Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence
1 like275 views
This document proposes integrating multi-agent systems and the Internet of Things to support ambient intelligence. The author aims to develop an architecture called the Internet of Smart Things that allows smart devices to collaborate as autonomous agents. Individual smart devices would be able to self-configure and interact using standard negotiation protocols. The architecture would also support distributed context reasoning and the formation of groups and societies of smart things. To achieve this, the author plans to develop smart things that function as augmented agents, extend existing agent platforms, and define organizational models for smart thing collectives.
![3Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence
• Ubiquitous Systems
Ubiquitous Computing or pervasive computing is the capability of embedding
intelligence in everyday objects in a way that the person who interacts with this object
reduces the level of interaction with the device or even does not notice them. [Weiser,
2002]
Ambient Intelligence (AmI)
• Internet of Things (IoT)
• Agents [Wooldridge, 2000]
agents are autonomous and cognitive entities from artificial intelligence.
• Multi-Agent Systems [Wooldridge, 2009]
Agents can collaborate with other agents and they have common or conflicting goals.
Besides they are situated in an environment.
1. INTRODUCTION](https://image.slidesharecdn.com/20180413-qualifyv1-180413015502/85/Integrating-Multi-Agent-Systems-and-Internet-of-Things-To-Support-Ambient-Intelligence-3-320.jpg)
![30Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence
4.1. HYBRID ARCHITECTURE FOR SMART THINGS
• Layered Architecture
Hardware
Serial interface
High-level programming language
• Agents in a Smart Thing
Standard [Bordini et al.,2007]
Argo [Pantoja et al., 2016b]
Communicator
Augmented [Casals et al., 2017]
• Different Microcontrollers
ATMEGA
PIC
Any other which uses serial
communication](https://image.slidesharecdn.com/20180413-qualifyv1-180413015502/85/Integrating-Multi-Agent-Systems-and-Internet-of-Things-To-Support-Ambient-Intelligence-30-320.jpg)
![33Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence
A
A C
C
A
MAS A MAS B
ContextNet
[Endler et al.,
2011]
SMART
THING
SMART
THING
4.2. COMMUNICABILITY AND CONNECTIVITY](https://image.slidesharecdn.com/20180413-qualifyv1-180413015502/85/Integrating-Multi-Agent-Systems-and-Internet-of-Things-To-Support-Ambient-Intelligence-33-320.jpg)
Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence
- 1. Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence Doctorate Qualifying UFF • 1. Federal Center for Technological Education (CEFET/RJ), Brazil • 2. Fluminense Federal University (UFF), Brazil • 3. Université Pierre et Marie Curie (UPMC), Paris, France Carlos Eduardo Pantoja 1,2 Advisor: José Viterbo2 Co-Advisor: Amal El-Fallah Seghrouchni3 April 13th, 2018
- 2. OUTLINE 1. Introduction 2. Background 3. The Proposed Approach 4. Work In Progress 5. Schedule
- 3. 3Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence • Ubiquitous Systems Ubiquitous Computing or pervasive computing is the capability of embedding intelligence in everyday objects in a way that the person who interacts with this object reduces the level of interaction with the device or even does not notice them. [Weiser, 2002] Ambient Intelligence (AmI) • Internet of Things (IoT) • Agents [Wooldridge, 2000] agents are autonomous and cognitive entities from artificial intelligence. • Multi-Agent Systems [Wooldridge, 2009] Agents can collaborate with other agents and they have common or conflicting goals. Besides they are situated in an environment. 1. INTRODUCTION
- 4. 4Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 1. INTRODUCTION: DOMAINS The domain of this thesis proposal!
