|
About CALO
The Defense Advanced Research Projects Agency (DARPA)
has awarded SRI three years of a five-year contract to develop an
enduring Personalized Assistant that Learns (PAL).
The program responds to DARPA’s
New Cognitive Systems Vision, which states that “A cognitive computer system should be able to learn
from its experience, as well as by being advised. It should be able
to explain what it was doing and why it was doing it, and to recover
from mental blind alleys. It should be able to reflect on what goes
wrong when an anomaly occurs, and anticipate such occurrences in the
future. It should be able to reconfigure itself in response to
environmental changes. And it should be able to be configured,
maintained, and operated by non-experts.”
DARPA expects the PAL
program to generate innovative ideas that result in new science, new
approaches to current software problems, new algorithms and tools,
and new technology of significant value to the military. CALO is one
of two projects funded by PAL. The other is RADAR.
CALO stands for
Cognitive Assistant that Learns and Organizes. The name was inspired
by the Latin word calonis, “soldier’s servant,”
because DARPA’s goal is to create a cognitive system that can
reason, learn, and respond to surprise in order to assist in military
situations.
The CALO project brings
together leading computer scientists and researchers in artificial
intelligence, perception, machine learning, natural language
processing, knowledge representation, multimodal dialog,
cyber-awareness, human-computer interaction, and flexible planning.
The single research focus of all these experts is to create an
integrated system that can “learn in the wild”—that
is, adapt to changes in its environment and its user’s goals
and tasks without programming assistance or technical intervention.
The groundbreaking nature of this ambitious goal is discussed further
in the CALO Vision.
Related Links
|
