Filter by type:

Sort by year:

Bushwalking

Amalia Foka
Exhibition IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) AI Art Gallery, Seattle, USA, Jun 19-21, 2024.

Abstract

More details on Bushwalking.

Bushwalking

Amalia Foka
ExhibitionXXIII Festival Internacional de la Imagen, GeoPoiesis, Cine (y) Digital Exhibition, Manizales and Bogota, Colombia. May 6th-May 12th 2024.

Abstract

More details on Bushwalking.

Anticipating 2020s

Amalia Foka
ExhibitionVisual Arts Festival, Galeria XX1, Mazowiecki Instytut Kultury, Warsaw, Poland. February 16th to March 29th, 2024. Curated by Milena Stryjewska, Małgorzata Miśkowiec and Karol Szafraniec.

Abstract

The "Relationships" Visual Arts Festival is a bit like a series, each new installment of which may resemble the next season of a story told over the years. The next edition begins where the previous one ends - the story is continued and deepened - each time from a slightly different side. "Relations" once again tries to reflect on our contemporary mediatized reality, of which digital technology is an important component. We look, through art, at its various elements and how they coexist. Life in the rush of information - at the intersection of the organic and electronic, digital and analog worlds, between human and algorithmic messages - is easily overstimulated, drowns in chaos, lost in the general atrophy of meanings. However, when you stop for a moment and look at individual phenomena that are seemingly randomly adjacent to each other from a non-obvious perspective, you can see hidden networks of connections between them. The right lens allows you to bring out meanings waiting to be discovered and illuminate unexpected symbiotic relationships. This year's exhibition deals primarily with the Internet understood as a space where individual self-expression, filtered through the social and political context, becomes an element of a collective voice that wants to make its impact known. We are interested in the moment when the individual somehow loses control over itself, dissolving into the multiplicity of an eternal collage remix, but also when the opposite happens - the need to leave an individual mark becomes apparent, even within mass, collective, theoretically anonymous activities. . Many contemporary discourses seem to contrast individualism and collectivity. But do these have to be values that are in eternal dispute with each other? At the same time, we are curious about the ways in which digital culture took over elements of artistic practices of the pre-internet era and how it becomes an inspiration for subsequent generations of artists who were already raised on it. It may turn out that a certain model of commenting on reality has its sources in the ancient beginnings of art, and what is digitally reproduced interestingly seeks its physical roots in the world. The phenomenon of the Internet meme unites various elements of this edition of "Relations" (exhibition, performative activities, meetings with guests, film screening), and is a starting point for combining digital with analog, technological with organic, public with private. It is also a source of reflection on the roots and heritage of today's Internet culture, its multicolor, internal inconsistencies, opportunities and threats, and the strength of its social impact.

More details on Anticipating 2020s.

Anticipating 2020s: Deep Learning Methods for Generating Videos from Found Footage Toward a Database Aesthetic

Amalia Foka
Conference Papers In VINCI '23: Proceedings of the 16th International Symposium on Visual Information Communication and Interaction, Guangzhou China September 22 - 24, 2023.

Abstract

This paper presents the methodology employed for generating the video Anticipating 2020s which attempts to portray our collective imagination about how life in the 2020s would be from the perspective of decades-earlier science fiction films and books. The video was generated by rearranging the found footage of small excerpts from various science fiction movies set in the 2020s based on the output of a deep learning algorithm for object detection. Furthermore, Anticipating 2020s is subtitled with text generated by the deep learning model GPT-2 finetuned on the text of science fiction books set in the 2020s. The presented methodology explores the use of machine learning algorithms to create a database of found footage and the potential of trajectories through the database to create new narratives.



More details

Anticipating 2020s

Amalia Foka
ExhibitionDrawing Now 2023 exhibition, November 22nd 2023 - December 10th 2023. Czong Institute for Contemporary Art (CICA) Museum, South Korea.

Abstract

Featured Artists 참여작가: Jennifer Cabral, Woosik Choi (최우식), Susan David, DJK, Amalia Foka, Leo Hainzl, Greg Hallahan, Stephan Halter, Darnia Hobson, Jeesoo Im (임지수), Kim Aromsaemi (김아롬새미), Kyungsoo Kim (김경수), Sion Kim (김시온), Ann-Kathrin Kuhn, Eunsom Kwon (권은솜), Hyunju Lee (이현주), Nicole Lenzi, Lily (박채은), Emma Louise, Madison Luetge, Miodrag Manojlovic, Andrew Martin, Nicolas Piret, Téa Popovic, P. Whitley, Kaylee Rose, Michael Ward-Rosenbaum, Shelby Shadwell, Fredy Solan, Petra Stefankova

An international exhibition with the theme of drawing, digital drawings, video drawings, interactive drawings, drawing performance videos, paper or mixed media drawings, prints, and three-dimensional drawings are exhibited.

