AHCI RESEARCH GROUP
Publications
Papers published in international journals,
proceedings of conferences, workshops and books.
OUR RESEARCH
Scientific Publications
How to
Here you can find the complete list of our publications.
You can use the tag cloud to select only the papers dealing with specific research topics.
You can expand the Abstract, Links and BibTex record for each paper.
You can use the tag cloud to select only the papers dealing with specific research topics.
You can expand the Abstract, Links and BibTex record for each paper.
2022
Augello, Agnese; Infantino, Ignazio; Pilato, Giovanni; Vitale, Gianpaolo
Extending Affective Capabilities for Medical Assistive Robots Journal Article
In: Cognitive Systems Research, vol. 73, pp. 21–25, 2022, ISSN: 13890417.
Abstract | Links | BibTeX | Tags: Anthropomorphic Robots, Assistive Robots, Emotion Detection, Facial Expressions, Human computer interaction, Human Robot Interaction, Humanoid Robots, Natural Language Processing, Robotics, Wellbeing
@article{augelloExtendingAffectiveCapabilities2022,
title = {Extending Affective Capabilities for Medical Assistive Robots},
author = { Agnese Augello and Ignazio Infantino and Giovanni Pilato and Gianpaolo Vitale},
doi = {10.1016/j.cogsys.2021.12.004},
issn = {13890417},
year = {2022},
date = {2022-01-01},
journal = {Cognitive Systems Research},
volume = {73},
pages = {21--25},
abstract = {In this work, we discuss methodologies and implementation choices to enable a humanoid robot to estimate patients' mood and emotions during postoperative home rehabilitation. The approach is modular and it has been implemented into a SoftBank Pepper robotic architecture; however, the approach is general and it can be easily adapted to other robotic platforms. A sample of an interactive session for the detection of the patient's affective state is also reported. textcopyright 2022 Elsevier B.V.},
keywords = {Anthropomorphic Robots, Assistive Robots, Emotion Detection, Facial Expressions, Human computer interaction, Human Robot Interaction, Humanoid Robots, Natural Language Processing, Robotics, Wellbeing},
pubstate = {published},
tppubtype = {article}
}
In this work, we discuss methodologies and implementation choices to enable a humanoid robot to estimate patients' mood and emotions during postoperative home rehabilitation. The approach is modular and it has been implemented into a SoftBank Pepper robotic architecture; however, the approach is general and it can be easily adapted to other robotic platforms. A sample of an interactive session for the detection of the patient's affective state is also reported. textcopyright 2022 Elsevier B.V.
2018
Augello, Agnese; Infantino, Ignazio; Lieto, Antonio; Maniscalco, Umberto; Pilato, Giovanni; Vella, Filippo
Towards a Dual Process Approach to Computational Explanation in Human-Robot Social Interaction Proceedings Article
In: A., Bhatt M. Bhatt M. Lieto (Ed.): CEUR Workshop Proceedings, pp. 21–26, CEUR-WS, 2018.
Abstract | BibTeX | Tags: Artificial intelligence, Dual Process Theory, Explainability, Human Robot Interaction
@inproceedings{augelloDualProcessApproach2018,
title = {Towards a Dual Process Approach to Computational Explanation in Human-Robot Social Interaction},
author = { Agnese Augello and Ignazio Infantino and Antonio Lieto and Umberto Maniscalco and Giovanni Pilato and Filippo Vella},
editor = { Bhatt M. Bhatt M. Lieto A.},
year = {2018},
date = {2018-01-01},
booktitle = {CEUR Workshop Proceedings},
volume = {2099},
pages = {21--26},
publisher = {CEUR-WS},
abstract = {The capacity for AI systems of explaining their decisions represents nowadays a huge challenge for both academia and industry (e.g. let us think at the autonomous cars sector). In this paper we sketch a preliminary proposal suggesting the adoption of a dual process approach for computational explanation. Our proposal is declined in the field of Human-Robot Social Interaction; namely, in a gesture recognition task. textcopyright 2018 CEUR-WS. All rights reserved.},
keywords = {Artificial intelligence, Dual Process Theory, Explainability, Human Robot Interaction},
pubstate = {published},
tppubtype = {inproceedings}
}
The capacity for AI systems of explaining their decisions represents nowadays a huge challenge for both academia and industry (e.g. let us think at the autonomous cars sector). In this paper we sketch a preliminary proposal suggesting the adoption of a dual process approach for computational explanation. Our proposal is declined in the field of Human-Robot Social Interaction; namely, in a gesture recognition task. textcopyright 2018 CEUR-WS. All rights reserved.
