Resumen
The article is devoted to the control system synthesis problem considering collision avoidance system in the task of collective regrouping of dynamic objects. Our goal is to find the closed loop control system with probabilistic mapping of the current state vector to the optimal control vector. We propose to consider the control of pairs of dynamic objects, as simultaneous collision of more than 2 multiple objects can be decomposed to build a set of individual pairs of objects for which the violation of phase dynamic constraints is taking place. Control system is realized as a conditional density function with control as a random variable conditioned on the states of both dynamic object and moving obstacle, which reflects the novelty of the research. Proposed control system is universal in a sense that it is able to resolve collisions between dynamic objects even in the unknown environment for arbitrary initial and terminal states given for objects. Moreover, it is able to consider alternate obstacle avoidance routes through the probability density function of control. The control system also assumes the control of the group is decentralized. Individual object will be acting as a standalone system after the control system is uploaded in the memory.