Stable modifiable walking pattern generator with arm swing motion using evolutionary optimized central pattern generator

Abstract

In this paper, a stable modifiable walking pattern generator (MWPG) is proposed by a employing arm swing motion. The arm swing motion is generated by a central pattern generator (CPG) which is optimized by a constraint evolutionary algorithm. In this scheme, the MWPG generates a position trajectory of center of mass (COM) of humanoid robot and the CPG generates the arm swing motion. A sensory feedback in the CPG is designed, which uses a inertial measurement unit (IMU) signal. For the optimization of the CPG parameters, a two-phase evolutionary programming (TPEP) is employed. The effectiveness of the proposed scheme is demonstrated by simulations using a Webots dynamic simulator for a small sized humanoid robot, HSR-IX, developed in the Robot Intelligence Technology (RIT) Lab, KAIST.