Mobile Robotics Planning using Abstract Markov Decision Processes

Pierre Laroche; François Charpillet; René Schott

inria-00098843, version 1

Mobile Robotics Planning using Abstract Markov Decision Processes

Pierre Laroche ()^a^, 1, François Charpillet ()^a^, 1, René Schott^b^, 2

International Conference on Tools with Artificial Intelligence - ICTAI'99 (1999) 299-306

Résumé : Markov Decision Processes have been successfully used in robotics for indoor robot navigation problems. They allow to compute optimal sequences of actions in order to achieve a given goal, accounting for actuators uncertainties. But MDPs are weak to avoid unknown obstacles. At the opposite reactive navigators are particulary a dapted to that, and don't need any prior knowledge about the environment. But they are unable to plan the set of actions that will permit the realization of a given mission. We present a new state aggregation technique for Markov Decision Processes, such that part of the work usually dedicated to the planner is achieved by a reactive navigator. Thus some characteristics of our environments, such as width of corridors, have not to be considered, which allows to cluster states together, si gnificantly reducing the state space. As a consequence, policies are computed faster and are shown to be at least as efficient as optimal ones.

a – INRIA
b – UNIVERSITE HENRI POINCARE
1 : MAIA (INRIA Lorraine - LORIA)
INRIA – CNRS : UMR7503 – Université Henri Poincaré - Nancy I – Université Nancy II – Institut National Polytechnique de Lorraine (INPL)
2 : Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA)
INRIA – CNRS : UMR7503 – Université Henri Poincaré - Nancy I – Université Nancy II – Institut National Polytechnique de Lorraine (INPL)

inria-00098843, version 1
http://hal.inria.fr/inria-00098843
oai:hal.inria.fr:inria-00098843
Contributeur : Publications Loria <>
Soumis le : Mardi 26 Septembre 2006, 08:39:07
Dernière modification le : Jeudi 28 Septembre 2006, 15:22:45

Voir la fiche détaillée

Exporter

Bibtex EndNote TEI RefWorks

%% inria-00098843, version 1
%% http://hal.inria.fr/inria-00098843
@inproceedings{laroche:inria-00098843,
    hal_id = {inria-00098843},
    url = {http://hal.inria.fr/inria-00098843},
    title = {{Mobile Robotics Planning using Abstract Markov Decision Processes}},
    author = {Laroche, Pierre and Charpillet, Fran{\c c}ois and Schott, Ren{\'e}},
    abstract = {{Markov Decision Processes have been successfully used in robotics for indoor robot navigation problems. They allow to compute optimal sequences of actions in order to achieve a given goal, accounting for actuators uncertainties. But MDPs are weak to avoid unknown obstacles. At the opposite reactive navigators are particulary a dapted to that, and don't need any prior knowledge about the environment. But they are unable to plan the set of actions that will permit the realization of a given mission. We present a new state aggregation technique for Markov Decision Processes, such that part of the work usually dedicated to the planner is achieved by a reactive navigator. Thus some characteristics of our environments, such as width of corridors, have not to be considered, which allows to cluster states together, si gnificantly reducing the state space. As a consequence, policies are computed faster and are shown to be at least as efficient as optimal ones.}},
    keywords = {planning under uncertainty; markov decision processes; state aggregation || planification sous incertitude; processus d{\'e}cisionnels de markov; agr{\'e}gation d'{\'e}tats},
    language = {Anglais},
    affiliation = {MAIA - INRIA Lorraine - LORIA , Laboratoire Lorrain de Recherche en Informatique et ses Applications - LORIA},
    booktitle = {{International Conference on Tools with Artificial Intelligence - ICTAI'99}},
    publisher = {none},
    pages = {299-306},
    address = {Chicago, Illinois},
    organization = {IEEE Computer Society},
    editor = {IEEE Computer Society },
    note = {Colloque avec actes et comit{\'e} de lecture. 99-R-251 || laroche99a 99-R-251 || laroche99a },
    audience = {non sp{\'e}cifi{\'e}e },
    year = {1999},
}

<?xml version="1.0" encoding="UTF-8"?>
<listBibl xmlns="http://www.tei-c.org/ns/1.0" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML">
<listBibl type="inproceedings"><head>Communications avec actes</head>
<biblStruct type="inproceedings" xml:id="inria-00098843"><analytic>
<author><persName><forename>Pierre</forename><surname>Laroche</surname></persName>
<affiliation>
<orgName type="laboratory">INRIA Lorraine - LORIA</orgName>
<orgName type="team">MAIA</orgName>
<country>FR</country>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">CNRS : UMR7503</orgName>
<orgName type="institution">Université Henri Poincaré - Nancy I</orgName>
<orgName type="institution">Université Nancy II</orgName>
<orgName type="institution">Institut National Polytechnique de Lorraine (INPL)</orgName>
</affiliation>
</author>
<author><persName><forename>François</forename><surname>Charpillet</surname></persName>
<affiliation>
<orgName type="laboratory">INRIA Lorraine - LORIA</orgName>
<orgName type="team">MAIA</orgName>
<country>FR</country>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">CNRS : UMR7503</orgName>
<orgName type="institution">Université Henri Poincaré - Nancy I</orgName>
<orgName type="institution">Université Nancy II</orgName>
<orgName type="institution">Institut National Polytechnique de Lorraine (INPL)</orgName>
</affiliation>
</author>
<author><persName><forename>René</forename><surname>Schott</surname></persName>
<affiliation>
<orgName type="laboratory">LORIA</orgName>
<orgName type="team">Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
<country>FR</country>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">CNRS : UMR7503</orgName>
<orgName type="institution">Université Henri Poincaré - Nancy I</orgName>
<orgName type="institution">Université Nancy II</orgName>
<orgName type="institution">Institut National Polytechnique de Lorraine (INPL)</orgName>
</affiliation>
</author>
<title type="main" level="a">Mobile Robotics Planning using Abstract Markov Decision Processes</title></analytic><monogr><meeting>International Conference on Tools with Artificial Intelligence - ICTAI'99</meeting><imprint><publisher>none</publisher><pubPlace><settlement>Chicago</settlement><country> Illinois</country></pubPlace><biblScope type="publicationDate">1999-00-00</biblScope><biblScope type="pp">299-306</biblScope></imprint></monogr><idno type="HALid">http://hal.inria.fr/inria-00098843</idno></biblStruct>
</listBibl>
</listBibl>