Bayesian Approach to Action Selection and Attention Focusing

Koike, Carla; Bessìère, Pierre; Mazer, Emmanuel

doi:10.1007/978-3-540-79007-5_8

Cited by 8 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Enfin des tâches motrices élémentaires peuvent être identifiées et modélisées sous forme de comportements de manière à isoler une partie du cout calculatoire du contrôle du reste de la chaine de raisonnement. EXEMPLE : Koike (2005) et Koike et al (2008) ont appliqué cette approche dans le domaine des systèmes sensorimoteurs mobiles autonomes. Koike a montré comment on peut s'accommoder de limites de temps et de mémoire sur des systèmes embarqués grâce à des hypothèses telles que la stationnarité des modèles temporels, l'indépendance partielle entre les processus sensoriels, la sélection du domaine d'intérêt et la sélection de comportement.…”

Section: Sélection De L'actionunclassified

See 1 more Smart Citation

Modèles probabilistes formels pour problèmes cognitifs usuels

Bessière,

Diard,

Colas

2016

intel

Self Cite

View full text Add to dashboard Cite

Comment un modèle incomplet et incertain de l'environnement peut-il être utilisé pour décider, agir, apprendre, raisonner et percevoir efficacement ? Voici le défi central que les systèmes cognitifs tant naturels qu'artificiels doivent résoudre. La logique, de par sa nature même, faite de certitudes et ne laissant aucune place au doute, est incapable de répondre à cette question. L'approche subjectiviste des probabilités est une extension de la logique conçue pour pallier ce manque. Dans cet article, nous passons en revue un ensemble de problèmes cognitifs usuels et nous montrons comment les formuler et les résoudre avec un formalisme probabiliste unique. Les concepts abordés sont : l'ambigüité, la fusion, la multi-modalité, les conflits, la modularité, les hiérarchies et les boucles. Chacune de ces questions est tout d'abord brièvement présentée à partir d'exemples venant des neurosciences, de la psychophysique ou de la robotique. Ensuite, le concept est formalisé en utilisant un modèle générique bayésien. Enfin, les hypothèses, les points communs et les différences de chacun de ces modèles sont analysés et discutés.Abstract: How can an incomplete and uncertain model of the environment be used to perceive, infer, decide and act efficiently? This is the challenge that both living and artificial cognitive systems have to face. Symbolic logic is, by its nature, unable to deal with this question. The subjectivist approach to probability is an extension to logic that is designed specifically to face this challenge. In this paper, we review a number of frequently encountered cognitive issues and cast them into a common Bayesian formalism. The concepts we review are ambiguities, fusion, multimodality, conflicts, modularity, hierarchies and loops. First, each of these concepts is introduced briefly using some examples from the neuroscience, psychophysics or robotics literature. Then, the concept is formalized using a template Bayesian model. The assumptions and common features of these models, as well as their major differences, are outlined and discussed.

show abstract

Section: Sélection De L'actionunclassified

“…MODELES : Incorporer de telles informations dans les modèles les rend moins génériques et plus sophistiqués. L'équation (45) montre la distribution conjointe du modèle complet de Koike (2005).…”

Section: Sélection De L'actionunclassified

Modèles probabilistes formels pour problèmes cognitifs usuels

Bessière,

Diard,

Colas

2016

intel

Self Cite

View full text Add to dashboard Cite

show abstract

“…Example: Koike (2005); Koike et al (2008) applied this approach in the domain of autonomous mobile sensorimotor systems. Koike showed how time and space limits on computations, and limited on-board processing power, could be accommodated, thanks to simplifying assumptions such as the stationarity of the temporal models, partial independence between sensory processes, domain-ofinterest selection at the processing stages (attention focusing) and behaviour selection.…”

Section: Action Selectionmentioning

confidence: 99%

Common Bayesian Models for Common Cognitive Issues

Colas

Diard²,

Bessìère³

2010

Acta Biotheor

Self Cite

View full text Add to dashboard Cite

How can an incomplete and uncertain model of the environment be used to perceive, infer, decide and act efficiently? This is the challenge that both living and artificial cognitive systems have to face. Symbolic logic is, by its nature, unable to deal with this question. The subjectivist approach to probability is an extension to logic that is designed specifically to face this challenge. In this paper, we review a number of frequently encountered cognitive issues and cast them into a common Bayesian formalism. The concepts we review are ambiguities, fusion, multimodality, conflicts, modularity, hierarchies and loops. First, each of these concepts is introduced briefly using some examples from the neuroscience, psychophysics or robotics literature. Then, the concept is formalized using a template Bayesian model. The assumptions and common features of these models, as well as their major differences, are outlined and discussed.

show abstract

“…Under the assumption of stationarity their template models are specified as 2-time-slice Bayesian networks (2-TBNs). The template model can be unrolled so that their interface variables (Koller and Friedman, 2009) Horrey et al (2006) and the Bayesian filter and action selection model of Koike (2008). The BAD-MoB-model we present here is tailored to a virtual highway scenario assuming a hierarchy of driving skills or expertise.…”

Section: Levels Of Expertise and Mixtures Of Behaviorsmentioning

confidence: 99%

Mixture-of-Behaviors and Levels-of-Expertise in a Bayesian Autonomous Driver Model

Möbus

Eilers²

2010

Advances in Human Factors and Ergonomics Series

View full text Add to dashboard Cite

Traffic scenario simulations and risk-based design require Digital Human Models (DHMs) of human control strategies. Furthermore, it is tempting to prototype assistance systems on the basis of a human driver model cloning an expert driver. We present the model architecture for embedding probabilistic models of human driver expertise with sharing of behaviors in different driving maneuvers. These models implement the sensory-motor system of human drivers in a mixtureof-behaviors (MoB) architecture with autonomous and goal-based attention allocation processes. A Bayesian MoB model is able to decompose complex skills (maneuvers) into basic skills (behaviors) and vice versa. The Bayesian-MoB-Model defines a probability distribution over driver-vehicle trajectories so that it has the ability to predict agent's behavior, to abduct hazardous situations, to generate anticipatory plans and control, and to plan counteractive measures by simulating counterfactual behaviors or actions preventing hazardous situations.Keywords: Bayesian models of human driver behavior and cognition, probabilistic

show abstract

Bayesian Approach to Action Selection and Attention Focusing

Cited by 8 publications

References 6 publications

Modèles probabilistes formels pour problèmes cognitifs usuels

Modèles probabilistes formels pour problèmes cognitifs usuels

Common Bayesian Models for Common Cognitive Issues

Mixture-of-Behaviors and Levels-of-Expertise in a Bayesian Autonomous Driver Model

Contact Info

Product

Resources

About