Abstract:
This paper presents about an intelligent service
robot named Moratuwa Intelligent Robot (MIRob) that can
acquire knowledge through interactive discussion with the user
while handling the uncertain information in the user instructions.
In order to facilitate this behavior, a finite state intention module
has been introduced to manage the interaction between the user
and the robot. A set of states has been defined to acquire and
update the knowledge as well as in order to perform the actions
required to satisfy the user instructions. Dialogue flows and
patterns have been defined for each state in order to maintain
the interaction with the user. The defined dialogue flows and
the dialogue patterns are presented. Furthermore, the concept
has been developed in such a way that the system is capable
of updating a Robot Experience Model (REM) according to the
acquired knowledge. In order to evaluate the performance of
the system, experiments have been carried out in an artificially
created domestic environment. The capabilities of the proposed
system have been demonstrated and validated from the experimental
results.
