A general computational recognition primed decision model with multi-agent rescue simulation benchmark
Analytical decision making strategies rely on weighing pros and cons of multiple options in an unbounded rationality manner. Contrary to these strategies, recognition primed decision (RPD) model which is a primary naturalistic decision making (NDM) approach assumes that experienced and professional decision makers when encounter problems in real operating conditions are able to use their previous experiences and trainings in order to diagnose the problem, recall the appropriate solution, evaluate it mentally, and implement it to handle the problem in a satisficing manner. In this paper, a computational form of RPD, now called C-RPD, is presented. Unified Modeling Language was used as a modeling language to represent the proposed C-RPD model in order to make the implementation easy and obvious. To execute the model, RoboCup Rescue agent simulation environment, which is one of the best and the most famous complex and multi-agent large-scale environments, was selected. The environment simulates the incidence of fire and earthquakes in urban areas where it is the duty of the police forces, firefighters and ambulance teams to control the crisis. Firefighters of SOS team are first modeled and implemented by utilizing C-RPD and then the system is trained using an expert experience. There are two evaluations. To find out the convergence of different versions developed during experience adding, some of the developed versions are chosen and evaluated on seven maps. Results show performance improvements. The SOS team ranked first in an official world championship and three official open tournaments.
Quantitative analysis of the simulation data
Simulation.
Burnt Area Proportion (between 0 and 1) (?)Death toll Proportion (between 0 and 1) (?)
To execute the model, RoboCup Rescue agent simulation environment, which is one of the best and the most famous complex and multi-agent large-scale environments, was selected. The environment simulates the incidence of fire and earthquakes in urban areas where it is the duty of the police forces, firefighters and ambulance teams to control the crisis.“To show the model’s practicality, we first presented an agent model for fire brigades in the proposed framework of C-RPD, and then implemented it as fire brigades of Polytechnic’s SOS team. Later, an expert trained the system using his and other teams’ experiences one by one. The developed system was validated in two forms. The first was the validation of system’s various versions developed while training it with expert’s experiences. The test shows the system convergence while adding experiences. The second was the official validation of the whole SOS team in four official contests.” (p. 55)“It is possible to evaluate rescue simulation teams in two ways: (1) the descriptive approach which analyzes agents’ behavior and (2) the official approach which evaluates the performance by the team’s final score or the agents’ scores” (p. 61)
Benchmark data from the simulation runs
Not explicitly stated … something like: how good is our approach in the RoboCup Rescue multi agent environment?
“Not only did the SOS team rank first in all four tournaments, but the firefighters’ excellent performance amazed the other teams as well.” (p. 55)Results show performance improvements. The SOS team ranked first in an official world championship and three official open tournaments.
Not applicable.
Simulation (in RoboCup Rescue agent simulation environment) , to test the functionality and practical benefits of a novel approach (C-RPD).
 |
Die Portfolio of Solutions Website wurde ursprünglich im Rahmen des DRIVER+ Projekts entwickelt. Heute wird das Service von der AIT Austrian Institute of Technology GmbH. zum Nutzen des europäischen Krisenmanagements betrieben. PoS ist vom Disaster Competence Network Austria (DCNA) sowie von den H2020-Projekten STAMINA und TeamAware befürwortet und unterstützt. |