使用零力矩点轨迹规划的四足机器人步态进化方法

Gait Evolving Method of Quadruped Robot Using Zero-Moment Point Trajectory Planning

  • 摘要: 通过对AIBO机器人行走时身体摇摆现象的研究,提出一种使用零力矩点轨迹规划的步态控制方法.与此同时,使用基于遗传算法的进化学习方法对步态控制参数进行优化.实验使用AIBO机器人进行测试,机器人使用该进化学习方法可自主地得到最优步态,其最优步态在保证稳定性的基础上最大速度达到了455mm/s.实验结果表明,应用该方法进行步态控制,机器人获取的最优步态不仅满足稳定性要求,而且对不平地形也具有较好的适应能力.

     

    Abstract: This paper presents a gait control method using ZMP(zero-moment point) trajectory planning by studying the body sway phenomenon of AIBO robots during walking.Meanwhile,an evolutionary learning method based on genetic algorithm is used to optimize those gait control parameters.In the experiments,the AIBO robots can obtain the optimal gait autonomously,and its maximum speed reaches 455 mm/s with stability.The experimental results show that the robots can obtain the optimal gait with better stability and stronger adaptability to uneven terrain by using the proposed gait control method.

     

/

返回文章
返回