"Robust Multiagent Decision-Making in Time-Critical
Environments"
The proposed research concentrates on the
implementation of flexible decision-making framework
that can be used by an autonomous agent in real-time
multi-agent settings. Real-time requirements and
agent's autonomy are indispensable in the real-world:
in most work on real-time systems, the agent's
rational behaviors need to be made in a timely
fashion. For example, real-time issues in space
exploration or battlefield situations are crucial
because any overhead or loss of timely response can
result in catastrophic failure. Robust autonomy is an
essential property for agents that perform unforeseen
tasks, which are too hazardous or expensive for humans
to perform.
We
will design and implement ways in which the autonomous agents can be
equipped with flexible decision-making procedures to be practical
under time constraints. The goal of our agents is to successfully
achieve their complex tasks using approximation techniques while
coping with real-time pressures by computing urgency of situation at
hand.
Back
|