- 5. 5Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 1.1. PROBLEM SETTING: AmI + Agents (Early Works)
- 6. 6Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 1.1. PROBLEM SETTING: AmI + Agents (Early Works)
- 7. 7Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 1.1. PROBLEM SETTING: AmI + Agents
- 8. 8Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 1.1. PROBLEM SETTING: AmI + Agents
- 9. 9Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 1.1. PROBLEM SETTING: AmI + Agents + IoT
- 10. 10Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 1.1. PROBLEM SETTING: AmI + Agents + IoT
- 11. 11Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 1.1. PROBLEM SETTING: AmI + Agents + IoT
- 12. 12Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 1.2. GOALS: AN ARCHITECTURE FOR IoST Metering Devices Indoor Air Quality Sensors Soil Humidity Sensors IoT
- 13. 13Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 1.2. GOALS: AN ARCHITECTURE FOR IoST Smart Thing Smart Thing Smart Thing Metering Devices Indoor Air Quality Sensors Soil Humidity Sensors Smart Thing IoT ST ST ST ST Smart Thing ST
- 14. 14Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 1.2. GOALS: SMART THING IoT
- 15. 15Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence Can a MAS be deployed for controlling a specific device embedded with sensors and actuators — working as a smart thing —, in a way that this device will be autonomous, proactive and independent from non-embedded or outside technologies? o Can these Smart Things be self-configurable, using standard negotiation protocols to interact with other smart things? o Can an AOPL be used or extended to develop truly autonomous Smart Things? 1.3. GOALS: RESEARCH QUESTIONS
- 16. 16Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence Can a MAS be deployed for controlling a specific device embedded with sensors and actuators — working as a smart thing —, in a way that this device will be autonomous, proactive and independent from non-embedded or outside technologies? o Can these Smart Things be self-configurable, using standard negotiation protocols to interact with other smart things? o Can an AOPL be used or extended to develop truly autonomous Smart Things? Is it possible to create an architecture to support and facilitate the implementation of scalable AmI systems using the agent approach, built over an IoT infrastructure, in which Smart Things collaborate to learn how to provide a better experience for users. o Is there an AmI or IoT middleware that could be extended for creating an architecture for interconnecting Smart Things? o Can this architecture provide support for distributed context reasoning? o Can this architecture support the formation of groups of Smart Things forming organizations or societies? 1.3. GOALS: RESEARCH QUESTIONS
- 17. OUTLINE 1. Introduction 3. The Proposed Approach 4. Work In Progress 5. Schedule
- 18. 18Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 2. BACKGROUND: JASON + ARGO
- 19. 19Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 2. BACKGROUND: AUGMENTED AGENT
- 20. 20Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 2. BACKGROUND: CONTEXNET Controller Gateway Gateway Gateway Processing node Core SDDL (DDS Domain) . . . . . . . . . 2G/3G Network WiFi Gateway Processing node . . . GroupDefiner PoA-Manager Data Connection MR-UDP MR-UDP MR-UDP MR-UDP
- 21. OUTLINE 1. Introduction 2. Background 4. Work In Progress 5. Schedule
- 22. 22Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence • Functional Attributes Autonomy Communicability Connectivity Context-awareness Heterogeneity Self-configurable 3. THE PROPOSED APPROACH: SMART THING
- 23. 23Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence • Functional Attributes Autonomy Communicability Connectivity Context-awareness Heterogeneity Self-configurable • Non-functional Attributes Adaptability Computational Capacity Interoperability Reliability Scalability 3. THE PROPOSED APPROACH: SMART THING
- 24. 24Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 3. THE PROPOSED APPROACH: ARCHITECTURE
- 25. 25Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 3. INTERNET OF SMART THINGS (IoST) ...
- 26. 26Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 3. INTERNET OF SMART THINGS (IoST) ORGANIZATION OF SMART THINGS (OoST) ...
- 27. 27Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 3. INTERNET OF SMART THINGS (IoST) SOCIETY OF SMART THINGS (SoST) ORGANIZATION OF SMART THINGS (OoST) OoST 1 OoST 2 OoST n ... ...
- 28. 28Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 3. INTERNET OF SMART THINGS (IoST) INTERNET OF SMART THINGS (IoST) SOCIETY OF SMART THINGS (SoST) ORGANIZATION OF SMART THINGS (OoST) OoST 1 OoST 2 OoST n ... SoST 1 SoST 1 SoST n ... ...