With works by: Amalia Foka, Anticipating 2020s (Experimental video) - Anna Brody, this is the only th드로잉을 주제로 한 국제전으로 디지털 드로잉, 영상 드로잉, 인터랙티브 드로잉, 드로잉 퍼포먼스 영상, 종이 또는 믹스미디어 드로잉, 판화, 입체 드로잉 작품을 전시합니다.

More details on Anticipating 2020s.

Anticipating 2020s

Amalia Foka
ExhibitionCell in SHAPE and the GHOST in the Shell - 21 positions out of art and literature exhibition, November 4th 2023 - February 23rd 2024. G.A.S-station Berlin

Abstract

The cell is seen as a self-contained unit that communicates with the outside world; its complex structures, such as the human body or a state, are composed of it. Questions about demarcation and connectedness, specialisation and communication, as well as dependencies, spiral open like a peacock's wheel. The diversity and beauty of the forms of matter in nature and in artistic creation are wide.

On the other hand, the call is addressed to the body-mind discourse of philosophy, unresolved for years. The title of the project "Cell in Shape and the Ghost in the Shell" opens up body-centred aspects and in turn, it evokes themes around Artificial Intelligence and its social implications that are topical today. Views on body and mind/soul have an effect on each other, culturally in society as well as in dealing with matter and the environment.

With works by: Amalia Foka, Anticipating 2020s (Experimental video) - Anna Brody, this is the only thing we've got (Experimental video) - Anna Martynenko, Freedom of the body (Photographie Digital Print) - Anna Maria Kursawe, Cluster 2 (Painting) - Eleonore Weber, HERZ IST NIE AUSREICHEND EINE (Mixed media installation) - Edin Bajric, Wurzel, Keim, Innereien (Painting) - Isolde Gorsboth, Das Spiel weiß nicht, was du tun wirst (Painting) - Josephine Riemann, Von schwerer Hand (Object) - Kornelia Hoffmann, LUCA (3 pages out of the seria since 2018, ongoing, grafic) - Carmen Alber und Lorena Pircher, How’s things? (Mixed media) - Marco Goldenstein, Das ist die Wahrheit (ongoing seria since 2013, DIN A4 pages lamineted) - Wolfgang Neipl, Muschel Denkt Anders, 2023 (Multimedia objects) - Xiayi Su, Great Snow First Pentad, cold sets in, winter begins, White Dew First Pentad, Dew glistens white on grass (Photography) - Yoonjee Geem, Ever Lucis 2021 (Perlmutt and other materials on canvas) - Elisa Asenbaum, zwischenzeitig irdisch (Mixed media installation) - Bettina Weiß, TVC15 (Oil and acrylic on canvas) Elisabeth Mittag, In Effigie (Short prose) - Monika Vasik, Knochenblüten (Poem out of the book Knochenblüten, 2022, ELIF VERLAG) - Rainer Wieczorek, Kunstzelle (Drawings, 3 Pages out of the seria Kunstzellenbuch) - Ulrich Gorsboth, Digitale Fantasien in Erwartung des Unbekannten (Art history statement).

More details on Anticipating 2020s.

Anticipating 2020s

Amalia Foka
ExhibitionAI The Next Evolution - Virtual exhibition, June 2023. Chimaera Gallery, Philadelphia, USA. Online

Abstract

My work "Anticipating 2020s", a video generated toward a database aesthetic by algorithmically rearranging found footage from science fiction films and subtitled with text generated by the GPT-2 fine-tuned on the text of science fiction novels, is part of the exhibition "AI: The Next Evolution" which features 18 artists from all over the world who are creating new and exciting work using AI.

Artificial intelligence quickly transforms every aspect of society, notably in art and living systems. With the advent of generative data and machine learning algorithms, scientists can train computers to identify patterns and trends in vast amounts of data much faster than ever. AI has given artists new tools to work with and has changed how they think about their work. As AI continues to evolve, its impact on the world will likely only grow. More details on Anticipating 2020s.

Forging Emotions: a deep learning experiment on emotions and art

Amalia Foka
Journal PaperArtnodes, 2023, Num. 31, pp. 1-10. doi: https://doi.org/10.7238/artnodes.v0i31.402397.

