@inproceedings {2024, title = {A Human-Robot Mutual Learning System with Affect-Grounded Language Acquisition and Differential Outcomes Training}, booktitle = {Social Robotics. 15th International Conference, ICSR 2023, Proceedings Part II}, volume = {LNAI 14454}, year = {2024}, pages = {108{\textendash}122}, publisher = {Springer}, organization = {Springer}, address = {Doha, Qatar, December 3{\textendash}7, 2023}, isbn = {978-981-99-8717-7}, issn = {0302-9743}, doi = {10.1007/978-981-99-8718-4}, url = {https://doi.org/10.1007/978-981-99-8718-4}, author = {Markelius, A. and Sj{\"o}berg, S. and Lemhaouri, Z. and Cohen, L. and Lowe, R. and Ca{\~n}amero, L.}, editor = {Abdulaziz Al Ali and Nader Meskin and Wanyue Jiang and Shuzhi Sam Ge and John-John Cabibihan and Silvia Rossi and Hongsheng He} } @inbook {2023, title = {When Emotional Machines are Intelligent Machines: The Tangled Knot of Affective Cognition}, booktitle = {Emotional Machines. Perspectives from Affective Computing and Emotional Human-Machine Interaction}, number = {Technikzuk{\"u}nfte, Wissenschaft und Gesellschaft / Futures of Technology, Science and Society}, year = {2023}, publisher = {Springer VS}, organization = {Springer VS}, address = {Wiesbaden}, abstract = {Research in neurobiology has provided evidence that emotions pervade human intelligence at many levels. However, {\textquotedblleft}emotion{\textquotedblright} and {\textquotedblleft}cognition{\textquotedblright} are still largely conceptualized as separate notions that {\textquotedblleft}interact{\textquotedblright}, and untangling and modeling those interactions remains a challenge, both in biological and artificial systems. My research focuses on modeling in autonomous robots how {\textquotedblleft}cognition{\textquotedblright}, {\textquotedblleft}motivation{\textquotedblright} and {\textquotedblleft}emotion{\textquotedblright} interact in what we could term embodied affective cognition, and particularly investigating how affect lies at the root of and drives how agents apprehend and interact with the world, making them {\textquotedblleft}intelligent{\textquotedblright} in the sense of being able to adapt to their environments in flexible and beneficial ways. In this chapter, I discuss this issue as I illustrate how my embodied model of affect has been used in my group to ground a broad range of affective, cognitive and social skills such as adaptive action selection, different types of learning, development, and social interaction.}, isbn = {978-3-658-37640-6}, issn = {2524-3764}, doi = {10.1007/978-3-658-37641-3_6}, url = {https://doi.org/10.1007/978-3-658-37641-3_6}, author = {Ca{\~n}amero, L.}, editor = {Misselhorn, C. and Poljan{\v s}ek, T. and St{\"o}rzinger, T. and M. Klein} } @inproceedings {9998, title = {Expression of Grounded Affect: How Much Emotion Can Arousal Convey?}, booktitle = {Proc. 21st Towards Autonomous Robotic Systems Conference (TAROS2020)}, series = {Lecture Notes in Computer Science}, volume = {12228}, year = {2020}, note = {Download (the complete proceedings are available from the link on this page)}, month = {09/2020}, pages = {234{\textendash}248}, publisher = {Springer}, organization = {Springer}, address = {Nottingham, UK}, abstract = {In this paper we consider how non-humanoid robots can communicate their affective state via bodily forms of communication (kinesics), and the extent to which this influences how humans respond to them. We propose a simple model of grounded affect and kinesic expression before presenting the qualitative findings of an exploratory study (N=9), during which participants were interviewed after watching expressive and non-expressive hexapod robots perform different {\textquoteleft}scenes{\textquoteright}. A summary of these interviews is presented and a number of emerging themes are identified and discussed. Whilst our findings suggest that the expressive robot did not evoke significantly greater empathy or altruistic intent in humans than the control robot, the expressive robot stimulated greater desire for interaction and was also more likely to be attributed with emotion.