@inproceedings {2010, title = {Using the Interaction Rhythm as a Natural Reinforcement Signal for Social Robots: A Matter of Belief}, booktitle = {Proc. International Conference on Social Robotics, ICSR 2010}, series = {Lecture Notes in Computer Science}, volume = {6414}, year = {2010}, pages = {81{\textendash}89}, publisher = {Springer}, organization = {Springer}, address = {Singapore}, abstract = {In this paper, we present the results of a pilot study of a human robot interaction experiment where the rhythm of the interaction is used as a reinforcement signal to learn sensorimotor associations. The algorithm uses breaks and variations in the rhythm at which the human is producing actions. The concept is based on the hypothesis that a constant rhythm is an intrinsic property of a positive interaction whereas a break reflects a negative event. Subjects from various backgrounds interacted with a NAO robot where they had to teach the robot to mirror their actions by learning the correct sensorimotor associations. The results show that in order for the rhythm to be a useful reinforcement signal, the subjects have to be convinced that the robot is an agent with which they can act naturally, using their voice and facial expressions as cues to help it understand the correct behaviour to learn. When the subjects do behave naturally, the rhythm and its variations truly reflects how well the interaction is going and helps the robot learn efficiently. These results mean that non-expert users can interact naturally and fruitfully with an autonomous robot if the interaction is believed to be natural, without any technical knowledge of the cognitive capacities of the robot.}, isbn = {978-3-642-17247-2}, doi = {10.1007/978-3-642-17248-9_9}, author = {Antoine Hiolle and Lola Ca{\~n}amero and Peirre Andry and Arnaud J Blanchard and Philippe Gaussier}, editor = {Shuzhi Sam Ge and Haizhou Li and John-John Cabibihan and Yeow Kee Tan} } @inbook {2007, title = {Anticipating Rewards in Continuous Time and Space: A Case Study in Developmental Robotics}, booktitle = {Anticipatory Behavior in Adaptive Learning Systems: From Brains to Individual and Social Behavior}, series = {Lecture Notes in Artificial Intelligence}, volume = {4520}, year = {2007}, pages = {267{\textendash}284}, publisher = {Springer}, organization = {Springer}, address = {Berlin, Heidelberg}, abstract = {This paper presents the first basic principles, implementation and experimental results of what could be regarded as a new approach to reinforcement learning, where agents{\textemdash}physical robots interacting with objects and other agents in the real world{\textemdash}can learn to anticipate rewards using their sensory inputs. Our approach does not need discretization, notion of events, or classification, and instead of learning rewards for the different possible actions of an agent in all the situations, we propose to make agents learn only the main situations worth avoiding and reaching. However, the main focus of our work is not reinforcement learning as such, but modeling cognitive development on a small autonomous robot interacting with an {\textquotedblleft}adult{\textquotedblright} caretaker, typically a human, in the real world; the control architecture follows a Perception-Action approach incorporating a basic homeostatic principle. This interaction occurs in very close proximity, uses very coarse and limited sensory-motor capabilities, and affects the {\textquotedblleft}well-being{\textquotedblright} and affective state of the robot. The type of anticipatory behavior we are concerned with in this context relates to both sensory and reward anticipation. We have applied and tested our model on a real robot.