Abstract

Affective computing is an interdisciplinary field that studies computational methods that relate to or influence emotion. These methods have been applied to interactive media artworks, but they have focused on affect detection rather than affect generation. For affect generation, computationally creative methods need to be explored that have recently been driven by the use of Generative Adversarial Networks (GANs), a deep learning method. The experiment presented in this paper, Forging Emotions, explores the use of visual emotion datasets and the working processes of GANs for visual affect generation, that is, for generating images that can convey or trigger specified emotions. This experiment concludes that the methodology used so far by computer science researchers to build image datasets for describing high-level concepts such as emotions is insufficient and proposes utilizing emotional networks of associations according to psychology research. Forging Emotions also concludes that to generate affect visually, merely corresponding to basic psychology findings, such as bright or dark colours, does not seem adequate. Therefore, research efforts should aim to understand the structure of trained GANs and compositional GANs in order to produce genuinely novel compositions that can convey or trigger emotions through the subject matter of generated images.

Forging Emotions: A Deep Learning Experiment on Emotions and Art

Amalia Foka
Conference Papers In Proceedings of the 27th International Symposium on Electronic Art (ISEA), Barcelona 10-16 June 2022.

Abstract

Affective computing is an interdisciplinary field that studies computational methods that relate to or influence emotion. These methods have been applied to interactive media art-works, but they have been focused on affect detection rather than affect generation. For affect generation, computationally creative methods need to be explored that lately have been driven with the use of Generative Adversarial Networks (GANs), a deep learning method. The experiment presented in this paper, Forging Emotions, explores the use of visual emotion datasets and the working processes of GANs for visual affect generation, i.e., to generate images that can con-vey or trigger specified emotions. This experiment concludes that the methodology used so far by computer science re-searchers to build image datasets for describing high-level concepts such as emotions is insufficient and proposes utiliz-ing emotional networks of associations according to psychol-ogy research. Forging Emotions also concludes that to gener-ate affect visually, merely corresponding to basic psychology findings, e.g., bright or dark colors, does not seem adequate. Therefore, research efforts should be targeted towards under-standing the structure of trained GANs and compositional GANs in order to produce genuinely novel compositions that can convey or trigger emotions through the subject matter of generated images.



More details

Constructing an Artworld Influencers Network by Mining Social Media

Amalia Foka
Journal PaperLeonardo (MIT Press) 2022; 55 (1): 24–29. doi: https://doi.org/10.1162/leon_a_02094

Abstract

The author shows a methodology for constructing an artworld network. The tweets posted by a manually comprised set of exemplar artworld actors and Natural Language Processing (NLP) methods are used to identify new artworld actors, including those that do not own a Twitter account. Identified artworld actors form communities detected with the Louvain method, and their authority is evaluated with the HITS centrality method. The resulting artworld network exhibits the ability, starting with a small set of exemplar actors, to identify new artworld actors and provides a wealth of data that would be very hard to collect otherwise.

The final artworld network can be explored in more detail at http://www.amaliafoka.com/artworld-network/

Breaking the Silence

Amalia Foka
Exhibition19th Media Art Biennale WRO 2021 REVERSO.DEPENDENT PLACES exhibition, Oct 1-28, 2021. WRO Art Center, Wroclaw, Poland.

Abstract

Breaking the Silence uses machine learning methods to understand what are the contemporary taboo topics. Initially, news articles that contained the word taboo were mined from various online sources. The mined articles were originally posted from January 2019 to September 2020. These articles include overt references to contemporary taboo topics in today’s press as well as the report of transgressions. Natural Language Processing (NLP) methods are then used to identify the main topic of each mined article and thus group them into sets according to similarity and relevance. Next, techniques for information extraction are used to determine the most meaningful elements of the articles’ text like entities, abstract concepts, etc. Finally, new documents are generated with the utilization of automatic text summarization techniques. These generated documents summarize the main ideas and opinions for each identified taboo topic. The images shown in all articles were generated with Runaway Generative Engine by randomly selecting sentences from each article. Breaking the Silence aims to highlight and bring to focus what topics are currently discussed as taboos. The generated summarizations underline the different topics discussed at different times and additionally the arguments for the creation, maintenance, or destruction of a taboo.

Visit the Breaking the Silence website.

Computer Vision Applications for Art History: reflections and paradigms for future research

Amalia Foka
Conference Papers In Proceedings of the International Electronic Visualisation & the Arts (EVA London) Conference, 5th–9th July 2021, London, U.K. / Online.

Abstract

One of the contributing factors to the continuing debate among art historians over the use of computational methods in art history research is that they do not consider the core of today's art history research questions. The lack of close collaboration between the two involved research communities makes the definition of contemporary art-historical methods as well-defined computer vision problems extremely difficult. For that purpose, it is devised as a methodology to study articles in art history journals from a computer science perspective. The objective is to identify which image features art historians utilise within their research and describe them in immediate and meaningful terms to the computer vision research community. Finally, some paradigms that could serve as a new starting point for exploring how computer vision applications for art history can address the core of today's art history research are given.

