We address the problem of distributed unconstrained convex optimization under separability assumptions, i.e., the framework where each agent of a network is endowed with a local private multidimensional convex cost, is subject to communication constraints, and wants to collaborate to compute the minimizer of the sum of the local costs. We propose a design methodology that combines average consensus algorithms and separation of time-scales ideas. This strategy is proved, under suitable hypotheses, to be globally convergent to the true minimizer. Intuitively, the procedure lets the agents distributedly compute and sequentially update an approximated Newton-Raphson direction by means of suitable average consensus ratios. We show with numerical simulations that the speed of convergence of this strategy is comparable with alternative optimization strategies such as the Alternating Direction Method of Multipliers. Finally, we propose some alternative strategies which trade-off communication and computational requirements with convergence speed.

Autonomous systems are becoming ubiquitous and gaining momentum within the marine sector. Since the electrification of transport is happening simultaneously, autonomous marine vessels can reduce environmental impact, lower costs, and increase efficiency. Although close monitoring is still required to ensure safety, the ultimate goal is full autonomy. One major milestone is to develop a control system that is versatile enough to handle any weather and encounter that is also robust and reliable. Additionally, the control system must adhere to the International Regulations for Preventing Collisions at Sea (COLREGs) for successful interaction with human sailors. Since the COLREGs were written for the human mind to interpret, they are written in ambiguous prose and therefore not machine-readable or verifiable. Due to these challenges and the wide variety of situations to be tackled, classical model-based approaches prove complicated to implement and computationally heavy. Within machine learning (ML), deep reinforcement learning (DRL) has shown great potential for a wide range of applications. The model-free and self-learning properties of DRL make it a promising candidate for autonomous vessels. In this work, a subset of the COLREGs is incorporated into a DRL-based path following and obstacle avoidance system using collision risk theory. The resulting autonomous agent dynamically interpolates between path following and COLREG-compliant collision avoidance in the training scenario, isolated encounter situations, and AIS-based simulations of real-world scenarios.

We study the problem of unconstrained distributed optimization in the context of multi-agents systems subject to limited communication connectivity. In particular we focus on the minimization of a sum of convex cost functions, where each component of the global function is available only to a specific agent and can thus be seen as a private local cost. The agents need to cooperate to compute the minimizer of the sum of all costs. We propose a consensus-like strategy to estimate a Newton-Raphson descending update for the local estimates of the global minimizer at each agent. In particular, the algorithm is based on the separation of time-scales principle and it is proved to converge to the global minimizer if a specific parameter that tunes the rate of convergence is chosen sufficiently small. We also provide numerical simulations and compare them with alternative distributed optimization strategies like the Alternating Direction Method of Multipliers and the Distributed Subgradient Method.

We consider estimation of network cardinality by distributed anonymous strategies relying on statistical inference methods. In particular, we focus on the relative Mean Square Error (MSE) of Maximum Likelihood (ML) estimators based on either the maximum or the average of M-dimensional vectors randomly generated at each node. In the case of continuous probability distributions, we show that the relative MSE achieved by the max-based strategy decreases as 1/M, independently of the used distribution, while that of the average-based estimator scales approximately as 2/M. We then introduce a novel strategy based on the average of M-dimensional vectors locally generated from Bernoulli random variables. In this case, the ML estimator, which is the Least Common Multiple (LCM) of the denominators of the irreducible fractions corresponding to the M elements of the average vector, leads to an MSE which goes exponentially to zero as M increases. We then discuss the effects of finite-precision arithmetics in practical dynamic implementations. Numerical experiments reveal that the MSE of the strategy based on Bernoulli trials is two order of magnitude smaller than that based on continuous random variables, at a price of one order of magnitude slower convergence time.

We address the problem of estimating the occupancy levels in rooms using the information available in standard HVAC systems. Instead of employing dedicated devices, we exploit the significant statistical correlations between the occupancy levels and the CO2 concentration, room temperature, and ventilation actuation signals in order to identify a dynamic model. The building occupancy estimation problem is formulated as a regularized deconvolution problem, where the estimated occupancy is the input that, when injected into the identified model, best explains the currently measured CO2 levels. Since occupancy levels are piecewise constant, the zero norm of occupancy is plugged into the cost function to penalize non-piecewise constant inputs. The problem then is seen as a particular case of fused-lasso estimator by relaxing the zero norm into the ℓ1 norm. We propose both online and offline estimators; the latter is shown to perform favorably compared to other data-based building occupancy estimators. Results on a real testbed show that the MSE of the proposed scheme, trained on a one-week-long dataset, is half the MSE of equivalent Neural Network (NN) or Support Vector Machine (SVM) estimation strategies.