基于IAPF-ACO的工业机器人运动规划

针对蚁群算法运动规划收敛慢且精度不佳的问题，提出一种改进势场蚁群(improved artificial potential field ant colony optimization, IAPF-ACO)算法。斥力计算模型引入目标调节因子解决势场寻优不可达且易陷入局部最优问题。蚁群算法计算框架加入改进势场模型，即启发信息函数中增加势场信息因子。三维障碍物空间仿真规划表明：IAPF-ACO算法在离散环境与聚集环境规划路径质量较优、规划结果较为稳定。在MATLAB搭建工业机器人仿真模型，关节空间内对规划路径点平滑处理，避障仿真结果表明，工业机器人末端位移是一条安全、平滑的运动轨迹。

Motion Planning of Industrial Robot Based on IAPF-ACO

Aiming at the problem of slow convergence and poor accuracy of ACO algorithm motion planning, this paper proposes an IAPF-ACO algorithm. The repulsive force calculation model introduces the target adjustment factor to solve the problem that the potential field is unreachable and easy to fall into the local optimum. The improved potential field model is added to the ACO algorithm calculation framework, and the potential field information factor is added to the heuristic information function. The 3D obstacle space simulation planning shows that the IAPF-ACO algorithm has better planning path quality and more stable planning results in discrete and aggregated environments. The industrial robot simulation model is built in MATLAB, and the planned path points are processed smoothly in the joint space. The simulation results of obstacle avoidance show that the end displacement of the industrial robot is a safe and smooth motion trajectory.