}, doi = {10.1007/978-3-030-63486-5_26}, url = {https://link.springer.com/chapter/10.1007/978-3-030-63486-5_26}, author = {Hickton, Luke and Lewis, Matthew and Lola Ca{\~n}amero}, editor = {Abdelkhilick Mohammad and Xin Dong and Matteo Russo} } @article {2016, title = {Towards Long-Term Social Child-Robot Interaction: Using Multi-Activity Switching to Engage Young Users}, journal = {Journal of Human-Robot Interaction}, volume = {5}, year = {2016}, note = {Download (Open Access)}, pages = {32{\textendash}67}, abstract = {Social robots have the potential to provide support in a number of practical domains, such as learning and behaviour change. This potential is particularly relevant for children, who have proven receptive to interactions with social robots. To reach learning and therapeutic goals, a number of issues need to be investigated, notably the design of an effective child-robot interaction (cHRI) to ensure the child remains engaged in the relationship and that educational goals are met. Typically, current cHRI research experiments focus on a single type of interaction activity (e.g. a game). However, these can suffer from a lack of adaptation to the child, or from an increasingly repetitive nature of the activity and interaction. In this paper, we motivate and propose a practicable solution to this issue: an adaptive robot able to switch between multiple activities within single interactions. We describe a system that embodies this idea, and present a case study in which diabetic children collaboratively learn with the robot about various aspects of managing their condition. We demonstrate the ability of our system to induce a varied interaction and show the potential of this approach both as an educational tool and as a research method for long-term cHRI.}, issn = {2163-0364}, doi = {10.5898/JHRI.5.1.Coninx}, url = {https://dl.acm.org/doi/abs/10.5898/JHRI.5.1.Coninx}, author = {Coninx, Alexandre and Paul E. Baxter and Oleari, Elettra and Bellini, Sara and Bierman, Bert and Henkemans, Olivier Blanson and Lola Ca{\~n}amero and Cosi, Piero and Valentin Enescu and Espinoza, Raquel Ros and Antoine Hiolle and Remi Humbert and Kiefer, Bernd and Kruijff-Korbayov{\'a}, Ivana and Looije, Rosmarijn and Mosconi, Marco and Mark A. Neerincx and Giulio Paci and Patsis, Georgios and Pozzi, Clara and Sacchitelli, Francesca and Hichem Sahli and Alberto Sanna and Sommavilla, Giacomo and Tesser, Fabio and Yiannis Demiris and Tony Belpaeme} } @inproceedings {3, title = {An Embodied AI Approach to Individual Differences: Supporting Self-Efficacy in Diabetic Children with an Autonomous Robot}, booktitle = {Proc. 7th International Conference on Social Robotics (ICSR-2015)}, series = {Lecture Notes in Computer Science}, year = {2015}, note = {Download (or Download authors{\textquoteright} draft)}, pages = {401{\textendash}410}, publisher = {Springer International Publishing}, organization = {Springer International Publishing}, address = {Paris}, abstract = {In this paper we discuss how a motivationally autonomous robot, designed using the principles of embodied AI, provides a suitable approach to address individual differences of children interacting with a robot, without having to explicitly modify the system. We do this in the context of two pilot studies using Robin, a robot to support self-confidence in diabetic children.}, isbn = {978-3-319-25553-8}, doi = {10.1007/978-3-319-25554-5_40}, url = {https://link.springer.com/chapter/10.1007\%2F978-3-319-25554-5_40}, author = {Lewis, Matthew and Oleari, Elettra and Pozzi, Clara and Lola Ca{\~n}amero}, editor = {Tapus, Adriana and Andr{\'e}, Elisabeth and Martin, Jean-Claude and Ferland, Fran{\c c}ois and Ammi, Mehdi} } @inproceedings {2015, title = {Let{\textquoteright}s Be Friends: Perception of a Social Robotic Companion for children with T1DM}, booktitle = {Proc. New Friends 2015}, year = {2015}, note = {Download full proceedings (PDF)}, month = {10/2015}, pages = {32{\textendash}33}, address = {Almere, The Netherlands}, abstract = {We describe the social characteristics of a robot developed to support children with Type 1 Diabetes Mellitus (T1DM) in the process of education and care. We evaluated the perception of the robot at a summer camp where diabetic children aged 10-14 experienced the robot in group interactions. Children in the intervention condition additionally interacted with it also individually, in one-to-one sessions featuring several game-like activities. These children perceived the robot significantly more as a friend than those in the control group. They also readily engaged with it in dialogues about their habits related to healthy lifestyle as well as personal experiences concerning diabetes. This indicates that the one-on-one interactions added a special quality to the relationship of the children with the robot.