Conclusions: What Is Known and What Is Still Challenging About Landmarks - Landmarks: GIScience for Intelligent Services - page 202

needs to be to also make up for human mistakes and cognitive limitations. Systems
interacting with humans in a way meaningful to the human seems to be a reasonable
expectation for an intelligent geospatial system. It is also an expectation more
inspiring than the pure imitation of people's sometimes unreliable spatial skills and
spatial communication behavior.
At this stage we should clarify our own aspirations in using computers to
understand human cognition and in using them to achieve artificial cognition. In line
with French's call for meaningful interaction [ 7 ] , this topic does search to enable
the computer to understand human spatial expressions, and to generate spatial
expressions that can easily be digested by people. The suggested and reviewed
formal models do aim to enter into a meaningful dialog with a person, and hence,
need to sufficiently understand human spatial cognition. But they do not aspire to
explain and map processes of human spatial cognition and communication behavior
on representations in a computer. This topic is not about cognitive modeling.
In other words we do not see a need for computational processes replicating
the neurological basis of spatial representations in the brain in order to achieve a
meaningful dialog supporting a person in spatial decision making. But we do see a
need for models of landmarks that capture the nature of landmarks and are able to
relate to human embodied experiences.

7.3 What We Need to Know: Human-Computer Interaction

We see two major obstacles why modeling landmarks in computational systems
is still a great challenge. We believe that these two would definitely need to be
overcome in order to develop the kind of intelligent geospatial systems we have just
described.

1. Knowledge: The computer does not have embodied experiences of physical
reality.
In this topic, much of the human embodied experience as it has been identified
by cognitive science research has been taken as basis for formal models, differing
from current approaches based on directories or gazetteers. Lacking embodied
experiences, a computational system has to find some substitute landmark 'expe-
rience', i.e., smart ways of reasoning about existing data about an environment.
One such approach will always be machine learning from large datasets, a
stochastical approach successfully demonstrated among others by IBM's Watson
computer. Using the same philosophy, the Todai Robo t 1 sets out to pass the entry
exams of Japan's leading university, which includes questions requiring spatial
abilities such as predicting trajectories. Factual spatial knowledge, however,
would be sought from the data resources of the web or large databases. Another

1 http://21robot.org/about/?lang=english , last visited 3/1/2014.