fdsfds

AUTO: Automated Service composition for Disaster Management
robot
  

PhD Project @ Telematics Engineering Group - University of Cauca

By: Jose Armando Ordonez

 

AUTO is a framework able to design plans of composed services for environmental early warning management. AUTO is based on three components: a request processing module that transforms natural language and context information into a planning instance; the automated planning and execution module based on an architecture for planning and ex-
ecution, PELEA; and the Service Execution Environment for Web and Telco Services. The integration of a planning component provides two basic functionalities: the possibility of customizing the composition of services based on the preferences of the user and a middleware level that interfaces the execution of services in the environment.

The project was suported by the ACE from the University of East London, the Planning & Learning research Group of University Carlos III de Madrid and GRINWEB Group from Universidad Nacional de Colombia Sede Medellin

 

  

Description

The goal of the environmental early warning eld is to create contingency plans that help resolve potentially harmful or dangerous situations based on the
information gathered from sensors and the input of relevant users. An example of such a situation would be evacuating all the villages close to a river after
detecting that its level has risen beyond regular measurements or upon the request of an observer. In this case a contingency plan would include actions to
monitor the river, determine a ected areas, warn the villagers and coordinate the logistics of the evacuation.


Since the participation of a human is required in critical scenarios, we assume that all the requests are triggered by users. Besides, in rural environments the access to a device able to send a request in the format speci ed by the system may be limited. This means that the system should be able to process natural language so it can be initiated through simple communication means like a phone call or an SMS.

The overall functioning of the architecture is as follows: the user request is received in natural language from a given device and processed to determine the goals and preferences of the user. At the same time, information obtained from the sensors may be added to the request depending on the context. Next, the request is translated dynamically into a planning instance modeled using the Planning Domain De nition Language (PDDL). Then, the PDDL formatted request is sent to the High Level Replanner module of the Planning, Learning and Execution Architecture (PELEA) [6] in order to obtain and execute a plan that represents the composition of services. Finally, the composed plan is executed in a Jain SLEE 5 environment for convergent services.
   

Publications
  • A. Ordonez, J Corral, P Falcarin, "Natural language processing based Services Composition for Environmental management" . SOSE 2012 Genoa Italy.
  • A. Ordonez, J Corral, P Falcarin, "Automated context aware composition for convergent services" SOSE 2012 Genoa Italy, 2012.
  • A.. Ordonez, V. Alcazar, Daniel Borrajo, J Corral, P. Falcarin. "An Automated User-Centered Planning Framework for Decision Support in Environmental Early Warnings". IBERAMIA 2012, Cartagena. Colombia.
  • A. Ordonez, J Corral, J Guzman, P. Falcarin.. "User Centred Automated Composition in Telco 2.0". IARIA 2012. Nice France.

Downloads