}, url = {https://mheerink.home.xs4all.nl/pdf/ProceedingsNF2015-3.pdf}, author = {Kruijff-Korbayov{\'a}, Ivana and Oleari, Elettra and Pozzi, Clara and Sacchitelli, Francesca and Bagherzadhalimi, Anahita and Bellini, Sara and Kiefer, Bernd and Racioppa, Stefania and Coninx, Alexandre and Paul E. Baxter and Bierman, Bert and Henkemans, Olivier Blanson and Mark A. Neerincx and Rosemarijn Looije and Yiannis Demiris and Espinoza, Raquel Ros and Mosconi, Marco and Cosi, Piero and Remi Humbert and Lola Ca{\~n}amero and Hichem Sahli and Joachim de Greeff and James Kennedy and Robin Read and Lewis, Matthew and Antoine Hiolle and Giulio Paci and Sommavilla, Giacomo and Tesser, Fabio and Athanasopoulos, Georgios and Patsis, Georgios and Verhelst, Werner and Alberto Sanna and Tony Belpaeme} } @inproceedings {2015, title = {A Reactive Competitive Emotion Selection System}, booktitle = {Proc. 7th International Conference on Social Robotics (ICSR-2015)}, series = {Lecture Notes in Computer Science}, year = {2015}, note = {Download}, pages = {31{\textendash}40}, publisher = {Springer International Publishing}, organization = {Springer International Publishing}, address = {Paris}, abstract = {We present a reactive emotion selection system designed to be used in a robot that needs to respond autonomously to relevant events. A variety of emotion selection models based on "cognitive appraisal" theories exist, but the complexity of the concepts used by most of these models limits their use in robotics. Robots have physical constrains that condition their understanding of the world and limit their capacity to built the complex concepts needed for such models. The system presented in this paper was conceived to respond to "disturbances" detected in the environment through a stream of images, and use this low-level information to update emotion intensities. They are increased when specific patterns, based on Tomkins{\textquoteright} affect theory, are detected or reduced when it is not. This system could also be used as part of (or as first step in the incremental design of) a more cognitively complex emotional system for autonomous robots.}, keywords = {Emotion production, Emotional models, Human Robot Interaction, Social robotics}, isbn = {978-3-319-25553-8}, doi = {10.1007/978-3-319-25554-5_4}, url = {https://link.springer.com/chapter/10.1007\%2F978-3-319-25554-5_4}, author = {Angel Fernandez, Julian M. and Bonarini, Andrea and Lola Ca{\~n}amero}, editor = {Tapus, Adriana and Andr{\'e}, Elisabeth and Martin, Jean-Claude and Ferland, Fran{\c c}ois and Ammi, Mehdi} } @inproceedings {2013, title = {SimianWorld {\textendash} A Study of Social Organisation Using an Artificial Life Model}, booktitle = {Advances in Artificial Life, ECAL 2013}, year = {2013}, note = {Download (Open Access)}, pages = {633{\textendash}640}, publisher = {MIT Press}, organization = {MIT Press}, address = {Taormina, Italy}, abstract = {In studies of social behaviour it is commonly assumed that individual complexity is the origin of intricate social interactions. In primates for example, social complexity is attributed to their intelligence and it is argued by many that the cognitive capacity of primates are especially manifest in the way they regulate their social relationships. Whereas the complex societies of non-human primates are considered to be as a direct result of their cognitive abilities this assumption is not made about social insects. In the absence of certain cognitive abilities their complex societies and structurally sophisticated nests are thought to arise from self-organisation. Since it is unlikely that cognitive capacities are all-or-nothing, usually integrating a range of mechanisms, it is possible that different species use similar cognitive mechanisms resulting in different behavioural outcomes.}, isbn = {9780262317092}, doi = {10.7551/978-0-262-31709-2-ch090}, url = {https://www.mitpressjournals.org/doi/abs/10.1162/978-0-262-31709-2-ch090}, author = {Sue Attwood and Lola Ca{\~n}amero and Ren{\'e} te Boekhorst}, editor = {Pietro Li{\`o} and Orazio Miglino and Giuseppe Nicosia and Stefano Nolfi and Mario Pavone} } @inproceedings {2010, title = {Emotion in Decisions of Life and Death {\textendash} Its Role in Brain-Body-Environment Interactions for Predator and Prey}, booktitle = {Artificial Life XII: Proc. of the 12th International Conference on the Synthesis and Simulation of Living Systems}, year = {2010}, note = {Download (Open Access)}, month = {08/2010}, pages = {812{\textendash}822}, publisher = {MIT Press}, organization = {MIT Press}, address = {Odense, Denmark}, abstract = {Taking inspiration from the biological world, in our work we are attempting to create and examine artificial predator-prey relationships using two LEGO robots. We do so to explore the possible adaptive value of emotion-like states for action selection in this context. However, we also aim to study and consider these concepts together at different levels of abstraction. For example, in terms of individual agents{\textquoteright} brain-body-environment interactions, as well as the (emergent) predator-prey relationships resulting from these. Here, we discuss some of the background concepts and motivations driving the design of our implementation and experiments. First, we explain why we think the predator-prey relationship is so interesting. Narrowing our focus to emotion-based architectures, this is followed by a review of existing literature, comparing different types and highlighting the novel aspects of our own. We conclude with our proposed contributions to the literature and thus, ultimately, the design and creation of artificial life.