People - Miloš Prágr

Miloš Prágr

About

My research aims to improve the autonomy of mobile robots on long-term, unsupervised missions in outdoor environments. I study traversability, which describes the ease or difficulty experienced by the robot when attempting to traverse a particular terrain. For a mobile robot, understanding its traversability is crucial for its ability to select safe and efficient paths through potentially hazardous environments without supervision. My main focus is on assessing traversability through complex environments, such as terrains whose traversability changes with time or vegetation that appears rigid but can be passed through. To address these challenges, I advocate that traversability models should be adapted incrementally during the deployment, both exploiting the robot’s newly accrued experience and actively seeking new information about unknown areas. To this end, my contributions are centered on applying incremental learning and active perception in traversability modeling.

Position after leaving CRL:

Postdoc researcher at Autonomous Mobile Machines Group, Tampere University

Publications (20)

Prágr, Miloš and Feber, Jan and Adámek, Roman and Hulchuk, Vsevolod and Mazal, Jan and Faigl, Jan: On Autonomous Ground Vehicle Navigation in Leader-Follower Off-Road Environments, 2024 Modelling and Simulation for Autonomous Systems (MESAS), 2026, pp. 146–161.

PDF url BibTeX

@inproceedings{pragr24mesas,
	author = {Prágr, Miloš and Feber, Jan and Adámek, Roman and Hulchuk, Vsevolod and Mazal, Jan and Faigl, Jan},
	title = {On Autonomous Ground Vehicle Navigation in Leader-Follower Off-Road Environments},
	booktitle = {2024 Modelling and Simulation for Autonomous Systems (MESAS)},
	pages = {146–161},
	year = {2026},
	doi = {10.1007/978-3-031-99732-7_10},
}

Prágr, Miloš and Bayer, Jan and Faigl, Jan: On Predicting Terrain Changes Induced by Mobile Robot Traversal, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024, pp. 11693–11698.

PDF url BibTeX

@inproceedings{pragr24iros,
	author = {Prágr, Miloš and Bayer, Jan and Faigl, Jan},
	title = {On Predicting Terrain Changes Induced by Mobile Robot Traversal},
	booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
	pages = {11693–11698},
	year = {2024},
	doi = {10.1109/IROS58592.2024.10802070},
}

Faigl, Jan and Prágr, Miloš and Kubík, Jiří: On Autonomous Mobile Robot Exploration Projects in Robotics Course, International Conference on Robotics in Education (RiE), 2023, pp. 3–15.

PDF url BibTeX

@inproceedings{faigl23rie,
	author = {Faigl, Jan and Prágr, Miloš and Kubík, Jiří},
	title = {On Autonomous Mobile Robot Exploration Projects in Robotics Course},
	booktitle = {International Conference on Robotics in Education (RiE)},
	pages = {3–15},
	year = {2023},
	doi = {10.1007/978-3-031-38454-7_1},
}

Prágr, Miloš and Bayer, Jan and Faigl, Jan: Autonomous exploration with online learning of traversable yet visually rigid obstacles, Autonomous Robots, 47 :161–180, 2023.

PDF url BibTeX

@article{pragr22auro,
	author = {Prágr, Miloš and Bayer, Jan and Faigl, Jan},
	title = {Autonomous exploration with online learning of traversable yet visually rigid obstacles},
	journal= {Autonomous Robots},
	volume= {47},
	number= {},
	pages = {161–180},
	year = {2023},
	doi = {10.1007/s10514-022-10075-4},
}

Prágr, Miloš and Szadkowski, Rudolf and Bayer, Jan and Zelinka, Josef and Faigl, Jan: Terrain Traversal Cost Learning with Knowledge Transfer Between Multi-legged Walking Robot Gaits, 2022 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC), 2022, pp. 148–153.

PDF url BibTeX

@inproceedings{pragr22icarsc,
	author = {Prágr, Miloš and Szadkowski, Rudolf and Bayer, Jan and Zelinka, Josef and Faigl, Jan},
	title = {Terrain Traversal Cost Learning with Knowledge Transfer Between Multi-legged Walking Robot Gaits},
	booktitle = {2022 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)},
	pages = {148–153},
	year = {2022},
	doi = {10.1109/ICARSC55462.2022.9784790},
}

Zelinka, Josef and Prágr, Miloš and Szadkowski, Rudolf and Bayer, Jan and Faigl, Jan: Deep Transfer Learning of Traversability Assessment for Heterogeneous Robots, Conference Information Technologies - Applications and Theory (ITAT), 2022, pp. 12–20.

