Logical-probabilistic method for controlling modular robots
This work presents a logical-probabilistic method for adaptive control of modular systems based on the use of the modules functional similarity and the logical-probabilistic algorithm of the guided search of rules. The proposed method is based on the joint learning of the control modules, starting with finding the common control rules for all modules and finishing with their subsequent specification in accordance with the ideas of the probabilistic inference. With an interactive 3D simulator, a number of successful experiments were carried out to train four virtual models of robots. Experimental studies have shown that the proposed approach is quite effective and can be used to manage modular systems with many degrees of freedom.