DBDimitris Boskos

Dimitris Boskos

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Dimitris Boskos has a total of 8 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Reinforcement Learning with Distributed MPC for Fuel-Efficient Platoon Control with Discrete Gear Transitions

    by Samuel Mallick, Gianpietro Battocletti, Dimitris Boskos, Azita Dabiri, Bart De Schutter

    Cooperative control of groups of autonomous vehicles (AVs), i.e., platoons, is a promising direction to improving the efficiency of autonomous transportation systems. In this context, distributed co-optimization of both vehicle speed and gear position can offer benefits for fuel-efficient driving. To this end, model predictive control (MPC) is a popular approach, optimizing the speed and gear-shift schedule while explicitly considering the vehicles' dynamics over a prediction window. However, optimization over both the vehicles' continuous dynamics and discrete gear positions is computationally intensive, and may require overly long sample times or high-end hardware for real-time implementation. This work proposes a reinforcement learning (RL)-based distributed MPC approach to address this issue. For each vehicle in the platoon, a policy is trained to select and fix the gear positions across the prediction window of a local MPC controller, leaving a significantly simpler continuous optimization problem to be solved as part of a distributed MPC scheme. In order to reduce the computational cost of training and facilitate the scalability of the proposed approach to large platoons, the policies are parameterized such that the emergent multi-agent RL problem can be decoupled into single-agent learning tasks. In addition, a recurrent neural-network (RNN) architecture is proposed for the gear selection policy, such that the learning is scalable even as the number of possible gear-shift schedules grows exponentially with the MPC prediction horizon. In highway-driving simulations, the proposed approach is shown to have a significantly lower computation burden and a comparable performance in terms of fuel-efficient platoon control, with respect to pure MPC-based co-optimization.


  • Open Access

    Reduced-Order Modelling and Closed-Loop Control of the Cylinder Wake

    by Tea Vojković, Dimitris Boskos, Abel-John Buchner

    We present a model-based approach for the closed-loop control of vortex shedding in the cylinder wake. The control objective is to suppress the unsteadiness of the flow, which arises at a critical Reynolds number $Re_c$ through a supercritical Hopf bifurcation. In the vicinity of $Re_c$ the flow is well described by a forced Stuart-Landau equation derived via a global weakly nonlinear analysis. This Stuart-Landau equation governs the evolution of the amplitude $A$ of the global mode on the slow time scale. In this paper, we generalize the approach from [Sipp 2012], which considers a fixed-amplitude harmonic forcing, by allowing the forcing amplitude E0 to vary on the slow time scale. This enables the design of closed-loop controllers for multiple surrogate Stuart-Landau models, which we obtain for different classes of forcing frequencies. When these frequencies are near the global mode oscillation frequency at Rec, we can bring both $A$ and $E'$ to zero, which fully suppresses the unsteady part of the flow. We also show that near this frequency, the optimal forcing structure is in the direction of the adjoint global mode. Assuming partial velocity measurements of the flow, we design an output-feedback control law that stabilizes the flow. The approach hinges on a model predictive controller for the surrogate model, which exploits the full-order model measurements to determine the necessary forcing amplitudes while respecting the modelling constraints. We achieve suppression of the wake oscillations with spatially dense volume forcing and two-point velocity measurement at $Re=50$.

  • Open Access

    High-Confidence Data-Driven Ambiguity Sets for Time-Varying Linear Systems

    by Dimitris Boskos, Jorge Cortés, Sonia Martínez

    This paper builds Wasserstein ambiguity sets for the unknown probability distribution of dynamic random variables leveraging noisy partial-state observations. The constructed ambiguity sets contain the true distribution of the data with quantifiable probability and can be exploited to formulate robust stochastic optimization problems with out-of-sample guarantees. We assume the random variable evolves in discrete time under uncertain initial conditions and dynamics, and that noisy partial measurements are available. All random elements have unknown probability distributions and we make inferences about the distribution of the state vector using several output samples from multiple realizations of the process. To this end, we leverage an observer to estimate the state of each independent realization and exploit the outcome to construct the ambiguity sets. We illustrate our results in an economic dispatch problem involving distributed energy resources over which the scheduler has no direct control.