Breaking the Silence: Machine Learning Identified Taboos

Amalia Foka
Conference Papers In Proceedings of Interdisciplinary Conference Taboo – Transgression – Transcendence in Art & Science (TTT20), 26-28 November 2020, University of Applied Arts Vienna/Online.

Abstract

Breaking the Silence uses machine learning methods to understand what are the contemporary taboo topics. Initially, news articles that contained the word taboo were mined from various online sources. The mined articles were originally posted from January 2019 to September 2020. These articles include overt references to contemporary taboo topics in today’s press as well as the report of transgressions. Natural Language Processing (NLP) methods are then used to identify the main topic of each mined article and thus group them into sets according to similarity and relevance. Next, techniques for information extraction are used to determine the most meaningful elements of the articles’ text like entities, abstract concepts, etc. Finally, new documents are generated with the utilization of automatic text summarization techniques. These generated documents summarize the main ideas and opinions for each identified taboo topic. The images shown in all articles were generated with Runaway Generative Engine by randomly selecting sentences from each article. Breaking the Silence aims to highlight and bring to focus what topics are currently discussed as taboos. The generated summarizations underline the different topics discussed at different times and additionally the arguments for the creation, maintenance, or destruction of a taboo. Visit the Breaking the Silence website.

Forging Emotions

Amalia Foka
TalksTechnarte 2020 Art & Technology International Conference, 12-13 November 2020, Los Angeles/Online.

Abstract

The question "What is an emotion?" generates many different answers depending on the different emotional phenomena or theoretical issues studied from various disciplines. Affective computing is an interdisciplinary field that studies computational methods that relate or influence emotion. These methods have been applied to interactive media artworks, but until now, they have been focused on affect detection rather than affect generation. For affect generation, computationally creative methods need to be explored that lately have been driven with the use of Generative Adversarial Networks (GANs), a deep learning method. The experiment presented in this paper, Forging Emotions, explores the use of visual emotion datasets and the working processes of GANs for visual affect generation. This experiment concludes that the methodology used so far by researchers to build datasets for describing high-level concepts such as emotions is not sufficient. This conclusion is also in line with the comments artists made while working on affective computing methods. Finally, Forging Emotions also concludes that to generate affect visually, research effort should be targeted towards understanding the structure of trained GANs and compositional GANs in order to produce genuinely novel compositions that can convey emotions through the subject matter of generated images.

More details

Classification of EEG Signals Produced by Musical Notes as Stimuli

Konstantina Tsekoura and Amalia Foka
Journal Paper Expert Systems with Applications, Volume 159, 30 November 2020, 113507.

Abstract

In this paper, we present the classification of electroencephalograph (EEG) signals produced by the first-octave musical notes of the piano as stimuli. The EEG classification of musical notes is attempted for the first time, to the best of our knowledge. This type of classification could be applied towards the development of Brain-Computer Interfaces (BCIs) for the composition of music via thought as well as the definition of mappings between different stimuli for Sensory Substitution Devices (SSDs) that are based on their actual impact on brain signals and thus serve better the purpose of SSDs, which is to translate between senses at the perceptual level. Event-Related Spectral Perturbations (ERSP) are extracted as features and are fed into a Support Vector Machine (SVM) classifier. Our aim was to classify musical notes as C, C#, D, D#, E, F, F#, G, G#, A, A#, B and we have achieved it with an average accuracy of 70%.

Thoughts (or a discussion) on the history of art in a digital environment

Areti Adamopoulou and Amalia Foka
TalksSixth Conference of History of Art: Periods of Crisis and Paradigm Shifts, November 22-24, 2019, Benaki Museum, Athens, Greece.

Digital technology since the early 1990s has influenced advanced economies not only the way and the speed of disseminating information about historical, economic and factual information about past artworks, but also how modern art is produced. It has also sparked widespread and interdisciplinary discussions about how it can help research for the humanities in general, but also how it affects the selection of research subjects and the production of discourse itself within them.

For the sixth conference of the Association of Greek Art Historians we propose a "discussion" between a computer scientist (Amalia Foka) and an art historian (Areti Adamopoulou), who will argue in favor and against this modern convention in the field of art history and will express their thoughts on the uses of technology in this scientific field.

The Invisible Structures of the Artworld

Amalia Foka
ExhibitionACM ARTECH 2019 exhibition, Oct 23–25, 2019, Braga, Portugal.

Abstract

The Invisible Structures of the Artworld presented as video in juried exhibition at 9th International Conference on Digital and Interactive Arts from an international call for work.

The Invisible Structures of the Artworld draws inspiration from the contemporary artworld processes through which artists and artworks are appreciated and gain recognition as well as the fact that the artworld structure at any given time is not entirely known. Another point from which this work draws inspiration is the approaches taken for social network analysis, the process of investigating social structures through the use of networks. The Invisible Structures of the Artworld is a data-driven work. It collects real-time social media data to identify artworld actors and finally visualize an artworld network whose structure becomes visible. Thus, it visualizes the global transformations of the contemporary artworld as well as the role and impact of artworld actors involved in the processes of the production and mediation of art.