PDF BibTeX

@inproceedings{zelinka22itat,
	author = {Zelinka, Josef and Prágr, Miloš and Szadkowski, Rudolf and Bayer, Jan and Faigl, Jan},
	title = {Deep Transfer Learning of Traversability Assessment for  Heterogeneous Robots},
	booktitle = {Conference Information Technologies - Applications and Theory (ITAT)},
	pages = {12–20},
	year = {2022},
	doi = {},
}

Zelinka, Josef and Prágr, Miloš and Szadkowski, Rudolf and Bayer, Jan and Faigl, Jan: Traversability Transfer Learning Between Robots with Different Cost Assessment Policies, 2021 Modelling and Simulation for Autonomous Systems (MESAS), 2022, pp. 333–344.

PDF url BibTeX

@inproceedings{zelinka21mesas,
	author = {Zelinka, Josef and Prágr, Miloš and Szadkowski, Rudolf and Bayer, Jan and Faigl, Jan},
	title = {Traversability Transfer Learning Between Robots with Different Cost Assessment Policies},
	booktitle = {2021 Modelling and Simulation for Autonomous Systems (MESAS)},
	pages = {333–344},
	year = {2022},
	doi = {10.1007/978-3-030-98260-7_21},
}

Prágr, Miloš and Bayer, Jan and Faigl, Jan: Autonomous robotic exploration with simultaneous environment and traversability models learning, Frontiers in Robotics and AI, 9 :, 2022.

PDF url BibTeX

@article{pragr22frontiers,
	author = {Prágr, Miloš and Bayer, Jan and Faigl, Jan},
	title = {Autonomous robotic exploration with simultaneous environment and traversability models learning},
	journal= {Frontiers in Robotics and AI},
	volume= {9},
	number= {},
	pages = {},
	year = {2022},
	doi = {10.3389/frobt.2022.910113},
}

Zoula, Martin and Prágr, Miloš and Faigl, Jan: On Building Communication Maps in Subterranean Environments, 2020 Modelling and Simulation for Autonomous Systems (MESAS), 2021, pp. 15–28.

PDF url BibTeX

@inproceedings{zoula20mesas,
	author = {Zoula, Martin and Prágr, Miloš and Faigl, Jan},
	title = {On Building Communication Maps in Subterranean Environments},
	booktitle = {2020 Modelling and Simulation for Autonomous Systems (MESAS)},
	pages = {15–28},
	year = {2021},
	doi = {10.1007/978-3-030-70740-8_2},
}

Szadkowski, Rudolf and Prágr, Miloš and Faigl, Jan: Self-Learning Event Mistiming Detector Based on Central Pattern Generator, Frontiers in Neurorobotics, 15 :5, 2021.

PDF url BibTeX

@article{szadkowski21frontiers,
	author = {Szadkowski, Rudolf and Prágr, Miloš and Faigl, Jan},
	title = {Self-Learning Event Mistiming Detector Based on Central Pattern Generator},
	journal= {Frontiers in Neurorobotics},
	volume= {15},
	number= {},
	pages = {5},
	year = {2021},
	doi = {10.3389/fnbot.2021.629652},
}

Szadkowski, Rudolf and Prágr, Miloš and Faigl, Jan: Transfer of Inter-Robotic Inductive Classifier, International Conference on Automation, Control and Robots (ICACR), 2020, pp. 32–36.

PDF url BibTeX

@inproceedings{szadkowski20icacr,
	author = {Szadkowski, Rudolf and Prágr, Miloš and Faigl, Jan},
	title = {Transfer of Inter-Robotic Inductive Classifier},
	booktitle = {International Conference on Automation, Control and Robots (ICACR)},
	pages = {32–36},
	year = {2020},
	doi = {10.1109/ICACR51161.2020.9265509},
}

Prágr, Miloš and Váňa, Petr and Faigl, Jan: Aerial Reconnaissance and Ground Robot Terrain Learning in Traversal Cost Assessment, 2019 Modelling and Simulation for Autonomous Systems (MESAS), 2020, pp. 3–10.

PDF url BibTeX

@inproceedings{pragr19mesas_uav,
	author = {Prágr, Miloš and Váňa, Petr and Faigl, Jan},
	title = {Aerial Reconnaissance and Ground Robot Terrain Learning in Traversal Cost Assessment},
	booktitle = {2019 Modelling and Simulation for Autonomous Systems (MESAS)},
	pages = {3–10},
	year = {2020},
	doi = {10.1007/978-3-030-43890-6_1},
}

Prágr, Miloš and Faigl, Jan: Terrain Learning Using Time Series of Ground Unit Traversal Cost, 2019 Modelling and Simulation for Autonomous Systems (MESAS), 2020, pp. 97–107.

