It can perceive the mental state of a human to
support her/him. E.g., give elderly people impact to do to something, to excite
them not to become passive. We see it like to good companion or the old wise
grandfather/mother.
Related Applications:
-
be a companion: cheer up, find someone to talk to (not the machine
itself, also another person), help when needed, suggest help when found
necessary, help when detected as really needed -
learn favourites and assist (pre-selection for shopping
clothes,
...)
-
clean up, after cooking, after party, after child, keep order at state
wanted and appreciated as comfortable
-
basic daily needs: cook, look at recipe and shop (find ripe fruits and
vegetables, edible mushrooms), assist during cooking, detect ready meat on oven,
detect hairs in soup, ...
-
extension to aid handicapped persons, be "eyes of blind people" (a
person's best friend with additional capabilities) Some needed cognitive capabilities
(interesting problem):
-
detect non-object (danger, fear, emotions, ...)
-
learn how to react and to handle different emotional states
-
understand relations between humans and objects
-
understand relations between two persons
-
reason about environment and its functions,
-
recognise dangerous situations (screw loose, hose open, pot at edge) and
errors/faults
-
separate good and not good actions (good in the sense of good for the
person and the community rules)
-
learn alternative behaviours dealing with the same situation (there is
not only one way to solve a problem), this ability helps to decrease
failures, additionally if a system
is assisting a person maybe preferences for one solution are demanded (learn
priority of alternative solutions).
Envisioned results of open research
problems:
-
recognise objects under all lighting and cluttered settings possible
(many objects, classes of objects, learn objects from a few views)
-
find/recognise glass (handle reflections, maybe with other sensing
modes)
-
search web for objects/data of interest, e.g., red sport car, baroque
furniture
-
form relations between objects, reason about relations and
consequences
-
learn representations, learn to select a good representation, evolve
representations (for fast tracking, recognition, gesture interpretation,
...)
-
learn expectations and strategies: search for object in a house (not only
on one table) = look everywhere, even open drawers, stir in heaps of
objects
-
represent states, situations, models (a generic prediction tool using
environment models, e.g., bouncing ball, pot falling of shelf, a human action
expected)
-
memory at different time scales
-
automated learning of concepts given by humans (as part of acting
system)
-
learning of concepts by observation, maybe arriving at concepts different
to humans, and in this way find out more about how humans represent
concepts
-
recognise and interpret sign language (or any gestures) and find
differences between cultures, automatically translate gesture for another
cultural environment
-
recognise und understand intentions, draw conclusions from them
-
evolving vision system (learn by observation, keep running all time)
-
vision system that works and knows it works and knows it, or subparts,
fails (=does not fulfil the task), asks another vision system to help in case of
failure
-
serve multiple purposes and resolve conflicts
-
formalized methods for high level reasoning, linking high level reasoning
with low level vision, reason about elements of low level vision
-
camera/sensor working independent of lighting conditions
-
cooperating cognitive vision systems
Solving the research issues helps to solve
other applications, for example:
-
the perfect sport referee: detect fouls, incorrect play in all games,
offside in football, ...
-
sport aids: hit baseball, golf (+ golf caddy), play flipper, teach player
correct motions, ...
-
understand hand writing, hand drawings
-
recognise forged paintings, writings
-
detect weather conditions, earthquakes, hurricanes, floods
A system to aid society, a system that has a
"broad understanding" of humanity, a system that brings people together and
makes sure nobody is harmed. A visionary role as "human protector", similar to
Giskard in Asimov's novels. (Though mind reading is maybe too far away.) Example
applications, starting from simple and leading to more complex scenarios:
-
detect child seat on front seat to not unlock airbag
-
intelligent traffic control switching on most demand
-
detect waste, separate waste
-
detect landmines
-
detect unusual behaviour of patients under observation in hospital
-
detect drunken people getting into the car, car does not start
-
detect situations before they lead to accidents and react
accordingly
-
find thieves (while they are doing it, better stop them before)
-
detect and catch insects
-
detect bullets and move protection to avoid persons being hit
Why interesting problem: Takes the "personal
friend" scenario a step further and reasons not about individual humans but
about groups of persons, their behaviour, the relation to other groups, or the
relation within a mass of persons.
It requires the understanding and interpreting the actions and emotions
of many to many person relations (also involving objects). Hence, it adds
complexity to the needed cognitive abilities above.
Envisioned results of open research problems:
Same as above with the extension to groups, plus group specific topics:
-
understand and derive group behaviour from individual behaviour
-
understand inter-group behaviour
-
representation of abstracted group/human values and morale
-
multiple cooperating vision systems
-
detect animals (dolphin in net and set it free)