}, url = {https://mitpress-request.mit.edu/sites/default/files/titles/alife/0262290758chap141.pdf}, author = {O{\textquoteright}Bryne, Claire and Lola Ca{\~n}amero}, editor = {Harold Fellermann and Mark D{\"o}rr and Martin M Hanczy and Lone Ladegaard Laursen and Sarah Maurer and Daniel Merkle and Pierre-Alain Monnard and Kasper St{\o}y and Steen Rasmussen} } @inproceedings {2010, title = {Interpretation of Emotional Body Language Displayed by Robots}, booktitle = {Proc. 3rd International Workshop on Affective Interaction in Natural Environments, AFFINE{\textquoteright}10}, year = {2010}, pages = {37{\textendash}42}, publisher = {ACM}, organization = {ACM}, address = {Firenze, Italy}, abstract = {In order for robots to be socially accepted and generate empathy they must display emotions. For robots such as Nao, body language is the best medium available, as they do not have the ability to display facial expressions. Displaying emotional body language that can be interpreted whilst interacting with the robot should greatly improve its acceptance. This research investigates the creation of an "Affect Space" for the generation of emotional body language that could be displayed by robots. An Affect Space is generated by "blending" (i.e. interpolating between) different emotional expressions to create new ones. An Affect Space for body language based on the Circumplex Model of emotions has been created. The experiment reported in this paper investigated the perception of specific key poses from the Affect Space. The results suggest that this Affect Space for body expressions can be used to improve the expressiveness of humanoid robots. In addition, early results of a pilot study are described. It revealed that the context helps human subjects improve their recognition rate during a human-robot imitation game, and in turn this recognition leads to better outcome of the interactions.}, isbn = {978-1-4503-0170-1}, doi = {10.1145/1877826.1877837}, author = {Aryel Beck and Antoine Hiolle and Alexandre Mazel and Lola Ca{\~n}amero} } @inproceedings {2009, title = {Developing Preferential Attention to a Speaker: A Robot Learning to Recognise its Carer}, booktitle = {Proc. 2009 IEEE Symposium on Artificial Life (ALIFE 2009)}, year = {2009}, month = {03/2009}, pages = {77{\textendash}84}, publisher = {IEEE Press}, organization = {IEEE Press}, address = {Nashville, TN}, abstract = {In this paper we present a socially interactive multi-modal robotic head, ERWIN - Emotional Robot With Intelligent Networks, capable of emotion expression and interaction via speech and vision. The model presented shows how a robot can learn to attend to the voice of a specific speaker, providing a relevant emotional expressive response based on previous interactions. We show three aspects of the system; first, the learning phase, allowing the robot to learn faces and voices from interaction. Second, recognition of the learnt faces and voices, and third, the emotion expression aspect of the system. We show this from the perspective of an adult and child interacting and playing a small game, much like an infant and caregiver situation. We also discuss the importance of speaker recognition in terms of Human-Robot-Interaction and emotion, showing how the interaction process between a participant and ERWIN can allow the robot to prefer to attend to that person.}, isbn = {978-1-4244-2763-5}, issn = {2160-6374}, doi = {10.1109/ALIFE.2009.4937697}, url = {http://ieeexplore.ieee.org/document/4937697/}, author = {John C Murray and Lola Ca{\~n}amero} } @inbook {2009, title = {Emotion Modelling and Facial Affect Recognition in Human-Computer and Human-Robot Interaction}, booktitle = {Affective Computing, Emotion Modelling, Synthesis and Recognition}, year = {2009}, publisher = {InTechOpen Publishers}, organization = {InTechOpen Publishers}, chapter = {12}, isbn = {978-3-902613-42-4}, doi = {10.5772/6648}, url = {http://www.intechopen.com/books/state_of_the_art_in_face_recognition/emotion_modelling_and_facial_affect_recognition_in_human-computer_and_human-robot_interaction}, author = {Lori Malatesta and John C Murray and Amaryllis Raouzaiou and Antoine Hiolle and Lola Ca{\~n}amero and Kostas Karpouzis}, editor = {Mario I. Chacon-M.