V. DISCUSSION
The internal memory of two RP computers (1GB in total)
is enough for all telepresence robot operations including the
autonomous face following feature. Adding face detection
module pushes the CPU load up to its maximum. Thus, when
adding a new feature, like mobility, to the robot a separate
processing resource is required. Using the ServoBlaster
library for interfacing with servo motors added overhead on
the CPU load, thus, causing slower response from the robot.
In the future work, this hardware will be replaced with an
Arduino controller. A clear pattern of bandwidth requirement
has not yet found using this experimental design. The
maximum bandwidth used in this experiment is 143.4 KBps,
or 206 times increased over the baseline. Thus, all findings
suggested that the proposed face detection technique has reach
the maximum usage of computation resource on RP computer
model 1B. To achieve a low-cost autonomous telepresence
robot, the stable and high speed communication bandwidth
and the separation on CPU loads using task parallelism are the
key design factors.