Contact friction compensation for robots using genetic learning algorithms

In this paper, the issues of contact friction compensation for constrained robots are presented. The proposed design consists of two loops. The inner loop is for the inverse dynamics control which linearizes the system by can celing nonlinear dynamics, while the outer loop is for friction compensatio n. Although various models of friction have been proposed in many engineeri ng applications, frictional force can be modeled by the Coulomb friction pi ns the viscous force. Based on such a model, an on-line genetic algorithm i s proposed to learn the friction coefficients for friction model. The frict ion compensation control input is also implemented in terms of the friction coefficients to cancel the effect of unknown friction. By the guidance of the fitness function, the genetic learning algorithm searches for the best- fit value in a way like the natural surviving laws. Simulation results demo nstrate that the proposed on-line genetic algorithm can achieve good fricti on compensation even under the conditions of measurement noise and system u ncertainty. Moreover, the proposed control scheme is also found to be feasi ble for friction compensation of friction model with Stribeck effect and po sition-dependent friction model.