Enhancing Data-Driven Stochastic Control via Bundled Interval MDP | IEEE Journals & Magazine | IEEE Xplore

Enhancing Data-Driven Stochastic Control via Bundled Interval MDP

Publisher: IEEE

Abstract:

The abstraction of dynamical systems is a powerful tool that enables the design of feedback controllers using a correct-by-design framework. We investigate a novel scheme...View more

Abstract:

The abstraction of dynamical systems is a powerful tool that enables the design of feedback controllers using a correct-by-design framework. We investigate a novel scheme to obtain data-driven abstractions of discrete-time stochastic processes in terms of richer discrete stochastic models, whose actions lead to nondeterministic transitions over the space of probability measures. The data-driven component of the proposed methodology lies in the fact that we only assume samples from an unknown probability distribution. We also rely on the model of the underlying dynamics to build our abstraction through backward reachability computations. The nondeterminism in the probability space is captured by a collection of Markov Processes, and we identify how this model can improve upon existing abstraction techniques in terms of satisfying temporal properties, such as safety or reach-avoid. The connection between the discrete and the underlying dynamics is made formal through the use of the scenario approach theory. Numerical experiments illustrate the advantages and main limitations of the proposed techniques with respect to existing approaches.
Published in: IEEE Control Systems Letters ( Volume: 8)
Page(s): 2069 - 2074
Date of Publication: 20 June 2024
Electronic ISSN: 2475-1456
Publisher: IEEE

References

References is not available for this document.