The Invisible Structures of the Artworld

Amalia Foka
Conference Papers In Proceedings of Artech 2019, 9th International Conference on Digital and Interactive Arts (ARTECH 2019), October 23–25, 2019, Braga, Portugal.

Abstract

The Invisible Structures of the Artworld draws inspiration from the contemporary artworld processes through which artists and artworks are appreciated and gain recognition as well as the fact that the artworld structure at any given time is not entirely known. Another point from which this work draws inspiration is the approaches taken for social network analysis, the process of investigating social structures through the use of networks. The Invisible Structures of the Artworld is a data-driven work. It collects real-time social media data to identify artworld actors and finally visualize an artworld network whose structure becomes visible. Thus, it visualizes the global transformations of the contemporary artworld as well as the role and impact of artworld actors involved in the processes of the production and mediation of art.

Social Media Mining for the Analysis of the Art World

Amalia Foka
Talks107th College Art Association of America (CAA) Annual Conference, Art and Artificial Intelligence Session, New York, USA, 13-16 February 2019.

The continuous increase of social media users and content has brought new opportunities to understand individuals, groups and society by mining social media. Numerous methodologies have emerged that have been proven a valuable tool for a wide range of industries and markets. However, the same does not hold for the art world. In this paper, it is proposed to perform a social media network structure analysis for the art world. This study will attempt to identify the field and its actors (artists, curators, historians, auction-house experts, etc.) as they exist online and evaluate their effect on a wide range of art-related processes. Existing approaches cannot be applied directly to the art world mainly because they are based on mining the public opinion about a brand or a product to estimate their market value or their intangible assets. Yet, artworks as products incorporate cultural values, that are a social construction that is related to reputations and occurs between art world experts and established art institutions. Hence, new social media mining methodologies need to be devised that reflect the elitist nature of the art world and can estimate the inherent cultural value of artworks and actors of the art world. This ability will give rise to new opportunities including: the identification of new and emerging actors; the identification of the most influential actors; the identification and evaluation of exhibition or auction events and in general the identification and evaluation of a wide range of art-related actors and processes.

An artist ranking system based on social media mining

Amalia Foka
Journal Paper Information Retrieval Journal, Vol. 21, Issue 5, pp 410-448, 2018.

Abstract

Currently users on social media post their opinion and feelings about almost everything. This online behavior has led to numerous applications where social media data are used to measure public opinion in a similar way as a poll or a survey. In this paper, we will present an application of social media mining for the art market. To the best of our knowledge, this will be the first attempt to mine social media to extract quantitative and qualitative data for the art market. Although there are previous works on analyzing and predicting other markets, these methodologies cannot be applied directly to the art market. In our proposed methodology, artists will be treated as brands. That is, we will mine Twitter posts that mention specific artists' names and attempt to rank artists in a similar manner as brand equity and awareness would be measured. The particularities of the art market are considered mainly in the construction of a topic-specific user network where user expertise and influence is evaluated and later used to rank artists. The proposed ranking system is evaluated against two other available systems to identify the advantages it can offer.

How would a School of Fine Arts curriculum be formed with the problem-solving logic of an engineer?

Amalia Foka
Conference PapersIn Proceedings of International Scientific Conference: For a School of Visual Arts in the 21st Century, Florina, Greece, 12-14 May 2017, ISBN: 978-618-83267-2-9.

The job description of an engineer, of any specialty - civil, electrical, mechanical, chemical or computer engineer, is common: to solve problems, face challenges and problems of the real world with creative and innovative solutions aiming to make the world work better and contribute to progress. In the context of this paper, we will consider the forming of a curriculum for a 21st century School of Fine Arts to be a “problem”. The logic and process of problem-solving will be followed in the same manner as it would be followed in a School of Engineering. This approach will allow us to identify and study the different perceptions and practices in art and engineering education. As we would do for solving any other problem, we will first examine the situation from which we start, the input, and the situation in which we want to conclude, the output. In our case, we will initially examine the reasons for which someone enters a school, their expectations from it and eventually the knowledge, skills, and abilities that they are expected to have as graduates of this school to accomplish a successful career path. The study of the defined problem of forming a curriculum will be tackled with a systems design approach that allows us to move from an initial to a final desired state. This will lead us to identify the key differences and/or similarities in the two kinds of Schools that are examined. More importantly, it will allow us to explore the different ways in which a system like that can be designed, while, at the same time, it will be juxtaposed with the existing curricula and teaching methods in Schools of Fine Arts.