Augello, Agnese; Infantino, Ignazio; Maniscalco, Umberto; Pilato, Giovanni; Vella, Filippo
Robot Inner Perception Capability through a Soft Somatosensory System Journal Article
In: International Journal of Semantic Computing, vol. 12, no. 1, pp. 59–87, 2018, ISSN: 1793351X.
Abstract | Links | BibTeX | Tags: Anthropomorphic Robots, Cognitive Architectures, Cognitive Model, Human Robot Interaction, Motivation, Sensor systems, Somatosensory Systems
@article{augelloRobotInnerPerception2018,
title = {Robot Inner Perception Capability through a Soft Somatosensory System},
author = { Agnese Augello and Ignazio Infantino and Umberto Maniscalco and Giovanni Pilato and Filippo Vella},
doi = {10.1142/S1793351X18400044},
issn = {1793351X},
year = {2018},
date = {2018-01-01},
journal = {International Journal of Semantic Computing},
volume = {12},
number = {1},
pages = {59--87},
abstract = {The capability of a robot being aware of its internal status is a step forward to the enhancement of human-robot interaction. The possibility of feeling either pleasant or unpleasant sensations is at the basis of the motivation level of a robot. It can modulate the "willingness" of accomplishing a given task. Negative sensations can represent an alarm indicating dangerous situations, while the feeling of a reassuring environment or a well-being sensation can be a stimulus in pursuing the task, even in the presence of a painful perception. In this paper, we illustrate a bio-inspired somatosensory system embedded in a cognitive model for a humanoid robot. The system is based on a set of soft sensors that have been designed in order to make it possible for the interpretation of the robot physical sensations through a proper classification of the perceived somatosensory signals. This interpretation triggers and modulates the motivation level of the robot as well as its behavior. textcopyright 2018 World Scientific Publishing Company.},
keywords = {Anthropomorphic Robots, Cognitive Architectures, Cognitive Model, Human Robot Interaction, Motivation, Sensor systems, Somatosensory Systems},
pubstate = {published},
tppubtype = {article}
}
The capability of a robot being aware of its internal status is a step forward to the enhancement of human-robot interaction. The possibility of feeling either pleasant or unpleasant sensations is at the basis of the motivation level of a robot. It can modulate the "willingness" of accomplishing a given task. Negative sensations can represent an alarm indicating dangerous situations, while the feeling of a reassuring environment or a well-being sensation can be a stimulus in pursuing the task, even in the presence of a painful perception. In this paper, we illustrate a bio-inspired somatosensory system embedded in a cognitive model for a humanoid robot. The system is based on a set of soft sensors that have been designed in order to make it possible for the interpretation of the robot physical sensations through a proper classification of the perceived somatosensory signals. This interpretation triggers and modulates the motivation level of the robot as well as its behavior. textcopyright 2018 World Scientific Publishing Company.
Augello, Agnese; Dignum, Frank; Gentile, Manuel; Infantino, Ignazio; Maniscalco, Umberto; Pilato, Giovanni; Vella, Filippo
A Social Practice Oriented Signs Detection for Human-Humanoid Interaction Journal Article
In: Biologically Inspired Cognitive Architectures, vol. 25, pp. 8–16, 2018, ISSN: 2212683X.