} } @inproceedings {2009, title = {The Importance of the Body in Affect-Modulated Action Selection: A Case Study Comparing Proximal Versus Distal Perception in a Prey-Predator Scenario}, booktitle = {Proc. 3rd Intl. Conference on Affective Computing and Intelligent Interaction (ACII 2009)}, year = {2009}, month = {09/2009}, pages = {1{\textendash}6}, publisher = {IEEE Press}, organization = {IEEE Press}, address = {Amsterdam, The Netherlands}, abstract = {In the context of the animat approach, we investigate the effect of an emotion-like hormonal mechanism, as a modulator of perception - and second order controller to an underlying motivation-based action selection architecture - on brain-body-environment interactions within a prey-predator scenario. We are particularly interested in the effects that affective modulation of different perceptual capabilities has on the dynamics of interactions between predator and prey, as part of a broader study of the adaptive value of emotional states such as "fear" and "aggression" in the context of action selection. In this paper we present experiments where we modulated the architecture of a prey robot using two different types of sensory capabilities, proximal and distal, effectively creating combinations of different prey "brains" and "bodies".}, issn = {2156-8103}, doi = {10.1109/ACII.2009.5349596}, author = {O{\textquoteright}Bryne, Claire and Lola Ca{\~n}amero and John C Murray} } @inproceedings {2009, title = {The Influence of Social Interaction on the Perception of Emotional Expression: A Case Study with a Robot Head}, booktitle = {Advances in Robotics: Proc. FIRA RoboWorld Congress 2009}, series = {Lecture Notes in Computer Science}, volume = {5744}, year = {2009}, month = {08/2009}, pages = {63{\textendash}72}, publisher = {Springer Berlin Heidelberg}, organization = {Springer Berlin Heidelberg}, address = {Incheon, Korea}, abstract = {In this paper we focus primarily on the influence that socio-emotional interaction has on the perception of emotional expression by a robot. We also investigate and discuss the importance of emotion expression in socially interactive situations involving human robot interaction (HRI), and show the importance of utilising emotion expression when dealing with interactive robots, that are to learn and develop in socially situated environments. We discuss early expressional development and the function of emotion in communication in humans and how this can improve HRI communications. Finally we provide experimental results showing how emotion-rich interaction via emotion expression can affect the HRI process by providing additional information.}, isbn = {978-3-642-03983-6}, doi = {10.1007/978-3-642-03983-6_10}, url = {https://link.springer.com/chapter/10.1007\%2F978-3-642-03983-6_10}, author = {John C Murray and Lola Ca{\~n}amero and Kim A. Bard and Ross, Marina Davila and Thorsteinsson, Kate}, editor = {Kim, Jong-Hwan and Ge, Shuzhi Sam and Vadakkepat, Prahlad and Jesse, Norbert and Al Manum, Abdullah and Puthusserypady K, Sadasivan and R{\"u}ckert, Ulrich and Sitte, Joaquin and Witkowski, Ulf and Nakatsu, Ryohei and Braunl, Thomas and Baltes, Jacky and Anderson, John and Wong, Ching-Chang and Verner, Igor and Ahlgren, David} } @inproceedings {2009, title = {Towards a Model of Emotion Expression in an Interactive Robot Head}, booktitle = {Proc. 18th IEEE International Symposium on Robot and Human Interactive Communication (IEEE RO-MAN 2009)}, year = {2009}, month = {09/2009}, pages = {627{\textendash}632}, publisher = {IEEE Press}, organization = {IEEE Press}, address = {Toyama, Japan}, abstract = {In this paper we present a robotic head designed for interaction with humans, endowed with mechanisms to make the robot respond to social interaction with emotional expressions, allowing the emotional expression of the robot to be directly influenced by the social interaction process. We look into how emotionally expressive visual feedback from the robot can enrich the interaction process and provide the participant with additional information regarding the interaction, allowing the user to better understand the intentions of the robot. We discuss some of the interactions that are possible with ERWIN and how this can effect the response of the system. We show experimental scenarios where the interaction processes influences the emotional expressions and how the participants interpret this. We draw our conclusions from the feedback from experiments, showing that indeed emotional expression can have an influence on the social interaction between a robot and human.