基于人工势场—遗传算法的机械臂避障方法研究  

Obstacle Avoiding Research on the Machine Arm of Robot Based on Artificial Potential Field Method and Genetic Algorithm

作　　者：孙绍杰[1] 齐晓慧[1] 苏立军[1] 赵诚[1] 

机构地区：[1]军械工程学院光学与电子工程系

出　　处：《计算机测量与控制》2011年第12期3078-3081,共4页Computer Measurement &Control

摘　　要：人工势场法是机器人避障规划中常用的方法,具有简单、实时性强的特点,但其存在目标不可达和局部极小值问题;文中针对机械臂的避障问题,首先利用人工势场法确定机械臂末端的避障轨迹,使用改进的斥力场克服势场法的目标不可达问题,利用随机逃离和沿等势线逃离相结合的方法解决局部极小值问题;其次针对机械臂末端避障轨迹中的每个点,采用遗传算法计算其对应的机械臂逆运动学解,在确保杆件不发生碰撞的情况下,充分保持关节角变化的柔顺性;仿真结果表明算法能够有效地实现机械臂的避障规划。A method is put forward to avoid obstacles for a robot manipulator. Firstly, the path of the end - effector is planned based on artificial potential field （APF）. This paper utilized an improved artificial potential field to solve the problem of Goals Nonreachable with Obstacle Nearby （GNRON）. A method of adding random force and adopting the equipotential line method （ELM） is proposed to make the robot quickly escape from minimum. Secondly, each joint angle is given according to the inverse kinematics solutions of manipulator with genetic algorithm. Collisions between manipulator and obstacle are avoided for each trajectory. Effectiveness of the improved algorithm was verified by simulation.

关 键 词：机械臂 人工势场法 遗传算法 避障策略 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]