Cognitive Architectures and
Virtual Intelligent Agents
Pat Langley
School of Computing and Informatics
Arizona State University
Tempe, Arizona USA
Thanks to D. Choi, G. Cleveland, T. Konik, N. Li, N. Nejati, C. Park, and D. Stracuzzi
for their contributions. This talk reports research partly funded by grants from ONR and
DARPA, which are not responsible for its contents.
The Nature of Intelligence
Cognitive science and AI, although distinct fields, agree on
some core assumptions:
 Intelligence arises from computational processes
 A variety of functional abilities underlie intelligence
 These abilities are general yet benefit from knowledge
 Humans remain our best examples of intelligent systems
Progress toward understanding intelligence requires taking a
position on two key methodological questions:
• What theoretical framework should one assume?
• What problems or testbeds should drive research?
Frameworks for Intelligent Systems
Because intelligence involves distinct abilities, it is tempting
to develop them separately and then combine them.
This position is well represented in the AI community by:
 Software engineering (e.g., Brugali, 2009)
 Blackboard systems (Engelmore & Morgan, 1988)
 Multi-agent systems (Weiss, 2000)
Such integrated approaches offer clear advantages in terms of
modular development and division of labor.
But they are not the only way to create intelligent artifacts.
Cognitive Architectures
A cognitive architecture (Newell, 1990) is an infrastructure
for intelligent systems that:
 makes strong theoretical assumptions about the representations
and mechanisms underlying cognition
 incorporates many ideas from psychology about the nature
of the human mind
 contains distinct modules, but these access and alter the same
memories and representations
 comes with a programming language that eases construction of
knowledge-based systems
A cognitive architecture is all about mutual constraints, and it
should provide a unified theory of intelligent behavior.
Testbeds for Intelligent Systems
We also need problems and testbeds that pose challenges to
theories and evaluate their responses. Examples include:
 Educational tasks (e.g., reasoning in math and physics)
 Standardized tests (e.g., IQ, SAT, GRE exams)
 Integrated robots (e.g., for search and rescue)
 Synthetic characters in virtual worlds (e.g., for games)
Each problem class has advantages and disadvantages, but all
have important roles to play.
In this talk, I will report work on synthetic characters that has
driven our progress on cognitive architectures.
Synthetic Agents for Urban Driving
Insert
demo here
QuickTime™ and a
decompressor
are needed to see this picture.
Outline for the Talk
• Frameworks and testbeds for intelligent systems
• Review of the ICARUS cognitive architecture
• Common and distinctive features
• Representation and organization of memory
• Performance and learning mechanisms
• Synthetic agents developed with ICARUS
• Complex synthetic environments
• Lessons learned from these efforts
• Plans for future architectural / testbed research
The ICARUS Architecture
ICARUS (Langley, 2006) is a computational theory of the human
cognitive architecture that posits:
1. Short-term memories are distinct from long-term stores
2. Memories contain modular elements cast as symbolic structures
3. Long-term structures are accessed through pattern matching
4. Cognition occurs in retrieval/selection/action cycles
5. Learning involves monotonic addition of elements to memory
6. Learning is incremental and interleaved with performance
These assumptions are not novel; it shares them with architectures
like Soar (Laird et al., 1987) and ACT-R (Anderson, 1993).
Distinctive Features of ICARUS
However, ICARUS also makes assumptions that distinguish it from
these architectures:
1. Cognition is grounded in perception and action
2. Categories and skills are separate cognitive entities
3. Short-term elements are instances of long-term structures
4. Skills and concepts are organized in a hierarchical manner
5. Inference and execution are more basic than problem solving
Some of these tenets also appear in Bonasso et al.’s (2003) 3T,
Freed’s (1998) APEX, and Sun et al.’s (2001) Clarion.
But only ICARUS combines them into a unified cognitive theory.
Research Goals for ICARUS
Our current objectives in developing ICARUS are to produce:
 a computational theory of high-level cognition in humans
 that is qualitatively consistent with results from psychology
 that exhibits as many distinct cognitive functions as possible
 that supports creation of intelligent agents in virtual worlds
We have not yet modeled quantitative results from experiments,
but we hope to obtain such fits when ICARUS is more mature.