}, isbn = {978-3-540-74261-6}, doi = {10.1007/978-3-540-74262-3_15}, url = {https://www.springer.com/gp/book/9783540742616}, author = {Arnaud J Blanchard and Lola Ca{\~n}amero}, editor = {Martin V Butz and Olivier Sigaud and Giovanni Pezzulo and Gianluca Baldassarre} } @article {2007, title = {D{\'e}veloppement de Liens Affectifs Bas{\'e}s sur le Ph{\'e}nom{\`e}ne d{\textquoteright}Empreinte pour Moduler l{\textquoteright}Exploration et l{\textquoteright}Imitation d{\textquoteright}un Robot}, journal = {Enfance}, volume = {59}, year = {2007}, pages = {35{\textendash}45}, abstract = {Les comportements des enfants varient en fonction du contexte, notamment en fonction des liens affectifs qu{\textquoteright}ils d{\'e}veloppent avec d{\textquoteright}autres personnes en pr{\'e}sence. Celainfluence par exemple leurs facult{\'e}s {\`a} explorer ou imiter. Pour mieux comprendre ces ph{\'e}nom{\`e}nes, nous proposons un mod{\`e}le bas{\'e} sur le ph{\'e}nom{\`e}ne de l{\textquoteright}empreinte de liens affectifs et de leurs effets. Apr{\`e}s avoir propos{\'e} des solutions pour simuler ces liens, nous montrerons comment nous pouvons les utiliser, o{\`u} ils peuvent {\^e}tre utilis{\'e}s afin de moduler les comportements d{\textquoteright}exploration et d{\textquoteright}imitation d{\textquoteright}un robot r{\'e}el. Finalement, nous discuterons du nouveau regard que peut apporter cette mod{\'e}lisation sur le comportement et le d{\'e}veloppement affectif des enfants. An infant{\textquoteright}s behavior varies (depending on the context) to a large degree as a function of the affective bonds that they have with the people that are also present. This influences their ability to explore or imitate, for example. In order to better understand these phenomena, we propose a model of affective bonds and their effects based on the imprinting phenomenon. After proposing solutions for simulating these bonds, we show how we can use them to modulate exploratory and imitative behaviors in a real robot. Finally, we discuss the new light that this model sheds on the affective behavior and development of children.}, issn = {0013-7345}, doi = {10.3917/enf.591.0035}, url = {https://www.cairn.info/revue-enfance-2007-1-page-35.htm}, author = {Arnaud J Blanchard and Lola Ca{\~n}amero} } @inproceedings {2007, title = {Learning to Interact with the Caretaker: A Developmental Approach}, booktitle = {Proc. Second International Conference on Affective Computing and Intelligent Interaction (ACII 2007)}, series = {Lecture Notes in Computer Science}, volume = {4738}, year = {2007}, month = {09/2007}, pages = {422{\textendash}433}, publisher = {Springer Berlin Heidelberg}, organization = {Springer Berlin Heidelberg}, address = {Lisbon, Portugal}, abstract = {To build autonomous robots able to live and interact with humans in a real-world dynamic and uncertain environment, the design of architectures permitting robots to develop attachment bonds to humans and use them to build their own model of the world is a promising avenue, not only to improve human-robot interaction and adaptation to the environment, but also as a way to develop further cognitive and emotional capabilities. In this paper we present a neural architecture to enable a robot to develop an attachment bond with a person or an object, and to discover the correct sensorimotor associations to maintain a desired affective state of well-being using a minimum amount of prior knowledge about the possible interactions with this object.}, isbn = {978-3-540-74888-5}, issn = {0302-9743}, doi = {10.1007/978-3-540-74889-2_37}, author = {Antoine Hiolle and Lola Ca{\~n}amero and Arnaud J Blanchard}, editor = {Ana C R Paiva and Rui Prada and Rosalind W Picard} } @article {2006, title = {Attachment Bonds for Human-Like Robots}, journal = {International Journal of Humanoid Robotics}, volume = {3}, year = {2006}, pages = {301{\textendash}320}, abstract = {If robots are to be truly integrated in humans{\textquoteright} everyday environment, they cannot be simply (pre-)designed and directly taken "off the shelf" and embedded into a real-life setting. Also, technical excellence and human-like appearance and "superficial" traits of their behavior are not enough to make social robots trusted, believable, and accepted. Fuller and deeper integration into human environments would require that, like children, robots develop embedded in the social environment in which they will fulfill their roles. An important element to bootstrap and guide this integration is the establishment of affective bonds between the "infant" robot and the adults among whom it develops, from whom it learns, and who it will later have to look after. In this paper, we present a Perception{\textendash}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. 