PDF url BibTeX

@inproceedings{pragr19mesas_terrain,
	author = {Prágr, Miloš and Faigl, Jan},
	title = {Terrain Learning Using Time Series of Ground Unit Traversal Cost},
	booktitle = {2019 Modelling and Simulation for Autonomous Systems (MESAS)},
	pages = {97–107},
	year = {2020},
	doi = {10.1007/978-3-030-43890-6_8},
}

Faigl, Jan and Prágr, Miloš: Incremental Traversability Assessment Learning Using Growing Neural Gas Algorithm, Advances in Self-Organizing Maps, Learning Vector Quantization, Clustering and Data Visualization (WSOM 2019), 2020, pp. 166–176.

PDF url BibTeX

@inproceedings{faigl19wsom,
	author = {Faigl, Jan and Prágr, Miloš},
	title = {Incremental Traversability Assessment Learning Using Growing Neural Gas Algorithm},
	booktitle = {Advances in Self-Organizing Maps, Learning Vector Quantization, Clustering and Data Visualization (WSOM 2019)},
	pages = {166–176},
	year = {2020},
	doi = {10.1007/978-3-030-19642-4_17},
}

Faigl, Jan and Prágr, Miloš: On Unsupervised Learning of Traversal Cost and Terrain Types Identification using Self-Organizing Maps, International Conference on Artificial Neural Networks (ICANN), 2019, pp. 654–668.

PDF url BibTeX

@inproceedings{faigl19icann,
	author = {Faigl, Jan and Prágr, Miloš},
	title = {On Unsupervised Learning of Traversal Cost and Terrain Types Identification using Self-Organizing Maps},
	booktitle = {International Conference on Artificial Neural Networks (ICANN)},
	pages = {654–668},
	year = {2019},
	doi = {10.1007/978-3-030-30487-4_50},
}

Prágr, Miloš and Čížek, Petr and Bayer, Jan and Faigl, Jan: Online Incremental Learning of the Terrain Traversal Cost in Autonomous Exploration, Robotics: Science and Systems (RSS), 2019, pp. .

PDF url BibTeX

@inproceedings{pragr19rss,
	author = {Prágr, Miloš and Čížek, Petr and Bayer, Jan and Faigl, Jan},
	title = {Online Incremental Learning of the Terrain Traversal Cost in Autonomous Exploration},
	booktitle = {Robotics: Science and Systems (RSS)},
	pages = {},
	year = {2019},
	doi = {10.15607/RSS.2019.XV.040},
}

Prágr, Miloš and Faigl, Jan: Benchmarking Incremental Regressors in Traversal Cost Assessment, International Conference on Artificial Neural Networks (ICANN), 2019, pp. 685–697.

PDF url BibTeX

@inproceedings{pragr19icann,
	author = {Prágr, Miloš and Faigl, Jan},
	title = {Benchmarking Incremental Regressors in Traversal Cost Assessment},
	booktitle = {International Conference on Artificial Neural Networks (ICANN)},
	pages = {685–697},
	year = {2019},
	doi = {10.1007/978-3-030-30487-4_52},
}

Prágr, Miloš and Čížek, Petr and Faigl, Jan: Traversal Cost Modeling Based on Motion Characterization for Multi-legged Walking Robots, European Conference on Mobile Robots (ECMR), 2019, pp. 1–6.

PDF url BibTeX

@inproceedings{pragr19ecmr,
	author = {Prágr, Miloš and Čížek, Petr and Faigl, Jan},
	title = {Traversal Cost Modeling Based on Motion Characterization for Multi-legged Walking Robots},
	booktitle = {European Conference on Mobile Robots (ECMR)},
	pages = {1–6},
	year = {2019},
	doi = {10.1109/ECMR.2019.8870912},
}

Prágr, Miloš and Čížek, Petr and Faigl, Jan: Incremental Learning of Traversability Cost for Aerial Reconnaissance Support to Ground Units, Modelling and Simulation for Autonomous Systems (MESAS), 2019, pp. 412–421.

PDF url BibTeX

@inproceedings{pragr18mesas,
	author = {Prágr, Miloš and Čížek, Petr and Faigl, Jan},
	title = {Incremental Learning of Traversability Cost for Aerial Reconnaissance Support to Ground Units},
	booktitle = {Modelling and Simulation for Autonomous Systems (MESAS)},
	pages = {412–421},
	year = {2019},
	doi = {10.1007/978-3-030-14984-0_30},
}

Prágr, Miloš and Čížek, Petr and Faigl, Jan: Cost of Transport Estimation for Legged Robot Based on Terrain Features Inference from Aerial Scan, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018, pp. 1745–1750.

PDF url BibTeX

@inproceedings{pragr18iros,
	author = {Prágr, Miloš and Čížek, Petr and Faigl, Jan},
	title = {Cost of Transport Estimation for Legged Robot Based on Terrain Features Inference from Aerial Scan},
	booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
	pages = {1745–1750},
	year = {2018},
	doi = {10.1109/IROS.2018.8593374},
}