The proposed ACOPF combines ACO with potential field method (PFM) effectively and makes the optimal path finding more effective than using general ACO. Simulation results show that the proposed ACOPF is very effective and efficient for robot path planning.