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.}, issn = {0219-8436}, doi = {10.1142/S0219843606000771}, url = {http://www.worldscientific.com/doi/abs/10.1142/S0219843606000771}, author = {Lola Ca{\~n}amero and Arnaud J Blanchard and Jacqueline Nadel} } @inproceedings {2006, title = {Developing Affect-Modulated Behaviors: Stability, Exploration, Exploitation or Imitation?}, booktitle = {Proceedings of the Sixth International Workshop on Epigenetic Robotics}, series = {Lund University Cognitive Studies}, volume = {128}, year = {2006}, pages = {17{\textendash}24}, publisher = {Lund University}, organization = {Lund University}, address = {Paris, France}, abstract = {Exploring the environment is essential for autonomous agents to learn new things and to consolidate past experiences and apply them to improve behavior. However, exploration is also risky as it exposes the agent to unknown, potentially overwhelming or dangerous situations. A trade-off must hence exist between activities such as seeking stability, autonomous exploration of the environment, imitation of novel actions performed by another agents, and taking advantage of opportunities offered by new situations and events. In this paper, we present a Perception-Action robotic architecture that achieves this tradeoff on the grounds of modulatory mechanisms based on notions of {\textquotedblleft}well-being{\textquotedblright} and {\textquotedblleft}affect{\textquotedblright}. We have implemented and tested this architecture using a Koala robot, and we present and discuss behavior of the robot in different contexts.}, isbn = {91-974741-6-9}, issn = {1101-8453}, url = {https://www.lucs.lu.se/LUCS/128/BlanchardCanamero.pdf}, author = {Arnaud J Blanchard and Lola Ca{\~n}amero} } @inproceedings {2006, title = {Modulation of Exploratory Behavior for Adaptation to the Context}, booktitle = {Proc. AISB 2006 Symposium on Biologically Inspired Robotics (Biro-net)}, year = {2006}, pages = {131{\textendash}137}, publisher = {AISB Press}, organization = {AISB Press}, address = {Bristol, UK}, abstract = {For autonomous agents (children, animals or robots), exploratory learning is essential as it allows them to take advantage of their past experiences in order to improve their reactions in any situation similar to a situation already experimented. We have already exposed in Blanchard and Canamero (2005) how a robot can learn which situations it should memorize and try to reach, but we expose here architectures allowing the robot to take initiatives and explore new situations by itself. However, exploring is a risky behavior and we propose to moderate this behavior using novelty and context based on observations of animals behaviors. After having implemented and tested these architectures, we present a very interesting emergent behavior which is low-level imitation modulated by context.}, url = {https://uhra.herts.ac.uk/handle/2299/9888}, author = {Arnaud J Blanchard and Lola Ca{\~n}amero}, editor = {J Burn and M Wilson} } @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 {2005, title = {Using Visual Velocity Detection to Achieve Synchronization in Imitation}, booktitle = {Proc. 3rd Int. Symposium on Imitation in Animals and Artifacts}, year = {2005}, pages = {26{\textendash}29}, publisher = {AISB}, organization = {AISB}, address = {Hatfield, UK}, abstract = {Synchronization and coordination are important mechanisms involved in imitation and social interaction. In this paper, we study different methods to improve the reactivity of agents to changes in their environment in different coordination tasks. In a robot synchronization task, we compare the differences between using only position detection or velocity detection. We first test an existing position detection approach, and then we compare the results with those obtained using a novel method that takes advantage of visual detection of velocity. We test and discuss the applicability of these two methods in several coordination scenarios, to conclude by seeing how to combine the advantages of both methods.}, isbn = {1-902956-42-5}, url = {https://www.aisb.org.uk/publications/proceedings/aisb2005/3_Imitation_Final.pdf}, author = {Arnaud J Blanchard and Lola Ca{\~n}amero}, editor = {Demiris, Y} }