This would enable more direct comparison to architectures like
ACT-R, Clarion, and EPIC (Meyer & Kieras, 1997).
Cascaded Integration in ICARUS
Like other unified cognitive architectures, ICARUS incorporates a
number of distinct modules.
learning
problem solving
skill execution
conceptual inference
ICARUS adopts a cascaded approach to integration in which
lower-level modules produce results for higher-level ones.
ICARUS Beliefs and Goals for Urban Driving
Inferred beliefs:
(current-street me A)
(lane-to-right g599 g601)
(last-lane g599)
(under-speed-limit me)
(steering-wheel-not-straight me)
(in-lane me g599)
(on-right-side-in-segment me)
(building-on-left g288)
(building-on-left g427)
(building-on-left g431)
(building-on-right g287)
(increasing-direction me)
(current-segment me g550)
(first-lane g599)
(last-lane g601)
(slow-for-right-turn me)
(centered-in-lane me g550 g599)
(in-segment me g550)
(intersection-behind g550 g522)
(building-on-left g425)
(building-on-left g429)
(building-on-left g433)
(building-on-right g279)
(near-pedestrian me g567)
Top-level goals:
(not (near-pedestrian me ?any))
(on-right-side-in-segment me)
(not (over-speed-limit me))
(not (near-vehicle me ?other))
(in-lane me ?segment)
(not (running-red-light me))
ICARUS Concepts for Urban Driving
((in-rightmost-lane ?self ?clane)
:percepts ((self ?self) (segment ?seg)
(line ?clane segment ?seg))
:relations ((driving-well-in-segment ?self ?seg ?clane)
(last-lane ?clane)
(not (lane-to-right ?clane ?anylane))))
((driving-well-in-segment ?self ?seg ?lane)
:percepts ((self ?self) (segment ?seg) (line ?lane segment ?seg))
:relations ((in-segment ?self ?seg) (in-lane ?self ?lane)
(aligned-with-lane-in-segment ?self ?seg ?lane)
(centered-in-lane ?self ?seg ?lane)
(steering-wheel-straight ?self)))
((in-lane ?self ?lane)
:percepts ((self ?self segment ?seg) (line ?lane segment ?seg dist ?dist))
:tests
( (> ?dist -10) (<= ?dist 0)))
Hierarchical Organization of Concepts
ICARUS organizes conceptual memory in a hierarchical manner.
concept
concept clause
percept
The same conceptual predicate can appear in multiple clauses
to specify disjunctive and recursive concepts.
Conceptual Inference in ICARUS
Conceptual inference in ICARUS occurs from the bottom up.
concept
concept clause
percept
Starting with observed percepts, this process produces high-level
beliefs about the current state.
Conceptual Inference in ICARUS
Conceptual inference in ICARUS occurs from the bottom up.
concept
concept clause
percept
Starting with observed percepts, this process produces high-level
beliefs about the current state.
Conceptual Inference in ICARUS
Conceptual inference in ICARUS occurs from the bottom up.
concept
concept clause
percept
Starting with observed percepts, this process produces high-level
beliefs about the current state.
Conceptual Inference in ICARUS
Conceptual inference in ICARUS occurs from the bottom up.
concept
concept clause
percept
Starting with observed percepts, this process produces high-level
beliefs about the current state.
ICARUS Skills for Urban Driving
((in-rightmost-lane ?self ?line)
:percepts ((self ?self) (line ?line))
:start
((last-lane ?line))
:subgoals ((driving-well-in-segment ?self ?seg ?line)))
((driving-well-in-segment ?self ?seg ?line)
:percepts ((segment ?seg) (line ?line) (self ?self))
:start
((steering-wheel-straight ?self))
:subgoals ((in-segment ?self ?seg)
(centered-in-lane ?self ?seg ?line)
(aligned-with-lane-in-segment ?self ?seg ?line)
(steering-wheel-straight ?self)))
((in-segment ?self ?endsg)
:percepts ((self ?self speed ?speed) (intersection ?int cross ?cross)
(segment ?endsg street ?cross angle ?angle))
:start
((in-intersection-for-right-turn ?self ?int))
:actions (( steer 1)))
Hierarchical Organization of Skills
ICARUS organizes skills in a hierarchical manner, which each
skill clause indexed by the goal it aims to achieve.
goal
skill clause
operator
The same goal can index multiple clauses to allow disjunctive,
conditional, and recursive procedures.
