In this paper we propose Aggregative Tracking Feedback, i.e., a novel distributed feedback optimization law that steers network systems to a steady state, which is optimal according to an aggregative optimization problem. Aggregative optimization is a recently emerged distributed optimization framework in which the agents of a network minimize the sum of local objective functions. These functions depend both on local and aggregate decision variables (e.g., the barycenter). Motivated by this problem setup, we design a distributed feedback optimization law in which each agent reconstructs information not locally available while concurrently steering the network to an optimal steady state. We perform a system theoretical analysis based on a singular perturbation approach to show that Aggregative Tracking Feedback, in case of strongly convex objective functions, steers the network with a linear convergence rate to the problem minimum. Finally, we show some numerical simulations on a multi-robot surveillance scenario to validate the effectiveness of the proposed method.
Carnevale G., Mimmo N., Notarstefano G. (2022). Aggregative feedback optimization for distributed cooperative robotics. RADARWEG 29, 1043 NX AMSTERDAM, NETHERLANDS : Elsevier B.V. [10.1016/j.ifacol.2022.07.227].
Aggregative feedback optimization for distributed cooperative robotics
Carnevale G.;Mimmo N.;Notarstefano G.
2022
Abstract
In this paper we propose Aggregative Tracking Feedback, i.e., a novel distributed feedback optimization law that steers network systems to a steady state, which is optimal according to an aggregative optimization problem. Aggregative optimization is a recently emerged distributed optimization framework in which the agents of a network minimize the sum of local objective functions. These functions depend both on local and aggregate decision variables (e.g., the barycenter). Motivated by this problem setup, we design a distributed feedback optimization law in which each agent reconstructs information not locally available while concurrently steering the network to an optimal steady state. We perform a system theoretical analysis based on a singular perturbation approach to show that Aggregative Tracking Feedback, in case of strongly convex objective functions, steers the network with a linear convergence rate to the problem minimum. Finally, we show some numerical simulations on a multi-robot surveillance scenario to validate the effectiveness of the proposed method.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.