Xavier: A Robot Navigation Architecture Based on Partially Observable Markov Decision Process Models. Koenig, S. & Simmons, R. G. In Artificial Intelligence Based Mobile Robotics: Case Studies of Successful Robot Systems, pages 91–122, 1998. MIT Press. abstract bibtex Autonomous mobile robots need very reliable navigation capabilities in order to operate unattended for long periods of time. We present a technique for achieving this goal that uses partially observable Markov decision process models (POMDPs) to explicitly model navigation uncertainty, including actuator and sensor uncertainty and approximate knowledge of the environment. This allows the robot to maintain a probability distribution over its current pose. Thus, while the robot rarely knows exactly where it is, it always has some belief as to what its true pose is, and is never completely lost. We present a navigation architecture based on POMDPs that provides a uniform framework with an established theoretical foundation for pose estimation, path planning, robot control during navigation, and learning. Our experiments show that this architecture indeed leads to robust corridor navigation for an actual indoor mobile robot. 1
@inproceedings{koenig_xavier:_1998,
title = {Xavier: {A} {Robot} {Navigation} {Architecture} {Based} on {Partially} {Observable} {Markov} {Decision} {Process} {Models}},
shorttitle = {Xavier},
abstract = {Autonomous mobile robots need very reliable navigation capabilities in order to operate unattended for long periods of time. We present a technique for achieving this goal that uses partially observable Markov decision process models (POMDPs) to explicitly model navigation uncertainty, including actuator and sensor uncertainty and approximate knowledge of the environment. This allows the robot to maintain a probability distribution over its current pose. Thus, while the robot rarely knows exactly where it is, it always has some belief as to what its true pose is, and is never completely lost. We present a navigation architecture based on POMDPs that provides a uniform framework with an established theoretical foundation for pose estimation, path planning, robot control during navigation, and learning. Our experiments show that this architecture indeed leads to robust corridor navigation for an actual indoor mobile robot. 1},
booktitle = {Artificial {Intelligence} {Based} {Mobile} {Robotics}: {Case} {Studies} of {Successful} {Robot} {Systems}},
publisher = {MIT Press},
author = {Koenig, Sven and Simmons, Reid G.},
year = {1998},
pages = {91--122}
}
Downloads: 0
{"_id":"ehyjQwGx7mKmmq4Q2","bibbaseid":"koenig-simmons-xavierarobotnavigationarchitecturebasedonpartiallyobservablemarkovdecisionprocessmodels-1998","authorIDs":[],"author_short":["Koenig, S.","Simmons, R. G."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Xavier: A Robot Navigation Architecture Based on Partially Observable Markov Decision Process Models","shorttitle":"Xavier","abstract":"Autonomous mobile robots need very reliable navigation capabilities in order to operate unattended for long periods of time. We present a technique for achieving this goal that uses partially observable Markov decision process models (POMDPs) to explicitly model navigation uncertainty, including actuator and sensor uncertainty and approximate knowledge of the environment. This allows the robot to maintain a probability distribution over its current pose. Thus, while the robot rarely knows exactly where it is, it always has some belief as to what its true pose is, and is never completely lost. We present a navigation architecture based on POMDPs that provides a uniform framework with an established theoretical foundation for pose estimation, path planning, robot control during navigation, and learning. Our experiments show that this architecture indeed leads to robust corridor navigation for an actual indoor mobile robot. 1","booktitle":"Artificial Intelligence Based Mobile Robotics: Case Studies of Successful Robot Systems","publisher":"MIT Press","author":[{"propositions":[],"lastnames":["Koenig"],"firstnames":["Sven"],"suffixes":[]},{"propositions":[],"lastnames":["Simmons"],"firstnames":["Reid","G."],"suffixes":[]}],"year":"1998","pages":"91–122","bibtex":"@inproceedings{koenig_xavier:_1998,\n\ttitle = {Xavier: {A} {Robot} {Navigation} {Architecture} {Based} on {Partially} {Observable} {Markov} {Decision} {Process} {Models}},\n\tshorttitle = {Xavier},\n\tabstract = {Autonomous mobile robots need very reliable navigation capabilities in order to operate unattended for long periods of time. We present a technique for achieving this goal that uses partially observable Markov decision process models (POMDPs) to explicitly model navigation uncertainty, including actuator and sensor uncertainty and approximate knowledge of the environment. This allows the robot to maintain a probability distribution over its current pose. Thus, while the robot rarely knows exactly where it is, it always has some belief as to what its true pose is, and is never completely lost. We present a navigation architecture based on POMDPs that provides a uniform framework with an established theoretical foundation for pose estimation, path planning, robot control during navigation, and learning. Our experiments show that this architecture indeed leads to robust corridor navigation for an actual indoor mobile robot. 1},\n\tbooktitle = {Artificial {Intelligence} {Based} {Mobile} {Robotics}: {Case} {Studies} of {Successful} {Robot} {Systems}},\n\tpublisher = {MIT Press},\n\tauthor = {Koenig, Sven and Simmons, Reid G.},\n\tyear = {1998},\n\tpages = {91--122}\n}\n\n","author_short":["Koenig, S.","Simmons, R. G."],"key":"koenig_xavier:_1998","id":"koenig_xavier:_1998","bibbaseid":"koenig-simmons-xavierarobotnavigationarchitecturebasedonpartiallyobservablemarkovdecisionprocessmodels-1998","role":"author","urls":{},"downloads":0},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/tillhofmann","creationDate":"2019-12-09T14:42:18.076Z","downloads":0,"keywords":[],"search_terms":["xavier","robot","navigation","architecture","based","partially","observable","markov","decision","process","models","koenig","simmons"],"title":"Xavier: A Robot Navigation Architecture Based on Partially Observable Markov Decision Process Models","year":1998,"dataSources":["9pYjFWPBodPyDyb7N"]}