- 29. OUTLINE 1. Introduction 2. Background 3. The Proposed Approach 5. Schedule
- 30. 30Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 4.1. HYBRID ARCHITECTURE FOR SMART THINGS • Layered Architecture Hardware Serial interface High-level programming language • Agents in a Smart Thing Standard [Bordini et al.,2007] Argo [Pantoja et al., 2016b] Communicator Augmented [Casals et al., 2017] • Different Microcontrollers ATMEGA PIC Any other which uses serial communication
- 31. 31Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 4.1. HYBRID ARCHITECTURE FOR SMART THINGS
- 32. 32Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 4.1. HYBRID ARCHITECTURE FOR SMART THINGS SMARTTHING1 SMARTTHING2
- 33. 33Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence A A C C A MAS A MAS B ContextNet [Endler et al., 2011] SMART THING SMART THING 4.2. COMMUNICABILITY AND CONNECTIVITY
- 34. 34Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 4.2. COMMUNICABILITY AND CONNECTIVITY
- 35. 35Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 4.2. COMMUNICABILITY AND CONNECTIVITY Ex.: .sendOut ("788 b2b22−baa6 −4c61−b1bb− 33 01 cff1f5f878 ", achieve, decrease) preamble field size sender fffe 04 4 hex 2 hex up to 256 bytes field size 2 hex receiver up to 256 bytes field size 2 hex force up to 256 bytes field size 2 hex message up to 256 bytes kate 03 bob 07 achieve 08 Hello CN .sendOut(receiver, illocutionary forces, propositional content)
- 36. 36Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence RECEIVERSENDER Add the preamble Calculate the size of all fields Mount the message Send the message using ContexNet Verify the preamble Is Ok? Discard message Verify the size of all fields Is Ok? Mount a message Start sending a message Process it as a Jason’s Message End of the processyes yes no no 4.2. COMMUNICABILITY AND CONNECTIVITY
- 37. 37Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 4.3. NEXT STEPS: AUGMENTED AGENT It extends the Information Broker
- 38. 38Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence A C MAS A SMART THING AA M-Hub (pr,sub) (pr,obj) (pr,obj) (pr,sub) +context +raw data INFERENCE RULES CONTEXT RULES 4.3. NEXT STEPS: AUGMENTED AGENT
- 39. 39Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 4.3. NEXT STEPS: OVERVIEW ARGO HYBRID ARCHITECTURE JAVINO JAVIC COMMUNICABILITY INFERENCE SELF- CONFIGURABLE SMART THING EXTENDING GROUPS OoST ORGANIZATIONAL LANGUAGE SoST
- 40. OUTLINE 1. Introduction 2. Background 3. The Proposed Approach 4. Work In Progress
- 41. 41Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 5. SCHEDULE (2018) COMMUNICABILITY INFERENCE SELF- CONFIGURABLE SMART THING EXTENDING GROUPS OoST ORGANIZATIONAL LANGUAGE SoSTARGO HYBRID ARCHITECTURE JAVINO JAVIC
- 42. 42Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence 5. DETAILED SCHEDULE (2018) • APRIL - AVRIL Inference mechanisms of ContextNet Mobile Hub Writing Related Works Feedback from SEKE’18 • MAY – MAI Enhance a lab with Smart Things Implement Inference mechanisms Test the architecture in a small scenario • JUNE – JUIN Protocols for self-configuration Implement some study • JULY – JUILLET Self-configuration implementation and tests • AUGUST - AOÛT Explore organization technologies For agents and ContextNet • SEPTEMBER – SEPTEMBRE UPMC/LIP6 Augmented Agents • OCTOBER– OCTOBRE UPMC/LIP6 Augmented Agents Some tests • NOVEMBER – NOVEMBRE UPMC/LIP6 Architecture Implementation and tests • DECEMBER – DÉCEMBRE Architecture Implementation and tests
- 43. 43Integrating Multi-Agent Systems and Internet of Things To Support Ambient Intelligence AGRADECIMENTOS THANK YOU! pantoja@cefet-rj.br viterbo@ic.uff.br amal.elfallah@lip6.fr