}, isbn = {978-1-4244-5081-7}, issn = {1944-9445}, doi = {10.1109/ROMAN.2009.5326131}, author = {John C Murray and Lola Ca{\~n}amero and Antoine Hiolle} } @inproceedings {2008, title = {Adaptive Olfactory Encoding in Agents Controlled by Spiking Neural Networks}, booktitle = {From Animals to Animats 10: Proc. 10th International Conference on Simulation of Adaptive Behavior (SAB 2008)}, series = {Lecture Notes in Computer Science (LNCS)}, volume = { 5040}, year = {2008}, month = {07/2008}, pages = {148{\textendash}158}, publisher = {Springer, Berlin, Heidelberg}, organization = {Springer, Berlin, Heidelberg}, address = {Osaka, Japan}, abstract = {We created a neural architecture that can use two different types of information encoding strategies depending on the environment. The goal of this research was to create a simulated agent that could react to two different overlapping chemicals having varying concentrations. The neural network controls the agent by encoding its sensory information as temporal coincidences in a low concentration environment, and as firing rates at high concentration. With such an architecture, we could study synchronization of firing in a simple manner and see its effect on the agent{\textquoteright}s behaviour.}, isbn = {978-3-540-69134-1}, doi = {10.1007/978-3-540-69134-1_15}, url = {http://link.springer.com/chapter/10.1007/978-3-540-69134-1_15}, author = {Oros, Nicolas and Volker Steuber and Davey, Neil and Lola Ca{\~n}amero and Roderick G Adams}, editor = {Asada, Minoru and Hallam, John C T and Jean-Arcady Meyer and Tani, Jun} } @inproceedings {2008, title = {Receptor Response and Soma Leakiness in a Simulated Spiking Neural Controller for a Robot}, booktitle = {Proc. 4th International Workshop on Artificial Neural Networks and Intelligent Information Processing (ANNIIP 2008)}, year = {2008}, month = {05/2008}, pages = {100{\textendash}106}, publisher = {INSTICC (Inst. Syst. Technologies Information Control and Communication)}, organization = {INSTICC (Inst. Syst. Technologies Information Control and Communication)}, address = {Funchal, Madeira, Portugal}, abstract = {This paper investigates different models of leakiness for the soma of a simulated spiking neural controller for a robot exhibiting negative photo-taxis. It also investigates two models of receptor response to stimulus levels. The results show that exponential decay of ions across the soma and of a receptor response function where intensity is proportional to intensity is the best combination for dark seeking behaviour.}, isbn = {978-989-8111-33-3}, url = {https://uhra.herts.ac.uk/handle/2299/6832}, author = {David Bowes and Roderick G Adams and Lola Ca{\~n}amero and Volker Steuber and Davey, Neil}, editor = {Madani, K} } @inproceedings {2008, title = {Towards a Hormone-Modulated Model for Emotion Expression in a Socially Interactive Robot Head}, booktitle = {Workshop "The role of Emotion in Adaptive Behavior and Cognitive Robotics" held in conjunction with 10th International Conference on Simulation of Adaptive Behavior (SAB 2008)}, year = {2008}, month = {07/2008}, address = {Osaka, Japan}, abstract = {In this paper we present a robot head ERWIN capable of human-robot interaction, endowed with interactive mechanisms for allowing the emotional state and expression of the robot to be directly influenced by the social interaction process. Allowing the interaction process to influence the expression of the robot head can in turn influence the way the user interacts with the robot, in addition to allowing the user to better understand the intentions of the robot during this process. We discuss some of the interactions that are possible with ERWIN and how this can affect the response of the system. We show an example scenario where the interaction process makes the robot go through several different emotions.}, url = {http://image.ece.ntua.gr/projects/feelix/system/files/Murray_SAB_final-1.pdf}, author = {John C Murray and Lola Ca{\~n}amero}, editor = {Robert Lowe and Morse, A and Ziemke, T} } @inproceedings {2007, title = {Biasing Neural Networks Towards Exploration or Exploitation Using Neuromodulation}, booktitle = {Proc. 17th International Conference on Artificial Neural Networks (ICANN 2007), Part II}, series = {LNCS}, volume = {4669}, year = {2007}, month = {09/2007}, pages = {889{\textendash}898}, publisher = {Springer Berlin Heidelberg}, organization = {Springer Berlin Heidelberg}, address = {Porto, Portugal}, abstract = {Taking neuromodulation as a mechanism underlying emotions, this paper investigates how such a mechanism can bias an