Who takes command?

Amalia Foka
Book Chapter In: Thanasis Moutsopoulos (Ed.), Art | Non Art / RE-culture 4 | Pikramenos | 2016 | ISBN-13: 9789606628832

Ο καλλιτεχνικός θεσμός έχει αποδεχθεί ότι τα πάντα δύνανται να καταστούν έργα τέχνης εφόσον είναι μοναδικά αντικείμενα, φτιαγμένα από έναν καλλιτέχνη. Τι γίνεται όμως όταν ο δημιουργός τους δεν έχει αυτήν την πρόθεση ή ούτε καν συνείδηση ότι φτιάχνει ένα έργο; Όταν το έργο είναι ανώνυμο; Όταν η ελευθερία της έκφρασης δεν τον ενδιαφέρει καθόλου; Όταν το έργο δεν είναι αντικείμενο αισθητικής ανιδιοτέλειας αλλά σεξουαλικού αισθησιασμού; Όταν το λογισμικό και όχι ο άνθρωπος έχει τον πρώτο λόγο στη δημιουργία; Όταν το έργο τέχνης εκδίδεται ως καθημερινή εφημερίδα; Και τι συμβαίνει όταν τα έργα τέχνης στην εποχή τους και μέχρι σήμερα παραμένουν αφανή; Αποτελούν εξίσου τέχνη με αυτά των μουσείων και των βιβλίων ιστορίας της τέχνης ή μία τέχνη δεύτερης κατηγορίας; Αυτά τα ερωτήματα πραγματεύεται η παρούσα έκδοση με αφορμή τα έργα που εκτέθηκαν στο φεστιβάλ RE-culture 4 που πραγματοποιήθηκε το 2016 στην Πάτρα με τις ακόλουθες θεματικές: τέχνη των ψυχικά ασθενών, ανώνυμη τέχνη, τέχνη από τη Βόρεια Κορέα, το γκράφιτι, το σεξ στην τέχνη, ψυχεδελική τέχνη και το ελλαδικό καλλιτεχνικό αντεργκράουντ. Παράλληλα, φιλοξενούνται αφιερώματα στα νέα μέσα και στους καλλιτέχνες: Τζούλιο Καΐμη, Τάκη Γερμένη και Αντώνη Βάθη μαζί με έργα που επελέγησαν μέσω ανοικτής πρόσκλησης για τις θεματικές του φεστιβάλ.

Predictive Autonomous Robot Navigation: POMDPs for robot navigation with integrated human motion prediction

Amalia Foka
Book LAP LAMBERT Academic Publishing | September 14, 2016 | ISBN-10: 3659880078 | ISBN-13: 978-3659880070
image

A primary goal in robotics research is to provide means for mobile platforms to perform autonomously within their environment. Depending on the task at hand, autonomous performance can be defined as the execution by the robot, without human intervention, of certain navigational tasks. Commonly addressed navigation tasks include the localization, mapping, path planning and obstacle avoidance tasks. A probabilistic framework for the navigation tasks of localization, path planning and obstacle avoidance in dynamic environments is presented based on the Partially Observable Markov Decision Process (POMDP) model. POMDPs have the major shortcoming of their extreme computational complexity and hence they have been mainly used in robotics as high level path planners only. An hierarchical representation of POMDPs is introduced specifically designed for the autonomous robot navigation problem and termed as the Robot Navigation-Hierarchical POMDP (RNHPOMDP). Integration of human motion prediction into the navigation model is utilized with two kinds of prediction: short-term and long-term prediction. The book should be useful to students in Robotics utilizing POMDPs.

Probabilistic Autonomous Robot Navigation in Dynamic Environments with Human Motion Prediction

A. Foka and P. Trahanias
Journal Paper International Journal of Social Robotics,Vol. 2, No. 1, pp. 74-94, 2010

Abstract

This paper considers the problem of autonomous robot navigation in dynamic and congested environments. The predictive navigation paradigm is proposed where probabilistic planning is integrated with obstacle avoidance along with future motion prediction of humans and/or other obstacles. Predictive navigation is performed in a global manner with the use of a hierarchical Partially Observable Markov Decision Process (POMDP) that can be solved on-line at each time step and provides the actual actions the robot performs. Obstacle avoidance is performed within the predictive navigation model with a novel approach by deciding paths to the goal position that are not obstructed by other moving objects movement with the use of future motion prediction and by enabling the robot to increase or decrease its speed of movement or by performing detours. The robot is able to decide which obstacle avoidance behavior is optimal in each case within the unified navigation model employed.

