On the tuning of the free parameters of a new adaptive robot control based on geometric principles of Hamiltonian mechanics

A novel approach toward the adaptive control of robots dynamically interacting with an unmodelled environment and having only approximately known dynamic parameters has previously been developed on the basis of the principles of the Hamiltonian mechanics. Like different means of modern soft computing technology such as artificial neural networks (ANNs) or fuzzy controllers having a more or less uniform architecture independent of the particular details of the problems to be solved by them, the proposed method also has a uniform structure not strictly tailored to the peculiar properties of the mechanical system to be controlled. However, as special kinds of ANNs are fit to solve wide but typical classes of tasks the proposed method is invented for tackling problems related to the control of mechanical devices in which the dominating nonlinear coupling originates from the laws of classical mechanics. As ANNs have plenty of free parameters (connection weights and threshold values) the tuning of which means learning, this mechanical model also contains tunable parameters so offering the possibility for learning. In this paper the model´s free parameters, possible constraints imposed on them as well as different tuning strategies are discussed partly on the basis of computer simulations