Risk-averse trajectory optimization via sample average approximation

T Lew, R Bonalli, M Pavone - IEEE Robotics and Automation …, 2023 - ieeexplore.ieee.org
Trajectory optimization under uncertainty underpins a wide range of applications in robotics.
However, existing methods are limited in terms of reasoning about sources of epistemic and …

On the viability and invariance of proper sets under continuity inclusions in wasserstein spaces

B Bonnet-Weill, H Frankowska - SIAM Journal on Mathematical Analysis, 2024 - SIAM
In this article, we derive conditions for the existence of solutions to state-constrained
continuity inclusions in Wasserstein spaces whose right-hand sides may be discontinuous in …

Sample average approximation for stochastic programming with equality constraints

T Lew, R Bonalli, M Pavone - SIAM Journal on Optimization, 2024 - SIAM
We revisit the sample average approximation (SAA) approach for nonconvex stochastic
programming. We show that applying the SAA approach to problems with expected value …

An extension of Pontryagin Maximum principle in interval environment and its application to inventory problem

S Das, F Akhtar, AA Shaikh, AK Bhunia - IFAC Journal of Systems and …, 2024 - Elsevier
The control theory is one of the most fundamental branches of engineering as it implicates
solving abilities of numerous non-linear engineering design problems efficiently. Again …

A Gradient Descent-Ascent Method for Continuous-Time Risk-Averse Optimal Control

G Velho, J Auriol, R Bonalli - arXiv preprint arXiv:2306.12878, 2023 - arxiv.org
In this paper, we consider continuous-time stochastic optimal control problems where the
cost is evaluated through a coherent risk measure. We provide an explicit gradient descent …

[HTML][HTML] Maximum Principle for Variable-Order Fractional Conformable Differential Equation with a Generalized Tempered Fractional Laplace Operator

T Guan, L Zhang - Fractal and Fractional, 2023 - mdpi.com
In this paper, we investigate properties of solutions to a space-time fractional variable-order
conformable nonlinear differential equation with a generalized tempered fractional Laplace …

A Pontryagin Maximum Principle for agent-based models with convex state space

S Almi, R Durastanti, F Solombrino - arXiv preprint arXiv:2402.13680, 2024 - arxiv.org
We derive a first order optimality condition for a class of agent-based systems, as well as for
their mean-field counterpart. A relevant difficulty of our analysis is that the state equation is …

Non-Parametric Learning of Stochastic Differential Equations with Non-asymptotic Fast Rates of Convergence

R Bonalli, A Rudi - arXiv preprint arXiv:2305.15557, 2023 - arxiv.org
We propose a novel non-parametric learning paradigm for the identification of drift and
diffusion coefficients of multi-dimensional non-linear stochastic differential equations, which …

A Gradient Descent-Ascent Method for Continuous-Time Risk-Averse Optimal Control

R Bonalli, V Gabriel, J Auriol - 2024 - hal.science
In this paper, we consider continuous-time stochastic optimal control problems where the
cost is evaluated through a coherent risk measure. We provide an explicit gradient descent …

[图书][B] Uncertainty-Aware Control, Planning, and Learning for Reliable Robotic Autonomy

TJ Lew - 2023 - search.proquest.com
As autonomous systems take on increasingly challenging tasks in safety-critical settings
such as autonomous driving and aerospace, their ability to explicitly account for uncertainty …