Adaptive polynomial neural networks for time series forecasting

P. Liatsis, A. Foka, J.Y. Goulermas and L. Mandic
Conference Papers Int. Symp. ELMAR'07, September 12-14, Zadar, Croatia, pp.35-39, 2007

Abstract

Time series prediction involves the determination of an appropriate model, which can encapsulate the dynamics of the system, described by the sample data. Previous work has demonstrated the potential of neural networks in predicting the behaviour of complex, non-linear systems. In particular, the class of polynomial neural networks has been shown to possess universal approximation properties, while ensuring robustness to noise and missing data, good generalisation and rapid learning. In this work, a polynomial neural network is proposed, whose structure and weight values are determined with the use of evolutionary computing. The resulting networks allow an insight into the relationships underlying the input data, hence allowing a qualitative analysis of the models' performance. The approach is tested on a variety of non-linear time series data.

Real-Time Hierarchical POMDPs for Autonomous Robot Navigation

A. Foka and P. Trahanias
Journal Paper Robotics and Autonomous Systems (RAS) Journal , Vol. 55, Issue 7, pp. 561-571, 2007

Abstract

This paper proposes a new hierarchical formulation of POMDPs for autonomous robot navigation that can be solved in real-time, and is memory efficient. It will be referred to in this paper as the Robot Navigation–Hierarchical POMDP (RN-HPOMDP). The RN-HPOMDP is utilized as a unified framework for autonomous robot navigation in dynamic environments. As such, it is used for localization, planning and local obstacle avoidance. Hence, the RN-HPOMDP decides at each time step the actions the robot should execute, without the intervention of any other external module for obstacle avoidance or localization. Our approach employs state space and action space hierarchy, and can effectively model large environments at a fine resolution. Finally, the notion of the reference POMDP is introduced. The latter holds all the information regarding motion and sensor uncertainty, which makes the proposed hierarchical structure memory efficient and enables fast learning. The RN-HPOMDP has been experimentally validated in real dynamic environments.

Real-Time Hierarchical POMDPs for Autonomous Robot Navigation

A. Foka and P. Trahanias
Conference Papers IJCAI-05 Workshop: Reasoning with Uncertainty in Robotics (RUR-05), Edinburgh, Scotland, 30 July 2005

Abstract

This paper proposes a novel hierarchical representation of POMDPs that for the first time is amenable to real-time solution. It will be referred to in this paper as the Robot Navigation - Hierarchical POMDP (RN-HPOMDP). The RN-HPOMDP is utilized as a unified framework for autonomous robot navigation in dynamic environments. As such, it is used for localization, planning and local obstacle avoidance. Hence, the RN-HPOMDP decides at each time step the actions the robot should execute, without the intervention of any other external module. Our approach employs state space and action space hierarchy, and can effectively model large environments at a fine resolution. Finally, the notion of the reference POMDP, that holds all the information regarding motion and sensor uncertainty is introduced, which makes our hierarchical structure memory efficient and enables fast learning. The RN-HPOMDP has been tested extensively in a real-world environment.

Predictive Control of Robot Velocity to Avoid Obstacles in Dynamic Environments

A. Foka and P. Trahanias
Conference Papers Proceeding of 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, USA, Oct. 27 - 31, 2003

Abstract

This paper introduces a methodology for avoiding obstacles by controlling the robot's velocity. Contemporary approaches to obstacle avoidance usually dictate a detour from the originally planned trajectory to its goal position. In our previous work, we presented a method for predicting the motion of obstacles, and how to make use of this prediction when planning the robot trajectory to its goal position. This is extended in the current paper by also using this prediction to decide if the robot should change its speed to avoid an obstacle more effectively. The robot can choose to move at three different speeds: slow, normal and fast. A hierarchical partially observable Markov decision process (POMDP) controls the robot movement. The POMDP formulation is not altered to accommodate for the three different speeds, to avoid the increase of the size of the state space. Instead, a modified solution of POMDPs is used.

Predictive Autonomous Robot Navigation

A. Foka and P. Trahanias
Conference Papers IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), EPFL-Lausanne, Switzerland, Sep. 30 - Oct. 4, 2002

Abstract

This paper considers the problem of a robot navigating in a crowded or congested environment. A robot operating in such an environment can get easily blocked by moving humans and other objects. To deal with this problem it is proposed to attempt to predict the motion trajectory of humans and obstacles. Two kinds of prediction are considered: short-term and long-term. The short-term prediction refers to the one-step ahead prediction and the long-term to the prediction of the final destination point of the obstacle's movement. The robot movement is controlled by a partially observable Markov decision process (POMDP). POMDPs are utilized because of their ability to model information about the robot's location and sensory information in a probabilistic manner. The solution of a POMDP is computationally expensive and thus a hierarchical representation of POMDPs is used.