Abstract | Links | BibTeX | Tags: Cognitive Architectures, Human Robot Interaction, Social Context, Social Practices, Social Robots
@article{augelloSocialPracticeOriented2018,
title = {A Social Practice Oriented Signs Detection for Human-Humanoid Interaction},
author = { Agnese Augello and Frank Dignum and Manuel Gentile and Ignazio Infantino and Umberto Maniscalco and Giovanni Pilato and Filippo Vella},
doi = {10.1016/j.bica.2018.07.013},
issn = {2212683X},
year = {2018},
date = {2018-01-01},
journal = {Biologically Inspired Cognitive Architectures},
volume = {25},
pages = {8--16},
abstract = {In this work we propose a cognitive architecture, based on the Social Practice (SP) theory, aimed at the modeling of socially adaptive robots, able to interact with people, recognizing and interpreting the specific social context where it is acting. The proposed social robot is able to recognize and interpret social signs during ongoing social practices. The cognitive architecture is inspired by the well-known Psi model, and it is equipped with a Social Practice Engine that manages the whole conduct of the robot. The use of such an architecture simplifies and makes more natural the interaction between human beings and a robot. In particular, the scenario of a robot fulfilling the tasks of welcoming people in an office environment is being considered. textcopyright 2018 Elsevier B.V.},
keywords = {Cognitive Architectures, Human Robot Interaction, Social Context, Social Practices, Social Robots},
pubstate = {published},
tppubtype = {article}
}
In this work we propose a cognitive architecture, based on the Social Practice (SP) theory, aimed at the modeling of socially adaptive robots, able to interact with people, recognizing and interpreting the specific social context where it is acting. The proposed social robot is able to recognize and interpret social signs during ongoing social practices. The cognitive architecture is inspired by the well-known Psi model, and it is equipped with a Social Practice Engine that manages the whole conduct of the robot. The use of such an architecture simplifies and makes more natural the interaction between human beings and a robot. In particular, the scenario of a robot fulfilling the tasks of welcoming people in an office environment is being considered. textcopyright 2018 Elsevier B.V.
Clodic, Aurélie; Vazquez-Salceda, Javier; Dignum, Frank; Mascarenhas, Samuel; Dignum, Virginia; Augello, Agnese; Gentile, Manuel; Alami, Rachid
On the Pertinence of Social Practices for Social Robotics Journal Article
In: Frontiers in Artificial Intelligence and Applications, vol. 311, pp. 63–74, 2018, ISSN: 09226389.
Abstract | Links | BibTeX | Tags: Human Robot Interaction, Robotics, Social Context, Social Practices
@article{clodicPertinenceSocialPractices2018,
title = {On the Pertinence of Social Practices for Social Robotics},
author = { Aurélie Clodic and Javier {Vazquez-Salceda} and Frank Dignum and Samuel Mascarenhas and Virginia Dignum and Agnese Augello and Manuel Gentile and Rachid Alami},
editor = { Loh J. Norskov M. Coeckelbergh M. Seibt J. Funk M.},
doi = {10.3233/978-1-61499-931-7-63},
issn = {09226389},
year = {2018},
date = {2018-01-01},
journal = {Frontiers in Artificial Intelligence and Applications},
volume = {311},
pages = {63--74},
abstract = {In the area of consumer robots that need to have rich social interactions with humans, one of the challenges is the complexity of computing the appropriate interactions in a cognitive, social and physical context. We propose a novel approach for social robots based on the concept of Social Practices. By using social practices robots are able to be aware of their own social identities (given by the role in the social practice) and the identities of others and also be able to identify the different social contexts and the appropriate social interactions that go along with those contexts and identities. textcopyright 2018 The authors and IOS Press. All rights reserved.},
keywords = {Human Robot Interaction, Robotics, Social Context, Social Practices},
pubstate = {published},
tppubtype = {article}
}
In the area of consumer robots that need to have rich social interactions with humans, one of the challenges is the complexity of computing the appropriate interactions in a cognitive, social and physical context. We propose a novel approach for social robots based on the concept of Social Practices. By using social practices robots are able to be aware of their own social identities (given by the role in the social practice) and the identities of others and also be able to identify the different social contexts and the appropriate social interactions that go along with those contexts and identities. textcopyright 2018 The authors and IOS Press. All rights reserved.
