Modulating Behaviors Using Allostatic Control

Vouloutsi, Vasiliki; Lallee, Stéphane; Verschure, Paul F. M. J.

doi:10.1007/978-3-642-39802-5_25

Cited by 20 publications

(21 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The allostatic controller maintains consistency between drives in an adaptive way by assigning priorities to the different drives and making the appropriate corrections to maintain coherence (e.g., by adapting the difficulty of the task to the learners behavior). The learning algorithms of the allostatic controller [33,34] allow the STA to adapt its drives and homeostatic boundaries to a specific student's behaviour and skills. Successful interactions (i.e., contextual cues and actions) are then stored as memory segments in the Object Properties Collector (OPC) module to build a model of the user.…”

Section: Modules and Mapping To The Dac Architecturementioning

confidence: 99%

Towards a Synthetic Tutor Assistant: The EASEL Project and its Architecture

Vouloutsi

Blancas

Zucca

et al. 2016

Biomimetic and Biohybrid Systems

Self Cite

View full text Add to dashboard Cite

Abstract. Robots are gradually but steadily being introduced in our daily lives. A paramount application is that of education, where robots can assume the role of a tutor, a peer or simply a tool to help learners in a specific knowledge domain. Such endeavor posits specific challenges: affective social behavior, proper modelling of the learner's progress, discrimination of the learner's utterances, expressions and mental states, which, in turn, require an integrated architecture combining perception, cognition and action. In this paper we present an attempt to improve the current state of robots in the educational domain by introducing the EASEL EU project. Specifically, we introduce the EASEL's unified robot architecture, an innovative Synthetic Tutor Assistant (STA) whose goal is to interactively guide learners in a science-based learning paradigm, allowing us to achieve such rich multimodal interactions.

show abstract

Section: Modules and Mapping To The Dac Architecturementioning

confidence: 99%

Towards a Synthetic Tutor Assistant: The EASEL Project and its Architecture

Vouloutsi

Blancas

Zucca

et al. 2016

Biomimetic and Biohybrid Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…This phenomenon is called homeostasis and can be observed at the levels of physiology, behavior or at the interface between the two (i.e., the animal engages a specific behavior that will lead to the regulation of a physiological state). It has been a relatively popular and successful approach in the design of autonomous artificial systems, especially robots [22,39,53] as it produces ethologically realist behaviors. A tightly linked concept is the notion of emotion: Although they are not consensually modeled, it is agreed that humans are subject to internal state which shape and affect globally the way they behave [54][55][56].…”

Section: Agentmentioning

confidence: 99%

“…The hook between the representations and the sensory data presented in earlier work [22,72], allows the agent to make use of a set of heterogeneous sensors to fill in the information regarding the spatial behavior and identity of the various physical elements in the world. However, one may want to teach the system about facts that are beyond the spatial reach of its sensors (e.g., "It is cold outside"); moreover, when it comes to more abstract or qualitative concepts the sensing approach quickly shows limits (e.g., "Freedom is good.").…”

Section: Mapping Between Natural Language and H5w Semanticmentioning

confidence: 99%

“…At the same time, the architecture provides useful insight into the robots internal state and motivations, which is due to the careful design the knowledge representation. Our implementation of the architecture has already been presented and validated in several previous studies [21][22][23]; In particular we have investigated the impact of how different robot behaviors are perceived by a human observer or partner.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

How? Why? What? Where? When? Who? Grounding Ontology in the Actions of a Situated Social Agent

Lallee

Verschure

2015

Robotics

View full text Add to dashboard Cite

Robotic agents are spreading, incarnated as embodied entities, exploring the tangible world and interacting with us, or as virtual agents crawling over the web, parsing and generating data. In both cases, they require: (i) processes to acquire information; (ii) structures to model and store information as usable knowledge; (iii) reasoning systems to interpret the information; and (iv) finally, ways to express their interpretations. The H5W (How, Why, What, Where, When, Who) framework is a conceptualization of the problems faced by any agent situated in a social environment, which has defined several robotic studies. We introduce the H5W framework, through a description of its underlying neuroscience and the psychological considerations it embodies, we then demonstrate a specific implementation of the framework. We will focus on the motivation and implication of the pragmatic decisions we have taken. We report the numerous studies that have relied upon this technical implementation as a proof of its robustness and polyvalence; moreover, we conduct an additional validation of its applicability to the natural language domain by designing an information exchange task as a benchmark.

show abstract

“…a caress is triggering positive emotions while pinching will arise negative ones) and utility (effects on the robot drives). While the internal model is regulated by the external world, it is also guiding the actions of the robot through the mechanism of allostatic control [3]. The most systematic way of sharing the robot inner state is through facial expressions and speech: they increase a lot its life likeliness and influence the attitude of humans towards him.…”

Section: Introductionmentioning

confidence: 99%

Efaa

Lallee¹,

Vouloutsi²,

Wierenga³

et al. 2014

Proceedings of the 2014 ACM/IEEE International Conference on Human-Robot Interaction

Self Cite

View full text Add to dashboard Cite

In this video, we present the human robot interaction generated by applying the DAC cognitive architecture [1] on the iCub robot. We demonstrate how the robot reacts and adapts to its environment within the context a continuous interactive scenario including different games. We emphasize as well that the artificial agent is maintaining a self-model in terms of emotions and drives and how those are expressed in order affect the social interaction.

show abstract

Modulating Behaviors Using Allostatic Control

Cited by 20 publications

References 23 publications

Towards a Synthetic Tutor Assistant: The EASEL Project and its Architecture

Towards a Synthetic Tutor Assistant: The EASEL Project and its Architecture

How? Why? What? Where? When? Who? Grounding Ontology in the Actions of a Situated Social Agent

Efaa

Contact Info

Product

Resources

About