• Home
  • Results
  • Publications

Publications

Journal Publications

 

  1. Athina Ilioudi, Azita Dabiri, Ben J Wolf and Bart De Schutter. Deep Learning for Object Detection and Segmentation in Videos: Toward an Integration With Domain Knowledge. IEEE Access, 2022. URL, DOI BibTeX

    @article{ilioudi_Deep_2022,
    	title = "Deep {Learning} for {Object} {Detection} and {Segmentation} in {Videos}: {Toward} an {Integration} {With} {Domain} {Knowledge}",
    	url = "https://ieeexplore.ieee.org/document/9743897",
    	doi = "10.1109/ACCESS.2022.3162827",
    	abstract = "Deep learning has enabled the rapid expansion of computer vision tasks from image frames to video segments. This paper focuses on the review of the latest research in the field of computer vision tasks in general and on object localization and identification of their associated pixels in video frames in particular. After performing a systematic analysis of the existing methods, the challenges related to computer vision tasks are presented. In order to address the existing challenges, a hybrid framework is proposed, where deep learning methods are coupled with domain knowledge. An additional feature of this survey is that a review of the currently existing approaches integrating domain knowledge with deep learning techniques is presented. Finally, some conclusions on the implementation of hybrid architectures to perform computer vision tasks are discussed.",
    	urldate = "2022-05-05",
    	journal = "IEEE Access",
    	author = "Ilioudi, Athina and Dabiri, Azita and Wolf, Ben J. and De Schutter, Bart",
    	month = "",
    	year = 2022
    }
    
  2. Daniël M Bot, Ben J Wolf and Sietse M Netten. The Quadrature Method: A Novel Dipole Localisation Algorithm for Artificial Lateral Lines Compared to State of the Art. Sensors 21(13):4558, 2021. URL, DOI BibTeX

    @article{bot_Quadrature_2021,
    	title = "The {Quadrature} {Method}: {A} {Novel} {Dipole} {Localisation} {Algorithm} for {Artificial} {Lateral} {Lines} {Compared} to {State} of the {Art}",
    	volume = 21,
    	copyright = "http://creativecommons.org/licenses/by/3.0/",
    	issn = "1424-8220",
    	shorttitle = "The {Quadrature} {Method}",
    	url = "https://www.mdpi.com/1424-8220/21/13/4558",
    	doi = "10.3390/s21134558",
    	abstract = "The lateral line organ of fish has inspired engineers to develop flow sensor arrays—dubbed artificial lateral lines (ALLs)—capable of detecting near-field hydrodynamic events for obstacle avoidance and object detection. In this paper, we present a comprehensive review and comparison of ten localisation algorithms for ALLs. Differences in the studied domain, sensor sensitivity axes, and available data prevent a fair comparison between these algorithms from their original works. We compare them with our novel quadrature method (QM), which is based on a geometric property specific to 2D-sensitive ALLs. We show how the area in which each algorithm can accurately determine the position and orientation of a simulated dipole source is affected by (1) the amount of training and optimisation data, and (2) the sensitivity axes of the sensors. Overall, we find that each algorithm benefits from 2D-sensitive sensors, with alternating sensitivity axes as the second-best configuration. From the machine learning approaches, an MLP required an impractically large training set to approach the optimisation-based algorithms’ performance. Regardless of the data set size, QM performs best with both a large area for accurate predictions and a small tail of large errors.",
    	language = "en",
    	number = 13,
    	urldate = "2022-05-05",
    	journal = "Sensors",
    	author = "Bot, Daniël M. and Wolf, Ben J. and van Netten, Sietse M.",
    	month = "",
    	year = 2021,
    	note = "Number: 13 Publisher: Multidisciplinary Digital Publishing Institute",
    	keywords = "artificial lateral line, dipole localisation, hydrodynamic imaging, neural networks",
    	pages = 4558
    }
    
  3. Jan Brüdigam, Martin Schuck, Alexandre Capone, Stefan Sosnowski and Sandra Hirche. Structure-Preserving Learning Using Gaussian Processes and Variational Integrators. arXiv:2112.05451 [cs], 2022. URL BibTeX

    @article{brudigam_StructurePreserving_2022,
    	title = "Structure-{Preserving} {Learning} {Using} {Gaussian} {Processes} and {Variational} {Integrators}",
    	url = "http://arxiv.org/abs/2112.05451",
    	abstract = "Gaussian process regression is increasingly applied for learning unknown dynamical systems. In particular, the implicit quantification of the uncertainty of the learned model makes it a promising approach for safety-critical applications. When using Gaussian process regression to learn unknown systems, a commonly considered approach consists of learning the residual dynamics after applying some generic discretization technique, which might however disregard properties of the underlying physical system. Variational integrators are a less common yet promising approach to discretization, as they retain physical properties of the underlying system, such as energy conservation and satisfaction of explicit kinematic constraints. In this work, we present a novel structure-preserving learning-based modelling approach that combines a variational integrator for the nominal dynamics of a mechanical system and learning residual dynamics with Gaussian process regression. We extend our approach to systems with known kinematic constraints and provide formal bounds on the prediction uncertainty. The simulative evaluation of the proposed method shows desirable energy conservation properties in accordance with general theoretical results and demonstrates exact constraint satisfaction for constrained dynamical systems.",
    	urldate = "2022-05-05",
    	journal = "arXiv:2112.05451 [cs]",
    	author = "Brüdigam, Jan and Schuck, Martin and Capone, Alexandre and Sosnowski, Stefan and Hirche, Sandra",
    	month = "",
    	year = 2022,
    	note = "arXiv: 2112.05451",
    	keywords = "Computer Science - Machine Learning"
    }
    