Dignum, Virginia; Dignum, Frank; Vazquez-Salceda, Javier; Clodic, A.; Gentile, Manuel; Mascarenhas, Samuel; Augello, Agnese
Design for Values for Social Robot Architectures Journal Article
In: Frontiers in Artificial Intelligence and Applications, vol. 311, pp. 43–52, 2018, ISSN: 09226389.
Abstract | Links | BibTeX | Tags: Behavioral Research, Ethics, Human Robot Interaction, Responsible AI, Robotics, Social Practices
@article{dignumDesignValuesSocial2018,
title = {Design for Values for Social Robot Architectures},
author = { Virginia Dignum and Frank Dignum and Javier {Vazquez-Salceda} and A. Clodic and Manuel Gentile and Samuel Mascarenhas and Agnese Augello},
editor = { Loh J. Norskov M. Coeckelbergh M. Seibt J. Funk M.},
doi = {10.3233/978-1-61499-931-7-43},
issn = {09226389},
year = {2018},
date = {2018-01-01},
journal = {Frontiers in Artificial Intelligence and Applications},
volume = {311},
pages = {43--52},
abstract = {The integration of social robots in human societies requires that they are capable to take decisions that may affect the lives of people around them. In order to ensure that these robots will behave according to shared ethical principles, an important shift in the design and development of social robots is needed, one where the main goal is improving ethical transparency rather than technical performance, and placing human values at the core of robot designs. In this abstract, we discuss the concept of ethical decision making and how to achieve trust according to the principles of Autonomy, Responsibility and Transparency (ART). textcopyright 2018 The authors and IOS Press. All rights reserved.},
keywords = {Behavioral Research, Ethics, Human Robot Interaction, Responsible AI, Robotics, Social Practices},
pubstate = {published},
tppubtype = {article}
}
The integration of social robots in human societies requires that they are capable to take decisions that may affect the lives of people around them. In order to ensure that these robots will behave according to shared ethical principles, an important shift in the design and development of social robots is needed, one where the main goal is improving ethical transparency rather than technical performance, and placing human values at the core of robot designs. In this abstract, we discuss the concept of ethical decision making and how to achieve trust according to the principles of Autonomy, Responsibility and Transparency (ART). textcopyright 2018 The authors and IOS Press. All rights reserved.
Infantino, Ignazio; Augello, Agnese; Maniscalto, Umberto; Pilato, Giovanni; Vella, Filippo
A Cognitive Architecture for Social Robots Proceedings Article
In: IEEE 4th International Forum on Research and Technologies for Society and Industry, RTSI 2018 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 2018, ISBN: 978-1-5386-6282-3.
Abstract | Links | BibTeX | Tags: Cognitive Architectures, Human Robot Interaction, Social Robots, Somatosensory Systems
@inproceedings{infantinoCognitiveArchitectureSocial2018,
title = {A Cognitive Architecture for Social Robots},
author = { Ignazio Infantino and Agnese Augello and Umberto Maniscalto and Giovanni Pilato and Filippo Vella},
doi = {10.1109/RTSI.2018.8548520},
isbn = {978-1-5386-6282-3},
year = {2018},
date = {2018-01-01},
booktitle = {IEEE 4th International Forum on Research and Technologies for Society and Industry, RTSI 2018 - Proceedings},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {The paper illustrates a software architecture allowing a robot to socially interact with human beings, sharing with them some basilar cognitive mechanisms. Robust sensing of the environment and people is strongly linked with an artificial somatosensory system that drives the robot behavior at a low level and influences its motivation. Both long-term memory and short-term memory store relevant data to detect and recognize the social context (and social practice), and the human social behavior. Using both internal and external evaluations, the robot learns and improves its social skills, which take into account its physiological and emotional demands (affiliation, competence, certainty). Social interaction is encoded in the cognitive architecture by considering at the same level the human understanding and the robot communicative actions. This is done by using the same interaction channels (both verbal and nonverbal). Some examples derived from previous works show the effectiveness and the potential of the cognitive architecture. textcopyright 2018 IEEE.},
keywords = {Cognitive Architectures, Human Robot Interaction, Social Robots, Somatosensory Systems},
pubstate = {published},
tppubtype = {inproceedings}
}
The paper illustrates a software architecture allowing a robot to socially interact with human beings, sharing with them some basilar cognitive mechanisms. Robust sensing of the environment and people is strongly linked with an artificial somatosensory system that drives the robot behavior at a low level and influences its motivation. Both long-term memory and short-term memory store relevant data to detect and recognize the social context (and social practice), and the human social behavior. Using both internal and external evaluations, the robot learns and improves its social skills, which take into account its physiological and emotional demands (affiliation, competence, certainty). Social interaction is encoded in the cognitive architecture by considering at the same level the human understanding and the robot communicative actions. This is done by using the same interaction channels (both verbal and nonverbal). Some examples derived from previous works show the effectiveness and the potential of the cognitive architecture. textcopyright 2018 IEEE.
