164 research outputs found
Un chatterbot che sa rispondere alle domande tecniche RELUIS sulla ricostruzione post- sisma
No full textNella gestione della ricostruzione post-sisma ha assunto un ruolo importante il sito web del Consorzio RELUIS per i tecnici coinvolti nella progettazione di riparazione e adeguamento degli edifici inagibili. La conoscenza è stata messa disposizione tramite il mezzo convenzionale delle FAQ, insieme di domande frequenti in forma testuale. In base a recenti sviluppi sulla generazione automatica di basi di conoscenza AIML, viene proposto un metodo di analisi linguistica del corpus del testo delle FAQ tecniche, al fine di generare un chatbot che possa rispondere adeguatamente a domande poste in testo libero dagli utenti
#NEWPALMYRA CRAFT-GRID
No full textOpenSimulator model, in OAR format, of the virtual reconstruction of the Temple of Bel in Palmyra, Siria. The model is accessible to registered users of the virtual world Craft Grid http://www.craft-world.or
DALI Multi Agent System Framework
No full textDALI is a Prolog based framework to develop Logic Multi Agent System capable of Complex Event Processin
Strumenti basati su Metaversi 3D per l'insegnamento dell'Informatica e dei Sistemi di Elaborazione delle Informazioni
No full textDynamic goal decomposition and planning in MAS for Highly Changing Environments
No full textThis paper studies the problem of dynamic goal decomposition and planning in scenarios characterized by a strong inter-dependency between action and context, for instance those related to rescue intervention in a territory upon occurrence of some kind of catastrophic event. We propose an architecture that integrates DALI MASs (DALI Multi-Agent Systems) and ASP (Answer Set Programming) modules for reaching goals in a flexible and timely way, where DALI is a computational-logic-based fully implemented agent-oriented logic programming language and ASP modules allow for affordable and flexible planning capabilities. The proposed DALI MAS architecture exploits these modules for flexible goal decomposition and planning with the possibility to select plans according to a suite of possible preferences and to re-plan upon need. We present a case-study concerning DALI agents which cooperate for exploring an unknown territory under changing circumstances in an optimal or at least sub-optimal fashion. The architecture can be exploited not only by DALI agents, but rather by any kind of logical agent
Cartel formation in charging network for electric vehicles
No full textElectric Vehicles (EVs) depend on the charging network for their range and uninterrupted traversal across the city. Such dependency may be exploited by the firms who establish the charging stations. In this paper, we analyse the cartel formation among the firms who establish the charging stations. By forming cartel, the firms can establish individual monopoly at various localities across the city, i.e., the charging stations in a locality is controlled by only one firm. Hence it can manipulate the price as the limited range of the EVs compel them to use the stations only in their respective localities. In this paper, we analyse complexity of deciding on such cartel and we also propose mechanism that can prevent such cartel formation. © 2016 IEEE
Complex Reactivity with Preferences in Rule-Based Agents
No full textIn this paper, we extend our previous work on complex reaction in rule-based logical agents. In particular, we introduce the possibility of defining and exploiting complex preferences for choosing the course of action to undertake in response to external events, also based upon a (simplified) form of modal reasoning and on sequences of past events
Meta-level Constraints for Complex Event Processing in Logical Agents
No full text“Brittleness” can be intended as the propensity of an agent to perform poorly or fail in the face of circumstances not explicitly considered by the agent’s designer. In opposition to brittleness, ”Versatility” and ”Perturbation-tolerance” ex- press the ability of being able to cope with previously unan- ticipated situations. These properties are particularly impor- tant in many practical applications which have the need to actively monitor vast quantities of event data to make auto- mated decisions and take time-critical actions, i.e., perform ”Complex Event-Processing”. In this paper, we propose temporal meta-level constraints to be dynamically checked, that allow an agent to timely self-check and adapt its behavior, and in particular its reactive modalities
Laboratorio virtuale per la formazione di operatori di base stranieri nel settore socio-sanitario.
No full text- …