artificial neural network towards exploration of new courses of action, as seems to be the case in positive emotions, or exploitation of known possibilities, as in negative emotions such as predatory fear. We use neural networks of spiking leaky integrate-and-fire neurons acting as minimal disturbance systems, and test them with continuous actions. The networks have to balance the activations of all their output neurons concurrently. We have found that having the middle layer modulate the output layer helps balance the activations of the output neurons. A second discovery is that when the network is modulated in this way, it performs better at tasks requiring the exploitation of actions that are found to be rewarding. This is complementary to previous findings where having the input layer modulate the middle layer biases the network towards exploration of alternative actions. We conclude that a network can be biased towards either exploration of exploitation depending on which layers are being modulated.}, isbn = {978-3-540-74695-9}, doi = {10.1007/978-3-540-74695-9_91}, url = {https://link.springer.com/chapter/10.1007/978-3-540-74695-9_91}, author = {Parussel, Karla and Lola Ca{\~n}amero}, editor = {de S{\'a}, Joaquim Marques and Alexandre, Lu{\'\i}s A. and Duch, W{\l}odzis{\l}aw and Mandic, Danilo} } @inbook {2005, title = {Emotion Understanding: Robots as Tools and Models}, booktitle = {Emotional Development: Recent Research Advances}, year = {2005}, pages = {235{\textendash}258}, publisher = {Oxford University Press}, organization = {Oxford University Press}, chapter = {9}, isbn = {0-19-85-2883-3 (Hbk) 0-19-85-2884-1 (Pbk)}, doi = {10.1093/acprof:oso/9780198528845.003.0009}, author = {Lola Ca{\~n}amero and Philippe Gaussier}, editor = {Jacqueline Nadel and Darwin Muir} } @inproceedings {2005, title = {From Imprinting to Adaptation: Building a History of Affective Interaction}, booktitle = {Fifth International Workshop on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems (EpiRob2005)}, year = {2005}, pages = {23{\textendash}30}, publisher = {Lund University Cognitive Studies}, organization = {Lund University Cognitive Studies}, abstract = {We present a Perception-Action architecture and experiments to simulate imprinting{\textemdash}the establishment of strong attachment links with a "caregiver"{\textemdash}in a robot. Following recent theories, we do not consider imprinting as rigidly timed and irreversible, but as a more flexible phenomenon that allows for further adaptation as a result of reward-based learning through experience. Our architecture reconciles these two types of perceptual learning traditionally considered as different and even incompatible. After the initial imprinting, adaptation is achieved in the context of a history of "affective" interactions between the robot and a human, driven by "distress" and "comfort" responses in the robot.}, isbn = {91-974741-4-2}, author = {Arnaud J Blanchard and Lola Ca{\~n}amero}, editor = {Luc Berthouze and Fr{\'e}d{\'e}ric Kaplan and Hideki Kozima and Hiroyuki Yano and J{\"u}rgen Konczak and Giorgio Metta and Jacqueline Nadel and Giulio Sandini and Georgi Stojanov and Christian Balkenius} } @inproceedings {2004, title = {Using Hormonal Feedback to Modulate Action Selection in a Competitive Scenario}, booktitle = {From Animals to Animats 8: Proc. 8th Intl. Conf. on Simulation of Adaptive Behavior (SAB{\textquoteright}04)}, year = {2004}, pages = {243{\textendash}252}, publisher = {MIT Press}, organization = {MIT Press}, address = {Los Angeles, USA}, abstract = {In this paper we investigate the use of hormonal feedback as a mechanism to modulate a "motivation-based," homeostatic action selection mechanism (ASM) in a robot. We have framed our study in the context of a dynamic, multirobot, competitive "two-resource" action selection problem. The introduction of competitors has important consequences for action selection. We first show how the interaction between robots introduces new forms of environmental complexity that affect their viability. Secondly, we propose a "hormone-like" mechanism that, modulating the input of the ASM, tackles these new sources of complexity.