Nuccio, Carlo; Augello, Agnese; Gaglio, Salvatore; Pilato, Giovanni
Interaction Capabilities of a Robotic Receptionist Journal Article
In: Smart Innovation, Systems and Technologies, vol. 76, pp. 171–180, 2018, ISSN: 21903018.
Abstract | Links | BibTeX | Tags: Anthropomorphic Robots, Computational Creativity, Human computer interaction, Human Robot Interaction, Humanoid Robots, Ontologies, Robotics
@article{nuccioInteractionCapabilitiesRobotic2018,
title = {Interaction Capabilities of a Robotic Receptionist},
author = { Carlo Nuccio and Agnese Augello and Salvatore Gaglio and Giovanni Pilato},
editor = { Giuseppe De Pietro and Luigi Gallo and Robert J. Howlett and Lakhmi C. Jain},
doi = {10.1007/978-3-319-59480-4_18},
issn = {21903018},
year = {2018},
date = {2018-01-01},
journal = {Smart Innovation, Systems and Technologies},
volume = {76},
pages = {171--180},
abstract = {A system aimed at facilitating the interaction between a human user and an humanoid robot is presented. The system is suited to answer questions about laboratories activities, people involved, projects, research themes and collaborations among employees. The task is accomplished by the HermiT reasoner invoked by a speech recognition module. The system is capable of navigating a specific ontology making inference on it. The presented system is part of a broader social robot framework whose goal is to give the user a fulfilling social interaction experience, driven by the perception of the robot internal state and involving intuitive and computational creativity capabilities. textcopyright Springer International Publishing AG 2018.},
keywords = {Anthropomorphic Robots, Computational Creativity, Human computer interaction, Human Robot Interaction, Humanoid Robots, Ontologies, Robotics},
pubstate = {published},
tppubtype = {article}
}
A system aimed at facilitating the interaction between a human user and an humanoid robot is presented. The system is suited to answer questions about laboratories activities, people involved, projects, research themes and collaborations among employees. The task is accomplished by the HermiT reasoner invoked by a speech recognition module. The system is capable of navigating a specific ontology making inference on it. The presented system is part of a broader social robot framework whose goal is to give the user a fulfilling social interaction experience, driven by the perception of the robot internal state and involving intuitive and computational creativity capabilities. textcopyright Springer International Publishing AG 2018.
2016
Augello, Agnese; Infantino, Ignazio; Manfré, Adriano; Pilato, Giovanni; Vella, Filippo
Analyzing and Discussing Primary Creative Traits of a Robotic Artist Journal Article
In: Biologically Inspired Cognitive Architectures, vol. 17, pp. 22–31, 2016, ISSN: 2212683X.