Predictive Autonomous Robot Navigation

A. Foka
Ph.D. Thesis Department of Computer Science, University of Crete, 2005.

Abstract

A primary goal in robotics research is to provide means for mobile platforms to perform autonomously within their environment. Depending on the task at hand, autonomous performance can be defined as the execution by the robot, without human intervention, of certain navigational tasks. In mobile robotics literature, commonly addressed navigation tasks include the localization, mapping, path planning and obstacle avoidance tasks. Solving any of these tasks is a hard problem by itself. The reason stems from the inherent complexity associated with both the robot and its environment, each of them being an extremely complex dynamical system with uncertainty involved.

In this thesis, we propose a probabilistic framework for mobile robot navigation in dynamic environments based on the Partially Observable Markov Decision Process (POMDP) model. The proposed model is able to perform the navigation tasks of localization, path planning and obstacle avoidance. POMDPs are models for sequential decision making where the world in which the robot operates is partially observable, i.e. the true underlying robot's state is not known, and the outcome of actions it executes is modelled probabilistically. As such POMDPs perform localization and path planning in a probabilistic manner.

POMDPs have the major shortcoming of their extreme computational complexity and hence they have been mainly used in robotics as high level path planners only. In this thesis, we propose a novel hierarchical representation of POMDPs, specifically designed for the autonomous robot navigation problem and termed as the Robot Navigation-Hierarchical POMDP (RN-HPOMDP). The proposed hierarchical POMDP can efficiently model large real-world environments and is amenable to real time solution. This is achieved mainly due to the design choice of modelling the state transition and observation functions dependent only on the robot motion model and not on the environment as it is commonly used in the POMDP literature. Furthermore, the notion of the reference POMDP (rPOMDP) is introduced that infers the robot motion model in a very small POMDP and it transfers this information to the hierarchical structure while being solved. The environment specific information is modelled within the reward function of the RN-HPOMDP. The employed model is utilized as a unified probabilistic navigation framework that accommodates for localization, path planning and obstacle avoidance. Hence, real-time solution of the RN-HPOMDP is essential since no other external modules are utilized and paths have to be replanned at each time step.

The RN-HPOMDP has been developed for the application of robot navigation in dynamic real-world environments that are highly populated. Thus, it is desirable for the robot to perform obstacle avoidance in a manner that resembles the human motion for obstacle avoidance. That is, the robot should be able to decide the most suitable obstacle avoidance behavior based on the state of the environment. Therefore, the robot can decide to either perform a detour or follow a completely new path to the goal and also modify its speed of movement (increase it or decrease it) to bypass an obstacle or let it move away respectively. Any of the above four distinct behaviors for obstacle avoidance should be decided well before the robot comes too close to the obstacle. For that reason, future motion prediction of obstacles is employed. Two kinds of prediction are utilized: short-term and long-term prediction. Short term prediction refers to the one-step ahead prediction whereas long-term prediction refers to the prediction of the final destination point of the obstacle's movement. Both kinds of prediction are integrated into the reward function of the RN-HPOMDP and the speed decision is performed through a modified solution of the RN-HPOMDP. As a result, the RN-HPOMDP can decide the optimal obstacle avoidance behavior based on the current and the predicted state of the environment without the intervention of any other external module.

Experimental results have shown the applicability and effectiveness of the proposed framework for the navigation task. The robustness and the probabilistic nature of the RN-HPOMDP as well as the future motion prediction are required to be able to perform efficiently and effectively in dynamic real-world environments that are highly populated.

Time Series Prediction Using Evolving Polynomial Neural Networks

A. Foka
M.Sc. Dissertation Department of Electrical Engineering and Electronics, UMIST, 1999.

Abstract

Real world problems are described by non-linear and chaotic processes which makes them hard to model and predict. The aim of this dissertation is to determine the structure and weights of a polynomial neural network, using evolutionary computing methods, and apply it to the non-linear time series prediction problem.

This dissertation first develops a general framework of evolutionary computing methods. Genetic Algorithms, Niched Genetic Algorithms and Evolutionary Algorithms are introduced and their applicability to neural networks optimization is examined.

Following, the problem of time series prediction is formulated. The time series prediction problem is formulated as a system identification problem, where the input to the system is the past values of a time series, and its desired output is the future values of a time series. Then, the Group Method of Data Handling (GMDH) algorithms are examined in detail. These algorithms use simple partial descriptions, usually polynomials, to gradually build complex models. The hybrid method of GMDH and GAs, Genetics-Based Self-Organizing Network (GBSON), is also examined.

The method implemented for the time series prediction problem is based on the GBSON method. It uses a niched generic algorithm to determine the partial descriptions of the final model, as well as the structure of the neural network used to model the time series to be predicted. Finally, the results obtained with this method are compared with the results obtained by the GMDH algorithm.