Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


Dynamically Constructed (PO)MDPs for Adaptive Robot Planning

Shiqi Zhang, Piyush Khandelwal, and Peter Stone. Dynamically Constructed (PO)MDPs for Adaptive Robot Planning. In Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI), February 2017.

Download

[PDF]3.2MB  

Abstract

To operate in human-robot coexisting environments, intelligent robots need to imultaneously reason with commonsense knowledge and plan under uncertainty. Markov decision processes (MDPs) and partially observable MDPs (POMDPs), are good at planning under uncertainty toward maximizing long-term rewards; P-LOG, a declarative programming language under Answer Set semantics, is strong in commonsense reasoning. In this paper, we present a novel algorithm called iCORPP to dynamically reason about, and construct (PO)MDPs using P-LOG. iCORPP successfully shields exogenous domain attributes from (PO)MDPs, which limits computational complexity and enables (PO)MDPs to adapt to the value changes these attributes produce.We conduct a number of experimental trials using two example problems in simulation and demonstrate iCORPP on a real robot. Results show significant improvements compared to competitive baselines.

BibTeX Entry

@InProceedings{AAAI17-Zhang,
  author = {Shiqi Zhang and Piyush Khandelwal and Peter Stone},
  title = {Dynamically Constructed {(PO)MDP}s for Adaptive Robot Planning},
  booktitle = {Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI)},
  location = {San Francisco, CA},
  month = {February},
  year = {2017},
  abstract = {
    To operate in human-robot coexisting environments, intelligent robots need
      to imultaneously reason with commonsense knowledge and plan under
      uncertainty. Markov decision processes (MDPs) and partially observable
      MDPs (POMDPs), are good at planning under uncertainty toward maximizing
      long-term rewards; P-LOG, a declarative programming language under Answer
      Set semantics, is strong in commonsense reasoning. In this paper, we
      present a novel algorithm called iCORPP to dynamically reason about, and
      construct (PO)MDPs using P-LOG. iCORPP successfully shields exogenous
      domain attributes from (PO)MDPs, which limits computational complexity
      and enables (PO)MDPs to adapt to the value changes these attributes
      produce.We conduct a number of experimental trials using two example
      problems in simulation and demonstrate iCORPP on a real robot. Results
      show significant improvements compared to competitive baselines.
  },
}

Generated by bib2html.pl (written by Patrick Riley ) on Tue Mar 19, 2019 09:25:37