Rejection of an external force in the sagittal plane applied on a biped robot using a neuro-fuzzy controller

This paper describes the control of an autonomous biped robot capable to be subjected to external forces applied in the sagittal plane. A 1st order Takagi-Sugeno-Kang (TSK) type neuro fuzzy net, that was trained based on experimental and simulation data, is used. This net uses the zero moment point (ZMP) position and its variation as inputs, and the sagittal correction of the robot's body is obtained as the output. This control method is more accurate than the method based on an inverted pendulum model, which is based on a single mass concentration. The ZMP is obtained making use of the force distribution on four force sensors placed under each robot's foot. The gait implemented on our biped is similar to a human gait. A human gait was acquired and adapted to the robot size. In this paper some experiments are presented and the results show that the presented gait combined with the TSK neuro fuzzy net is appropriate to be used in the control of the biped robot, with and without an applied external force.