Ao Dai : Agent OrienteD Ambient Intelligence - PowerPoint PPT Presentation

� � � � Ao Dai : � Agent OrienteD Ambient Intelligence � ——————————————————————— � � Diego Salomone, Thi Thuy Nga Nguyen, Andrei Olaru � under the supervision of prof. Amal El Fallah Seghrouchni � Lip6, University Pierre et Marie Curie, Paris 22.06.2010 1/ 30 . . Diego Salomone, Thi Thuy Nga Nguyen, Andrei Olaru . 5th NII-LIP6 Workshop . Paris, 22.06.2010

� AmI � Context-awareness � Agents � CLAIM � Agentification Ao Dai : � Interaction Agent OrienteD Ambient � Anticipation Intelligence ——————————————- � Ontologies � Conclusion overview � Demo 2/ 30 . . Diego Salomone, Thi Thuy Nga Nguyen, Andrei Olaru . 5th NII-LIP6 Workshop . Paris, 22.06.2010

� Ao Dai : � Agent OrienteD Ambient � Intelligence Ambient intelligence is a ubiquitous electronic � Ambient Intelligence environment that supports people in their daily tasks, in a proactive, but invisible and non-intrusive manner. � Context-awareness [Ramos et al., 2008, Weiser, 1993] � Agents � CLAIM � Agentification � Interaction � Anticipation � Ontologies � Conclusion � Demo 3/ 30 . . Diego Salomone, Thi Thuy Nga Nguyen, Andrei Olaru . 5th NII-LIP6 Workshop . Paris, 22.06.2010

� Ao Dai : � Agent OrienteD Ambient � Intelligence � Ambient Intelligence Example scenarios: � Context-awareness � Agents � CLAIM � Agentification � Interaction � Anticipation � Ontologies � Conclusion The large screen can be used to display context-aware � Demo advertisements... 4/ 30 . . Diego Salomone, Thi Thuy Nga Nguyen, Andrei Olaru . 5th NII-LIP6 Workshop . Paris, 22.06.2010

� Ao Dai : � Agent OrienteD Ambient � Intelligence � Ambient Intelligence Example scenarios: � Context-awareness � Agents � CLAIM � Agentification � Interaction � Anticipation � Ontologies � Conclusion ...or to draw attention of the user... � Demo 4/ 30 . . Diego Salomone, Thi Thuy Nga Nguyen, Andrei Olaru . 5th NII-LIP6 Workshop . Paris, 22.06.2010

� Ao Dai : � Agent OrienteD Ambient � Intelligence � Ambient Intelligence Example scenarios: � Context-awareness � Agents � CLAIM � Agentification � Interaction � Anticipation � Ontologies � Conclusion ...to show an interactive map for which the mobile phone is � Demo too small [Canut et al., 2009] ... 4/ 30 . . Diego Salomone, Thi Thuy Nga Nguyen, Andrei Olaru . 5th NII-LIP6 Workshop . Paris, 22.06.2010

� Ao Dai : � Agent OrienteD Ambient A layered perspective on AmI � Intelligence � Ambient Intelligence � Context-awareness � Agents � CLAIM � Agentification � Interaction � Anticipation � Ontologies � Conclusion � Demo [Seghrouchni, 2008] The applicative (or ”intelligent” ) layer can use AI methods and techniques like software agents and ontologies. [Ramos et al., 2008] . 5/ 30 . . Diego Salomone, Thi Thuy Nga Nguyen, Andrei Olaru . 5th NII-LIP6 Workshop . Paris, 22.06.2010

� Ao Dai : � Agent OrienteD Ambient Context is any information that can be used to characterize � Intelligence the situation of an entity. An entity is a person, place, � AmI or object that is considered relevant to the interaction � Context-awareness between a user and an application, including the user and � Agents applications themselves. [Dey and Abowd, 2000] � CLAIM Aspects: � Agentification [Chen and Kotz, 2000] ◮ physical aspect (location, conditions) � Interaction ◮ temporal aspect � Anticipation ◮ user profile and preferences � Ontologies ◮ social aspect � Conclusion ◮ computing resources � Demo ◮ activity ◮ associations (e.g. time – place – activity) [Henricksen et al., 2002] 6/ 30 . . Diego Salomone, Thi Thuy Nga Nguyen, Andrei Olaru . 5th NII-LIP6 Workshop . Paris, 22.06.2010

� Ao Dai : � Agent OrienteD Ambient � Intelligence Relevance of new information is related to its compatibility � AmI with the user’s context. � Context-awareness � Agents · can be considered as a measure of proximity in space, time, � CLAIM activity, social relations, preferences and available resources. � Agentification � Interaction In the Ao Dai project, we have so far considered: � Anticipation � Ontologies ◮ the spatial location of the user � Conclusion ◮ the user’s preferences � Demo ◮ the available computing resources 7/ 30 . . Diego Salomone, Thi Thuy Nga Nguyen, Andrei Olaru . 5th NII-LIP6 Workshop . Paris, 22.06.2010