}, isbn = {9780262693417}, doi = {10.7551/mitpress/3122.003.0031}, url = {https://www.researchgate.net/profile/Orlando_Avila-Garcia/publication/228958663_Using_Hormonal_Feedback_to_Modulate_Action_Selection_in_a_Competitive_Scenario/links/0deec533c8411ebe0c000000.pdf}, author = {Avila-Garc{\'\i}a, Orlando and Lola Ca{\~n}amero}, editor = {Stefan Schaal and Auke Jan Ijspeert and Aude Billard and Sethu Vijayakumar and John Hallam and Jean-Arcady Meyer} } @inproceedings {2003, title = {Learning Object Functionalities in the Context of Action Selection}, booktitle = {Towards Intelligent Mobile Robots, TIMR{\textquoteright}03: 4th British Conference on Mobile Robotics}, year = {2003}, address = {University of the West of England, Bristol}, author = {Cos-Aguilera, Ignasi and Lola Ca{\~n}amero and Gillian M Hayes}, editor = {U Nehmzow and C Melhuish} } @inproceedings {2003, title = {Optimization Criteria Underlying "Winner-Take-All" and "Voting-Based" Action Selection Policies}, booktitle = {Towards Intelligent Mobile Robots, TIMR{\textquoteright}03: 4th British Conference on Mobile Robotics}, year = {2003}, address = {University of the West of England, Bristol}, author = {Avila-Garc{\'\i}a, Orlando and Lola Ca{\~n}amero and Ren{\'e} te Boekhorst and Davey, Neil}, editor = {U Nehmzow and C Melhuish} } @inproceedings {2002, title = {Relating Behavior Selection Architectures to Environmental Complexity}, booktitle = {From Animals to Animats: Proc. 7th International Conference on Simulation of Adaptive Behavior}, year = {2002}, pages = {127{\textendash}128}, publisher = {MIT Press}, organization = {MIT Press}, address = {Edinburgh, Scotland}, isbn = {9780-262-58217-9}, author = {Avila-Garc{\'\i}a, Orlando and Hafner, Elena and Lola Ca{\~n}amero}, editor = {Bridget Hallam and Dario Floreano and John Hallam and Gillian M Hayes and Jean-Arcady Meyer} } @inproceedings {2000, title = {Designing Clustering Methods for Ontology Building: The Mo{\textquoteright}K Workbench}, booktitle = {Proc. First Workshop on Ontology Learning. Workshop of the 14th European Conference on Artificial Intelligence (ECAI 2000)}, year = {2000}, pages = {13{\textendash}18}, abstract = {This paper describes Mo{\textquoteright}K, a configurable workbench that supports the development of conceptual clustering methods for ontology building. Mo{\textquoteright}K is intended to assist ontology developers in the exploratory process of defining the most suitable learning methods for a given task. To do so, it provides facilities for evaluation, comparison, characterization and elaboration of conceptual clustering methods. Also, the model underlying Mo{\textquoteright}K permits a fine- grained definition of similarity measures and class construction operators, easing the tasks of method instantiation and configuration. This paper presents some experimental results that illustrate the suitability of the model to help characterize and assess the performance of different methods that learn semantic classes from parsed corpora.}, author = {Bisson, Gilles and N{\'e}dellec, Claire and Ca{\~n}amero, Lola D}, editor = {Staab, S and Maedche, A and N{\'e}dellec, Claire and Wiemer-Hastins, P} } @inbook {1999, title = {Emotions pour les agents situ{\'e}s}, booktitle = {Intelligence Artificielle Situ{\'e}e}, year = {1999}, publisher = {Herm{\`e}s science publications}, organization = {Herm{\`e}s science publications}, address = {Paris}, abstract = {Contrairement {\`a} l{\textquoteright}intelligence artificielle (IA) symbolique, l{\textquoteright}IA situ{\'e}e, qui adopte une vision plus large de l{\textquoteright}intelligence "compl{\`e}te" qui ne la d{\'e}tache pas de sa r{\'e}alisation corporelle et qui s{\textquoteright}int{\'e}resse {\`a} son r{\^o}le adaptatif, ouvre naturellement la porte {\`a} l{\textquoteright}{\'e}tude des r{\^o}les des {\'e}motions d{\textquoteright}un point de vue {\'e}volutif et {\`a} leur int{\'e}gration dans les agents autonomes ou animats comme des m{\'e}canismes favorisant l{\textquoteright}adaptation. Cet article examine les raisons pour lesquelles il semble int{\'e}ressant de doter d{\textquoteright}{\'e}motions les agents situ{\'e}s, en {\'e}tablissant un lien avec les {\'e}motions naturelles, ainsi que les diff{\'e}rentes approches envisageables permettant de mod{\'e}liser les {\'e}motions dans le cadre de l{\textquoteright}IA situ{\'e}e, et les diff{\'e}rents probl{\`e}mes qui en d{\'e}coulent. The notion of intelligence underlying symbolic Artificial Intelligence (AI) is tightly coupled to the idea of rationality. On the contrary, situated AI, with a wider view of intelligence that focuses on its embodiment and its adaptive value, allows to study emotional phenomena in animats from the point of view of evolution, and to investigate their adaptive roles. This paper examines the main reasons why it seems interesting to endow animats with emotions, establishing a parallel with natural emotions. It also considers the main approches that can be used to model emotions within situated AI, and the problems they pose. }, isbn = {978-274620076-0}, author = {D Ca{\~n}amero}, editor = {Alexis Drogoul and Jean-Arcady Meyer} }