Conformal Data-driven Control of Stochastic Multi-Agent Systems under Collaborative Signal Temporal Logic Specifications

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Vlahakis, Eleftherios E., Lindemann, Lars, Dimarogonas, Dimos V.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914004844150784
author Vlahakis, Eleftherios E.
Lindemann, Lars
Dimarogonas, Dimos V.
author_facet Vlahakis, Eleftherios E.
Lindemann, Lars
Dimarogonas, Dimos V.
contents We address control synthesis of stochastic discrete-time linear multi-agent systems under jointly chance-constrained collaborative signal temporal logic specifications in a distribution-free manner using available disturbance samples, which are partitioned into training and calibration sets. Leveraging linearity, we decompose each agent's system into deterministic nominal and stochastic error parts, and design disturbance feedback controllers to bound the stochastic errors by solving a tractable optimization problem over the training data. We then quantify prediction regions (PRs) for the aggregate error trajectories corresponding to agent cliques, involved in collaborative tasks, using conformal prediction and calibration data. This enables us to address the specified joint chance constraint via Lipschitz tightening and the computed PRs, and relax the centralized stochastic optimal control problem to a deterministic one, whose solution provides the feedforward inputs. To enhance scalability, we decompose the deterministic problem into agent-level subproblems solved in an MPC fashion, yielding a distributed control policy. Finally, we present an illustrative example and a comparison with [1].
format Preprint
id arxiv_https___arxiv_org_abs_2504_04615
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Conformal Data-driven Control of Stochastic Multi-Agent Systems under Collaborative Signal Temporal Logic Specifications
Vlahakis, Eleftherios E.
Lindemann, Lars
Dimarogonas, Dimos V.
Systems and Control
Multiagent Systems
We address control synthesis of stochastic discrete-time linear multi-agent systems under jointly chance-constrained collaborative signal temporal logic specifications in a distribution-free manner using available disturbance samples, which are partitioned into training and calibration sets. Leveraging linearity, we decompose each agent's system into deterministic nominal and stochastic error parts, and design disturbance feedback controllers to bound the stochastic errors by solving a tractable optimization problem over the training data. We then quantify prediction regions (PRs) for the aggregate error trajectories corresponding to agent cliques, involved in collaborative tasks, using conformal prediction and calibration data. This enables us to address the specified joint chance constraint via Lipschitz tightening and the computed PRs, and relax the centralized stochastic optimal control problem to a deterministic one, whose solution provides the feedforward inputs. To enhance scalability, we decompose the deterministic problem into agent-level subproblems solved in an MPC fashion, yielding a distributed control policy. Finally, we present an illustrative example and a comparison with [1].
title Conformal Data-driven Control of Stochastic Multi-Agent Systems under Collaborative Signal Temporal Logic Specifications
topic Systems and Control
Multiagent Systems
url https://arxiv.org/abs/2504.04615