Extensions of POMCP Planning and Applications to Robotic and Cyber-physical Systems

Alberto Castellini, Enrico Marchesini, G. Mazzi, Federico Bianchi, Maddalena Zuccotto, Alessandro FarinelliZenodo 2021 · DOI · OpenAlex

Abstract

We present recent results related to extensions and applications of Partially Observable Monte Carlo Planning to real-world problems involving robotic and cyber-physical systems. Experiments were performed in the context of two projects: "Dipartimenti di Eccellenza 2018-22", Italian Ministry of Education, Universities and Research, and "Safe Place: Sistemi IoT per ambienti di vita salubri e sicuri", POR FESR 2014-20. Three main research lines are developed. The first concerns the explanation and monitoring of POMCP policies by integrating symbolic and non-symbolic approaches. The second regards the applicability of POMCP to real robotic scenarios. The third concerns POMCP policy improvement and adaptation.
BibTeX
@inproceedings{castellini2021extensions,
  author = {Alberto Castellini and Enrico Marchesini and G. Mazzi and Federico Bianchi and Maddalena Zuccotto and Alessandro Farinelli},
  title = {{Extensions of POMCP Planning and Applications to Robotic and Cyber-physical Systems}},
  booktitle = {Zenodo},
  year = {2021},
  doi = {10.5281/zenodo.6367936},
}

Loading related content...

Figure