Obstacle Persistent Adaptive Map Maintenance for Autonomous Mobile Robots using Spatio-temporal Reasoning. Pitsch, M. L. & Pryor, M. W. In 2019 IEEE 15th International Conference on Automation Science and Engineering (CASE), pages 1023–1028, August, 2019. ISSN: 2161-8089doi abstract bibtex 9 downloads Mobile robotic systems operate in increasingly realistic scenarios even as users have increased expectations for the duration of autonomous tasks. Mobile robots face unique challenges when operating in environments that change over time, where systems must maintain an accurate representation of the environment with respect to both spatial and temporal dimensions. This paper describes a spatio-temporal technique for extending the autonomy of a mobile robot in a changing environment. This new technique called Obstacle Persistent Adaptive Map Maintenance (OPAMM) uses navigation data collected during normal operations to perform periodic self-maintenance of its environment model. OPAMM implements a probabilistic feature persistence model to predict the survival state of obstacles and update the world model. Maintaining an accurate world model is necessary for extending the long-term autonomy of robots in realistic scenarios. Results show that robots using OPAMM had localizations scores higher than other methods, thus reducing long-term localization degradation.
@inproceedings{pitsch_obstacle_2019,
title = {Obstacle {Persistent} {Adaptive} {Map} {Maintenance} for {Autonomous} {Mobile} {Robots} using {Spatio}-temporal {Reasoning}},
doi = {10.1109/COASE.2019.8843095},
abstract = {Mobile robotic systems operate in increasingly realistic scenarios even as users have increased expectations for the duration of autonomous tasks. Mobile robots face unique challenges when operating in environments that change over time, where systems must maintain an accurate representation of the environment with respect to both spatial and temporal dimensions. This paper describes a spatio-temporal technique for extending the autonomy of a mobile robot in a changing environment. This new technique called Obstacle Persistent Adaptive Map Maintenance (OPAMM) uses navigation data collected during normal operations to perform periodic self-maintenance of its environment model. OPAMM implements a probabilistic feature persistence model to predict the survival state of obstacles and update the world model. Maintaining an accurate world model is necessary for extending the long-term autonomy of robots in realistic scenarios. Results show that robots using OPAMM had localizations scores higher than other methods, thus reducing long-term localization degradation.},
booktitle = {2019 {IEEE} 15th {International} {Conference} on {Automation} {Science} and {Engineering} ({CASE})},
author = {Pitsch, Meredith L. and Pryor, Mitchell W.},
month = aug,
year = {2019},
note = {ISSN: 2161-8089},
keywords = {Automation, Computer aided software engineering, Conferences, OPAMM, autonomous mobile robots, autonomous tasks, changing environment, environment model, long-term localization degradation, mobile robotic systems, mobile robots, obstacle persistent adaptive map maintenance, periodic self-maintenance, probabilistic feature persistence model, spatial dimensions, spatio-temporal reasoning, spatio-temporal technique, temporal dimensions, temporal reasoning},
pages = {1023--1028},
}
Downloads: 9
{"_id":"tWTZuMqkMw8SHzjLR","bibbaseid":"pitsch-pryor-obstaclepersistentadaptivemapmaintenanceforautonomousmobilerobotsusingspatiotemporalreasoning-2019","authorIDs":[],"author_short":["Pitsch, M. L.","Pryor, M. W."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Obstacle Persistent Adaptive Map Maintenance for Autonomous Mobile Robots using Spatio-temporal Reasoning","doi":"10.1109/COASE.2019.8843095","abstract":"Mobile robotic systems operate in increasingly realistic scenarios even as users have increased expectations for the duration of autonomous tasks. Mobile robots face unique challenges when operating in environments that change over time, where systems must maintain an accurate representation of the environment with respect to both spatial and temporal dimensions. This paper describes a spatio-temporal technique for extending the autonomy of a mobile robot in a changing environment. This new technique called Obstacle Persistent Adaptive Map Maintenance (OPAMM) uses navigation data collected during normal operations to perform periodic self-maintenance of its environment model. OPAMM implements a probabilistic feature persistence model to predict the survival state of obstacles and update the world model. Maintaining an accurate world model is necessary for extending the long-term autonomy of robots in realistic scenarios. Results