Prevention of Harmful Behaviors within Cognitive and Autonomous Agents

Caroline Chopinaud 1 Amal El Fallah Seghrouchni 1 Patrick Taillibert
1 SMA - Systèmes Multi-Agents
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : Being able to ensure that a multiagent system will not generate undesirable behaviors is essential within the context of critical applications (embedded systems or real-time systems). The emergence of behaviors from the agents interaction can generate situations incompatible with the expected system execution. The standard methods to validate a multiagent system do not prevent the occurrence of undesirable behaviors during its execution in real condition. We propose a complementary approach of dynamic self-monitoring and self-regulation allowing the agents to control their own behavior. This paper goes on to present the automatic generation of self-controlled agents. We use the observer approach to verify that the agents behavior respects a set of laws throughout the system execution.
Type de document :
Communication dans un congrès
European Conference on Artificial Intelligence, Aug 2006, Riva del Garda, Italy. IOS Press, European Conference on Artificial Intelligence, 141, pp.205-209, Frontiers in Artificial Intelligence and Applications
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01336919
Contributeur : Lip6 Publications <>
Soumis le : vendredi 24 juin 2016 - 11:05:13
Dernière modification le : jeudi 21 mars 2019 - 13:07:27

Identifiants

  • HAL Id : hal-01336919, version 1

Citation

Caroline Chopinaud, Amal El Fallah Seghrouchni, Patrick Taillibert. Prevention of Harmful Behaviors within Cognitive and Autonomous Agents. European Conference on Artificial Intelligence, Aug 2006, Riva del Garda, Italy. IOS Press, European Conference on Artificial Intelligence, 141, pp.205-209, Frontiers in Artificial Intelligence and Applications. 〈hal-01336919〉

Partager

Métriques

Consultations de la notice

96