Quick Search Adv. Search

J4 ›› 2016, Vol. 13 ›› Issue (4): 572-584.doi: 10.1016/S1672-6529(16)60329-3

• article • Previous Articles     Next Articles

Adaptive Walking Control of Biped Robots Using Online Trajectory Genera-tion Method Based on Neural Oscillators

Chengju Liu1, Danwei Wang2, Erik David Goodman3, Qijun Chen1   

  1. 1. School of Electronics and Information Engineering, Tongji University, Shanghai 201804, China
    2. School of Electrical and Electronic Engineering, Nanyang Technological University, Manyang Avenue 639798, Singapore
    3. BEACON Center for the Study of Evolution in Action, Michigan State University, East Lansing 48824, USA
  • Received:2016-03-06 Revised:2016-09-06 Online:2016-10-10 Published:2016-10-10
  • Contact: Qijun Chen E-mail:qjchen@tongji.edu.cn
  • About author:Chengju Liu1, Danwei Wang2, Erik David Goodman3, Qijun Chen1

Abstract:

This work concerns biped adaptive walking control on irregular terrains with online trajectory generation. A new trajectory generation method is proposed based on two neural networks. One oscillatory network is designed to generate foot trajectory, and another set of neural oscillators can generate the trajectory of Center of Mass (CoM) online. Using a motion engine, the char-acteristics of the workspace are mapped to the joint space. The entraining property of the neural oscillators is exploited for adaptive walking in the absence of a priori knowledge of walking conditions. Sensory feedback is applied to modify the generated trajectories online to improve the walking quality. Furthermore, a staged evolutionary algorithm is developed to tune system parameters to improve walking performance. The developed control strategy is tested using a humanoid robot on irregular terrains. The experiments verify the success of the presented strategy. The biped robot can walk on irregular terrains with varying slopes, unknown bumps and stairs through autonomous adjustment of its walking patterns.

Key words: biped robot, adaptive walking, neural oscillator, trajectory generation, staged evolution algorithm