show that robots using OPAMM had localizations scores higher than other methods, thus reducing long-term localization degradation.","booktitle":"2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)","author":[{"propositions":[],"lastnames":["Pitsch"],"firstnames":["Meredith","L."],"suffixes":[]},{"propositions":[],"lastnames":["Pryor"],"firstnames":["Mitchell","W."],"suffixes":[]}],"month":"August","year":"2019","note":"ISSN: 2161-8089","keywords":"Automation, Computer aided software engineering, Conferences, OPAMM, autonomous mobile robots, autonomous tasks, changing environment, environment model, long-term localization degradation, mobile robotic systems, mobile robots, obstacle persistent adaptive map maintenance, periodic self-maintenance, probabilistic feature persistence model, spatial dimensions, spatio-temporal reasoning, spatio-temporal technique, temporal dimensions, temporal reasoning","pages":"1023–1028","bibtex":"@inproceedings{pitsch_obstacle_2019,\n\ttitle = {Obstacle {Persistent} {Adaptive} {Map} {Maintenance} for {Autonomous} {Mobile} {Robots} using {Spatio}-temporal {Reasoning}},\n\tdoi = {10.1109/COASE.2019.8843095},\n\tabstract = {Mobile robotic systems operate in increasingly realistic scenarios even as users have increased expectations for the duration of autonomous tasks. Mobile robots face unique challenges when operating in environments that change over time, where systems must maintain an accurate representation of the environment with respect to both spatial and temporal dimensions. This paper describes a spatio-temporal technique for extending the autonomy of a mobile robot in a changing environment. This new technique called Obstacle Persistent Adaptive Map Maintenance (OPAMM) uses navigation data collected during normal operations to perform periodic self-maintenance of its environment model. OPAMM implements a probabilistic feature persistence model to predict the survival state of obstacles and update the world model. Maintaining an accurate world model is necessary for extending the long-term autonomy of robots in realistic scenarios. Results show that robots using OPAMM had localizations scores higher than other methods, thus reducing long-term localization degradation.},\n\tbooktitle = {2019 {IEEE} 15th {International} {Conference} on {Automation} {Science} and {Engineering} ({CASE})},\n\tauthor = {Pitsch, Meredith L. and Pryor, Mitchell W.},\n\tmonth = aug,\n\tyear = {2019},\n\tnote = {ISSN: 2161-8089},\n\tkeywords = {Automation, Computer aided software engineering, Conferences, OPAMM, autonomous mobile robots, autonomous tasks, changing environment, environment model, long-term localization degradation, mobile robotic systems, mobile robots, obstacle persistent adaptive map maintenance, periodic self-maintenance, probabilistic feature persistence model, spatial dimensions, spatio-temporal reasoning, spatio-temporal technique, temporal dimensions, temporal reasoning},\n\tpages = {1023--1028},\n}\n\n","author_short":["Pitsch, M. L.","Pryor, M. W."],"key":"pitsch_obstacle_2019","id":"pitsch_obstacle_2019","bibbaseid":"pitsch-pryor-obstaclepersistentadaptivemapmaintenanceforautonomousmobilerobotsusingspatiotemporalreasoning-2019","role":"author","urls":{},"keyword":["Automation","Computer aided software engineering","Conferences","OPAMM","autonomous mobile robots","autonomous tasks","changing environment","environment model","long-term localization degradation","mobile robotic systems","mobile robots","obstacle persistent adaptive map maintenance","periodic self-maintenance","probabilistic feature persistence model","spatial dimensions","spatio-temporal reasoning","spatio-temporal technique","temporal dimensions","temporal reasoning"],"metadata":{"authorlinks":{}},"downloads":9,"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero-group/mpryor/246442","creationDate":"2020-05-10T01:03:15.143Z","downloads":9,"keywords":["automation","computer aided software engineering","conferences","opamm","autonomous mobile robots","autonomous tasks","changing environment","environment model","long-term localization degradation","mobile robotic systems","mobile robots","obstacle persistent adaptive map maintenance","periodic self-maintenance","probabilistic feature persistence model","spatial dimensions","spatio-temporal reasoning","spatio-temporal technique","temporal dimensions","temporal reasoning"],"search_terms":["obstacle","persistent","adaptive","map","maintenance","autonomous","mobile","robots","using","spatio","temporal","reasoning","pitsch","pryor"],"title":"Obstacle Persistent Adaptive Map Maintenance for Autonomous Mobile Robots using Spatio-temporal Reasoning","year":2019,"dataSources":["E5HAvRxzabR7xmf5S","NnPAtJvwQQamPe64H"]}