Free Gait Planning for a Hexapod Robot Based on Reinforcement Learning

被引：0
|
作者：
Li M. [1 ]
Zhang M. [1 ]
Zhang J. [1 ]
Tian Y. [1 ]
Ma Y. [1 ]
机构：
[1] School of Mechanical Engineering, Hebei University of Technology, Tianjin
来源：
Jixie Gongcheng Xuebao/Journal of Mechanical Engineering | 2019年 / 55卷 / 05期
关键词：
Discretization; Free gait; Gait planning; Hexapod robot; Reinforcement learning;
D O I：
10.3901/JME.2019.05.036
中图分类号：
学科分类号：
摘要：
In order to solve the problem of gait planning for hexapod robots and achieve the optimization and learning of free gaits on specific terrains, a discrete gait model is built based on the discretization of strides and the fusion of CPG mode and reflect model. Through the analysis of robot stability and the study of gait planning strategies, the complex gait planning problem is transformed into the reorder problem of states with the interval of oscillation period. Inspired by this idea, a free gait planning method is proposed from a new perspective. Then a gait model based on reinforcement learning is constructed based on the discretization of gait sequences to imitate the learning behaviour of biological gaits. And using the average stability margin as performance index, a free gait planning method based on reinforcement learning is proposed by developing the adjustment strategies of dynamic conversion probabilities between discrete gait units. The prototype gait experiment results show that both the free gait planning method and the free gait planning method based on reinforcement learning can generate free gaits in line with the laws of biological movements, and the free gait planning method based on reinforcement learning can achieve the optimization and learning of free gaits on specific terrains using gait history information. © 2019 Journal of Mechanical Engineering.
引用
收藏
页码：36 / 44
页数：8
相关论文
共 22 条
  • [1] Deng H., Xin G., Zhong G., Et al., Gait and trajectory rolling planning and control of hexapod robots for disaster rescue applications, Robotics and Autonomous Systems, 95, 4, pp. 13-24, (2017)
  • [2] Chen X., Gao F., Energy expenditure of trotting gait under different gait parameters, Chinese Journal of Mechanical Engineering, 30, 4, pp. 1-8, (2017)
  • [3] Xu Y., Gao F., Pan Y., Et al., Method for six-legged robot stepping on obstacles by indirect force estimation, Chinese Journal of Mechanical Engineering, 29, 4, pp. 669-679, (2016)
  • [4] Ding X., Wang Z., Alberto R., Typical gaits and motion analysis of a hexagonal symmetrical hexapod robot, Robot, 32, 6, pp. 759-765, (2010)
  • [5] Zhen W., Kang X., Dai J., Et al., Gait planning of a novel metamorphic quadruped robot, Journal of Mechanical Engineering, 52, 11, pp. 26-33, (2016)
  • [6] Li M., Zhang M., Zhang J., Et al., Free gait generation algorithm for a hexapod robot based on discretization, Journal of Mechanical Engineering, 52, 3, pp. 18-25, (2016)
  • [7] Erden M.S., Kemal L., Free gait generation with reinforcement learning for a six-legged robot, Robotics and Autonomous Systems, 56, 3, pp. 199-212, (2008)
  • [8] Wang G., Zhang L., Wang L., On alternating equal-phase wave gait of crab-like robot, Robot, 33, 1, pp. 237-243, (2011)
  • [9] Carvalho C.S., Raptopoulos L.S., Andrade W.S., Et al., Extending SMER-based CPGs to accommodate total support phases and kinematics-safe transitions between gait rhythms of hexapod robots, Neurocomputing, 170, pp. 113-127, (2015)
  • [10] Zhu Y., Guo T., Liu Q., Et al., A study of arbitrary gait pattern generation for turning of a bio-inspired hexapod robot, Robotics and Autonomous Systems, 97, 2, pp. 125-135, (2017)
123