Abstract | Links | BibTeX | Tags: Anthropomorphic Robots, Artificial intelligence, Cognitive Architectures, Computational Creativity, Creative Agents, Creative Process, Human computer interaction, Human Robot Interaction, Humanoid Robots, Information Management, Social Robots
@article{augelloAnalyzingDiscussingPrimary2016,
title = {Analyzing and Discussing Primary Creative Traits of a Robotic Artist},
author = { Agnese Augello and Ignazio Infantino and Adriano Manfré and Giovanni Pilato and Filippo Vella},
doi = {10.1016/j.bica.2016.07.006},
issn = {2212683X},
year = {2016},
date = {2016-01-01},
journal = {Biologically Inspired Cognitive Architectures},
volume = {17},
pages = {22--31},
abstract = {We present a robot aimed at producing a collage formed by a mix of photomontage and digital collage. The artwork is created after a visual and verbal interaction with a human user. The proposed system, through a cognitive architecture, allows the robot to manage the three different phases of the real-time artwork process: (i) taking inspiration from information captured during the postural and verbal interaction with the human user and from the analysis of his/her social web items; (ii) performing a creative process to obtain a model of the artwork; (iii) executing the creative collage composition and providing a significant title. The paper explains, primarily, how the creativity traits of the robot are implemented in the proposed architecture: how ideas are generated through an elaboration that is modulated by affective influences; how the personality and the artistic behavior are modeled by learning and guided by external evaluations; the motivation and the confidence evolution as a function of successes or failures. textcopyright 2016 Elsevier B.V. All rights reserved.},
keywords = {Anthropomorphic Robots, Artificial intelligence, Cognitive Architectures, Computational Creativity, Creative Agents, Creative Process, Human computer interaction, Human Robot Interaction, Humanoid Robots, Information Management, Social Robots},
pubstate = {published},
tppubtype = {article}
}
We present a robot aimed at producing a collage formed by a mix of photomontage and digital collage. The artwork is created after a visual and verbal interaction with a human user. The proposed system, through a cognitive architecture, allows the robot to manage the three different phases of the real-time artwork process: (i) taking inspiration from information captured during the postural and verbal interaction with the human user and from the analysis of his/her social web items; (ii) performing a creative process to obtain a model of the artwork; (iii) executing the creative collage composition and providing a significant title. The paper explains, primarily, how the creativity traits of the robot are implemented in the proposed architecture: how ideas are generated through an elaboration that is modulated by affective influences; how the personality and the artistic behavior are modeled by learning and guided by external evaluations; the motivation and the confidence evolution as a function of successes or failures. textcopyright 2016 Elsevier B.V. All rights reserved.
Infantino, Ignazio; Augello, Agnese; Manfré, Adriano; Pilato, Giovanni; Vella, Filippo
Robodanza: Live Performances of a Creative Dancing Humanoid Proceedings Article
In: F., Cardoso F. A. Corruble V. Ghedini F. Pachet (Ed.): Proceedings of the 7th International Conference on Computational Creativity, ICCC 2016, pp. 388–395, Sony CSL, 2016, ISBN: 978-2-7466-9155-1.
Abstract | BibTeX | Tags: Anthropomorphic Robots, Artificial intelligence, Cognitive Architectures, Creative Agents, Human Robot Interaction, Social Robots
@inproceedings{infantinoRobodanzaLivePerformances2016,
title = {Robodanza: Live Performances of a Creative Dancing Humanoid},
author = { Ignazio Infantino and Agnese Augello and Adriano Manfré and Giovanni Pilato and Filippo Vella},
editor = { Cardoso F.A. Corruble V. Ghedini F. Pachet F.},
isbn = {978-2-7466-9155-1},
year = {2016},
date = {2016-01-01},
booktitle = {Proceedings of the 7th International Conference on Computational Creativity, ICCC 2016},
pages = {388--395},
publisher = {Sony CSL},
abstract = {The paper describes the artistic performances obtained with a creative system based on a cognitive architecture. The performances are executed by a humanoid robot whose creative behaviour is strongly influenced both by the interaction with human dancers and by internal and external evaluation mechanisms. The complexity of such a task requires the development of robust and fast algorithms in order to effectively perceive and process musical inputs, and the generation of coherent movements in order to realize an amusing and original choreography. A basic sketch of the choreography has been conceived and set-up in cooperation with professional dancers. The sketch takes into account both robot capabilities and limitations. Three live performances are discussed in detail, reporting their impact on the audience, the environmental conditions, and the adopted solutions to satisfy safety requirements, and achieve aesthetic pleasantness. textcopyright 2016 Proceedings of the 7th International Conference on Computational Creativity, ICCC 2016. All rights reserved.},
keywords = {Anthropomorphic Robots, Artificial intelligence, Cognitive Architectures, Creative Agents, Human Robot Interaction, Social Robots},
pubstate = {published},
tppubtype = {inproceedings}
}
The paper describes the artistic performances obtained with a creative system based on a cognitive architecture. The performances are executed by a humanoid robot whose creative behaviour is strongly influenced both by the interaction with human dancers and by internal and external evaluation mechanisms. The complexity of such a task requires the development of robust and fast algorithms in order to effectively perceive and process musical inputs, and the generation of coherent movements in order to realize an amusing and original choreography. A basic sketch of the choreography has been conceived and set-up in cooperation with professional dancers. The sketch takes into account both robot capabilities and limitations. Three live performances are discussed in detail, reporting their impact on the audience, the environmental conditions, and the adopted solutions to satisfy safety requirements, and achieve aesthetic pleasantness. textcopyright 2016 Proceedings of the 7th International Conference on Computational Creativity, ICCC 2016. All rights reserved.
