Optimization of Central Pattern Generator-Based Torque-Stiffness-Controlled Dynamic Bipedal Walking

In this paper, we propose a central pattern generator-based model to control the walking motion of a biped robot. The model independently controls the joint torque and joint stiffness in real time. Instead of the phase-dependent neural model used by Huang in 2014, we adopt the same structure for all the walking phases, reducing the number of connections between neurons. This reduction enables the employment of the particle swarm algorithm to find the optimal values of these parameters which lead to different solutions with different performance criteria. The simulation of the proposed method on a seven-link bipedal walking model gave a good performance in the range of walking speeds, which is referred to as versatility, and in walking pattern transition. The achieved walking gaits are 1-period cyclic motions for all the input control signals except for few gaits. Besides, these 1-period cyclic motions have a good local and global stability. Finally, we expanded our neural model by adding connections that work only when the robot walks on uneven terrains, which improved the robot's performance against this kind of perturbation.