Conference Publications

 

  1. Tudor Sântejudean and Lucian Busoniu. Path-aware optimistic optimization for a mobile robot. In 2021 60th IEEE Conference on Decision and Control (CDC). 2021. URL, DOI BibTeX

    @inproceedings{santejudean_Pathaware_14,
    	address = "Austin, TX, USA",
    	title = "Path-aware optimistic optimization for a mobile robot",
    	booktitle = "2021 60th IEEE Conference on Decision and Control (CDC)",
    	isbn = "978-1-66543-659-5",
    	url = "http://busoniu.net/files/papers/cdc21-tudor.pdf",
    	doi = "10.1109/CDC45484.2021.9683546",
    	abstract = "We consider problems in which a mobile robot samples an unknown function defined over its operating space, so as to find a global optimum of this function. The path travelled by the robot matters, since it influences energy and time requirements. We consider a branch-and-bound algorithm called deterministic optimistic optimization, and extend it to the path-aware setting, obtaining path-aware optimistic optimization (OOPA). In this new algorithm, the robot decides how to move next via an optimal control problem that maximizes the long-term impact of the robot trajectory on lowering the upper bound, weighted by bound and function values to focus the search on the optima. An online version of value iteration is used to solve an approximate version of this optimal control problem. OOPA is evaluated in extensive experiments in two dimensions, where it does better than path-unaware and local-optimization baselines.",
    	urldate = "2022-05-05",
    	publisher = "IEEE",
    	author = "Sântejudean, Tudor and Busoniu, Lucian",
    	month = "",
    	year = 2021
    }
    
  2. Bilal Yousuf, Zsofia Lendek and Lucian Busoniu. Exploration-Based Search for an Unknown Number of Targets using a UAV. In Proceedings 6th IFAC Conference on Intelligent Control and Automation Sciences (ICONS-22). 2022. URL BibTeX

    @inproceedings{icons22-bilal,
    	author = "Yousuf, Bilal and Lendek, Zsofia and Busoniu, Lucian",
    	title = "Exploration-Based Search for an Unknown Number of Targets using a UAV",
    	booktitle = "Proceedings 6th IFAC Conference on Intelligent Control and Automation Sciences ({ICONS-22})",
    	year = 2022,
    	note = "accepted",
    	month = "13--15 July",
    	address = "Cluj-Napoca, Romania",
    	url = "http://busoniu.net/files/papers/icons22-bilal.pdf"
    }
    
  3. Vicu-Mihalis Maer, Levente Tamas and Lucian Busoniu. Underwater robot pose estimation using acoustic methods and intermittent position measurements at the surface. In 2022 IEEE International Conference on Automation, Quality and Testing, Robotics (AQTR-22). 2014. URL BibTeX

    @inproceedings{aqtr22-mihalis,
    	author = "Vicu-Mihalis Maer and Levente Tamas and Lucian Busoniu",
    	title = "Underwater robot pose estimation using acoustic methods and intermittent position measurements at the surface",
    	booktitle = "2022 IEEE International Conference on Automation, Quality and Testing, Robotics ({AQTR-22})",
    	year = 2014,
    	month = "22--24 May",
    	address = "Cluj-Napoca, Romania",
    	url = "http://busoniu.net/files/papers/aqtr22-mihalis.pdf"
    }
    
  4. Tudor Santejudean, Lucian Busoniu, Vineeth Varma and Constantin Morarescu. A simple path-aware optimization method for mobile robots. In 6th IFAC Symposium on Telematics Applications (TA-22). 2022. URL BibTeX

    @inproceedings{ta22-tudor,
    	author = "Santejudean, Tudor and Busoniu, Lucian and Varma, Vineeth and Morarescu, Constantin",
    	title = "A simple path-aware optimization method for mobile robots",
    	booktitle = "6th IFAC Symposium on Telematics Applications ({TA-22})",
    	year = 2022,
    	note = "accepted",
    	month = "15--17 June",
    	address = "Nancy, France",
    	url = "http://busoniu.net/files/papers/ifacta22-tudor.pdf"
    }
    

This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 871295.

The SEACLEAR project spans four years, running from January 1st, 2020 to December 31st, 2023.

SEACLEAR NEWSLETTER

Stay up to date with news about the project. Expected frequency for the newsletter is twice a year.

SEACLEAR is not responsible for the content of third-party sites to which we link from this site.


Design & maintenance by Lichtbringer