Manfré, Adriano; Augello, Agnese; Pilato, Giovanni; Vella, Filippo; Infantino, Ignazio
Exploiting Interactive Genetic Algorithms for Creative Humanoid Dancing Journal Article
In: Biologically Inspired Cognitive Architectures, vol. 17, pp. 12–21, 2016, ISSN: 2212683X.
Abstract | Links | BibTeX | Tags: Artificial intelligence, Cognitive Architectures, Computational Creativity, Creative Agents, Human Robot Interaction
@article{manfreExploitingInteractiveGenetic2016,
title = {Exploiting Interactive Genetic Algorithms for Creative Humanoid Dancing},
author = { Adriano Manfré and Agnese Augello and Giovanni Pilato and Filippo Vella and Ignazio Infantino},
doi = {10.1016/j.bica.2016.07.004},
issn = {2212683X},
year = {2016},
date = {2016-01-01},
journal = {Biologically Inspired Cognitive Architectures},
volume = {17},
pages = {12--21},
abstract = {The paper discusses an approach aimed at endowing a cognitive architecture with artificial creativity capabilities in order to make a humanoid able to dance in a pleasant manner. The robot associates movements to music perception creating an aesthetically valuable dance by using a Hidden Markov Model with a nonclassical approach. Two matrices mainly influence the model: a Transition matrix TM, and an Emission Matrix EM. The TM matrix rules the transition between two subsequent movements. The EM matrix constitutes the link between a set of movements and the perceived music features. In order to compute the EM matrix, we exploit a genetic algorithm approach. The approach makes use of two kinds of fitness functions. The first one is an internal evaluation fitness that allows the robot to autonomously learn the association between music and movements. The second one depends on the interaction with a human teacher, leading to the determination of different dance styles, which constitute the robot repertoire. The experimental part discusses the effects on the creativity of different distances to compute fitness. textcopyright 2016 Elsevier B.V. All rights reserved.},
keywords = {Artificial intelligence, Cognitive Architectures, Computational Creativity, Creative Agents, Human Robot Interaction},
pubstate = {published},
tppubtype = {article}
}
The paper discusses an approach aimed at endowing a cognitive architecture with artificial creativity capabilities in order to make a humanoid able to dance in a pleasant manner. The robot associates movements to music perception creating an aesthetically valuable dance by using a Hidden Markov Model with a nonclassical approach. Two matrices mainly influence the model: a Transition matrix TM, and an Emission Matrix EM. The TM matrix rules the transition between two subsequent movements. The EM matrix constitutes the link between a set of movements and the perceived music features. In order to compute the EM matrix, we exploit a genetic algorithm approach. The approach makes use of two kinds of fitness functions. The first one is an internal evaluation fitness that allows the robot to autonomously learn the association between music and movements. The second one depends on the interaction with a human teacher, leading to the determination of different dance styles, which constitute the robot repertoire. The experimental part discusses the effects on the creativity of different distances to compute fitness. textcopyright 2016 Elsevier B.V. All rights reserved.