基于遗传算法的仿生双足爬壁机器人越障运动规划  

Motion Planning of a Bio-inspired Biped Wall Climbing Robot Stepping over Obstacles Based on Genetic Algorithm

作　　者：李志海[1] 付宜利[2] 

机构地区：[1]中国科学院沈阳自动化研究所机器人学国家重点实验室,辽宁沈阳110016 [2]哈尔滨工业大学机器人技术与系统国家重点实验室,黑龙江哈尔滨150001

出　　处：《机器人》2012年第6期751-757,共7页Robot

基　　金：国家自然科学基金资助项目(61105109)

摘　　要：针对仿生双足爬壁机器人的壁面越障运动,提出一种基于遗传算法的越障运动规划算法.该算法在分析机器人稳定运动条件和障碍物笛卡儿空间几何约束的基础上,通过加权系数法定义适应度函数,使机器人稳定裕度和运动代价在某种程度上达到综合最优.对笛卡儿位姿进行编码,在笛卡儿空间和关节空间约束下,规划出一条无碰撞、稳定性高的机器人运动序列.利用该算法对机器人跨越凸起障碍物运动进行规划仿真,结果证明该方法可保证机器人运动的稳定裕度和运动轨迹的平滑.For obstacle stepping over of a bio-inspired biped wall climbing robot, a motion planning algorithm based on genetic algorithm is proposed. By analyzing stability requirements and geometrical constraints of obstacle avoidance in Cartesian space, a fitness function is defined with a weighted coefficient method, so that the stability margin and movement cost can attain integrated optimum to a certain extent. By coding its posture in Cartesian space, a collision-free and highly stable motion sequence for the robot is planned, under the constraints in Cartesian space and joint space. Motion planning of the robot stepping over protruding obstacles is implemented in simulation with the proposed algorithm. Results show that the algorithm can guarantee the stability margin of robot motion and the smoothness of the trajectory.

关 键 词：仿生双足爬壁机器人 运动规划 遗传算法 越障 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]