A Global Optimization Stochastic Algorithm for Head Motion Stabilization during Quadruped Robot Locomotion

Visually-guided locomotion is important for autonomous robotics. However, there are several difficulties, for instance, the robot locomotion induces head shaking that constraints stable image acquisition and the possibility to rely on that information to act accordingly. In this work, we propose a combined approach based on a controller architecture that is able to generate locomotion for a quadruped robot and a genetic algorithm to generate head movement stabilization. The movement controllers are biologically inspired in the concept of Central Pattern Generators (CPGs) that are modelled based on nonlinear dynamical systems, coupled Hopf oscillators. This approach allows to explicitly specify parameters such as amplitude, offset and frequency of movement and to smoothly modulate the generated oscillations according to changes in these parameters. Thus, in order to achieve the desired head movement, opposed to the one induced by locomotion, it is necessary to appropriately tune the CPG parameters. Since this is a non-linear and non-convex optimization problem, the tuning of CPG parameters is achieved by using a global optimization method. The genetic algorithm searches for the best set of parameters that generates the head movement in order to reduce the head shaking caused by locomotion. Optimization is done offline according to the head movement induced by the locomotion when no stabilization procedure was performed. In order to evaluate the resulting head movement, a fitness function based on the Euclidian norm is investigated. Moreover, a constraint handling technique based on tournament selection was implemented. Experimental results on a simulated AIBO robot demonstrate that the proposed approach generates head movement that reduces significantly the one induced by locomotion.