� Ao Dai : � Agent OrienteD Ambient Software agents are an appropriate implementation for AmI, � Intelligence considering they satisfy the needs of AmI in terms of: � AmI � Context-awareness · reactivity � Software agents · proactivity � CLAIM · autonomy � Agentification · anticipation � Interaction · reasoning � Anticipation � Ontologies � Conclusion � Demo 8/ 30 . . Diego Salomone, Thi Thuy Nga Nguyen, Andrei Olaru . 5th NII-LIP6 Workshop . Paris, 22.06.2010

� Ao Dai : � Agent OrienteD Ambient Software agents are an appropriate implementation for AmI, � Intelligence considering they satisfy the needs of AmI in terms of: � AmI � Context-awareness · reactivity � Software agents · proactivity � CLAIM · autonomy � Agentification · anticipation � Interaction · reasoning � Anticipation � Ontologies Agents also offer beliefs, goals, intentions and easier � Conclusion implementation of a human-inspired behaviour. � Demo 8/ 30 . . Diego Salomone, Thi Thuy Nga Nguyen, Andrei Olaru . 5th NII-LIP6 Workshop . Paris, 22.06.2010

� Ao Dai : � Agent OrienteD Ambient Software agents are an appropriate implementation for AmI, � Intelligence considering they satisfy the needs of AmI in terms of: � AmI � Context-awareness · reactivity � Software agents · proactivity � CLAIM · autonomy � Agentification · anticipation � Interaction · reasoning � Anticipation � Ontologies Agents also offer beliefs, goals, intentions and easier � Conclusion implementation of a human-inspired behaviour. � Demo For Ao Dai, we use CLAIM + Sympa as agent-oriented programming language and platform. 8/ 30 . . Diego Salomone, Thi Thuy Nga Nguyen, Andrei Olaru . 5th NII-LIP6 Workshop . Paris, 22.06.2010

� Ao Dai : � Agent OrienteD Ambient � Intelligence · Agent-Oriented programming language � AmI � Context-awareness ◮ Created by Alexandru Suna, during his Thesis � Agents in Paris 6 [Suna and El Fallah Seghrouchni, 2007] � CLAIM agents for AmI Eases the programming task involving a · � Agentification Multi-Agent System � Interaction · Objectives � Anticipation � Ontologies ◮ Intelligence, Communication and Mobility � Conclusion ◮ Network Distribution and Adaptability � Demo ◮ Possibility of a Formal Verification 9/ 30 . . Diego Salomone, Thi Thuy Nga Nguyen, Andrei Olaru . 5th NII-LIP6 Workshop . Paris, 22.06.2010

� Ao Dai : CLAIM is based on explicit declaration of agent’s � Agent OrienteD Ambient characteristics: � Intelligence � AmI ◮ Capabilities � Context-awareness ◮ Procedures � Agents · Conditions · Triggers � CLAIM agents for AmI · ... � Agentification � Interaction � Anticipation � Ontologies � Conclusion � Demo 10/ 30 . . Diego Salomone, Thi Thuy Nga Nguyen, Andrei Olaru . 5th NII-LIP6 Workshop . Paris, 22.06.2010

� Ao Dai : � Agent OrienteD Ambient � Intelligence Works on top of a Java layer, giving direct access to Java � AmI resources if needed � Context-awareness � Agents � CLAIM agents for AmI � Agentification � Interaction � Anticipation � Ontologies � Conclusion � Demo 11/ 30 . . Diego Salomone, Thi Thuy Nga Nguyen, Andrei Olaru . 5th NII-LIP6 Workshop . Paris, 22.06.2010

� Ao Dai : Model context-awareness in terms of location and resources � Agent OrienteD Ambient � Intelligence as a hierarchy of agents. � AmI � Context-awareness � Agents � CLAIM agents for AmI � Agentification � Interaction � Anticipation � Ontologies � Conclusion � Demo An agent for each site, PDA, and device. 12/ 30 . . Diego Salomone, Thi Thuy Nga Nguyen, Andrei Olaru . 5th NII-LIP6 Workshop . Paris, 22.06.2010

� Ao Dai : � Agent OrienteD Ambient � Intelligence � AmI · 4 types of agents: � Context-awareness � Agents � CLAIM � Agentification � Interaction � Anticipation � Ontologies � Conclusion � Demo 13/ 30 . . Diego Salomone, Thi Thuy Nga Nguyen, Andrei Olaru . 5th NII-LIP6 Workshop . Paris, 22.06.2010

� Ao Dai : � Agent OrienteD Ambient � Intelligence � AmI � Context-awareness � Agents � CLAIM � Agentification � Interaction � Anticipation � Ontologies � Conclusion � Demo 14/ 30 . . Diego Salomone, Thi Thuy Nga Nguyen, Andrei Olaru . 5th NII-LIP6 Workshop . Paris, 22.06.2010