Skill Execution in ICARUS
Skill execution occurs from the top down, starting from goals,
to find applicable paths through the skill hierarchy.
goal
skill clause
operator
A skill clause is applicable if its goal is unsatisfied and if its
conditions hold, given bindings from above.
Skill Execution in ICARUS
This process repeats on each cycle to produce goal-directed but
reactive behavior (Nilsson, 1994).
goal
skill clause
operator
However, ICARUS prefers to continue ongoing skills when they
match, giving it a bias toward persistence over reactivity.
Skill Execution in ICARUS
If events proceed as expected, this iterative process eventually
achieves the agent’s top-level goal.
goal
skill clause
operator
At this point, another unsatisfied goal begins to drive behavior,
invoking different skills to pursue it.
Execution and Problem Solving in ICARUS
Skill Hierarchy
Reactive
Execution
no
Problem
goal
impasse?
beliefs
yes
Generated Plan
Primitive Skills
Problem
Solving
Problem solving involves means-ends analysis that chains backward over skills
and concept definitions, executing skills whenever they become applicable.
ICARUS Learns Skills from Problem Solving
Skill Hierarchy
Reactive
Execution
no
Problem
goal
impasse?
beliefs
yes
Generated Plan
Primitive Skills
Problem
Solving
Skill
Learning
Learning from Problem Solutions
ICARUS incorporates a mechanism for learning new skills that:
 operates whenever problem solving overcomes an impasse
 incorporates only information stored locally with goals
 generalizes beyond the specific objects concerned
 depends on whether chaining involved skills or concepts
 supports cumulative learning and within-problem transfer
This skill creation process is fully interleaved with means-ends
analysis and execution.
Learned skills carry out forward execution in the environment
rather than backward chaining in the mind.
ICARUS Summary
ICARUS is a unified theory of the cognitive architecture that:
 includes hierarchical memories for concepts and skills;
 interleaves conceptual inference with reactive execution;
 resorts to problem solving when it lacks routine skills;
 learns such skills from successful resolution of impasses.
We have developed ICARUS agents for a variety of simulated
physical environments.
However, each effort has revealed limitations that have led to
important architectural extensions.
Urban Combat
Urban Driving
MadRTS
Rush 2008
Creating Synthetic Agents in ICARUS
Synthetic Agents for ‘Urban Combat’
Urban Combat is a synthetic environment, built on the Quake
engine, used in the DARPA Transfer Learning program.
Tasks for agents involved traversing an urban landscape with a
variety of obstacles to capture a flag.
Our experiences in Urban Combat provided some clear lessons:
 Storing, using, and learning route knowledge
 Learning to handle obstacles through
trial and error
 Supporting different varieties of
structural transfer across problems
Each of these insights has influenced
our more recent work on ICARUS.
Transfer Studies with Urban Combat
Start
Start
Experiments with ICARUS agents
on Urban Combat demonstrated
varieties of structural transfer
across multiple goal-directed tasks
(Choi et al., ICCM-2007).
IED
IED
Transfer vs. Control Conditions
Source
Start
IED
Target
Synthetic Agents for Urban Driving
We have developed an urban driving environment using Garage
Games’ Torque game engine.
QuickTime™ and a
YUV420 codec decompressor
are needed to see this picture.
This domain involves a mixture of cognitive and sensori-motor
behavior in a constrained but complex and dynamic setting.
Synthetic Agents for Urban Driving
The Torque urban driving environment supports tasks of graded
complexity, including:
 Keeping the car aligned at a constant speed
 Changing speed to obey traffic signs and lights
 Changing lanes/speed to avoid vehicles/pedestrians
 Approaching and turning a corner
 Driving repeatedly around a block
 Delivering packages to specified addresses
We have developed ICARUS agents that address each of these
tasks in a reasonably robust manner.
We have also demonstrated its ability to learn driving skills from
problem solving (Langley & Choi, JMLR, 2006).
Synthetic Agents for Urban Driving
Our early efforts on urban driving motivated two key features
of the ICARUS architecture:
 Indexing skills by the goals they achieve
 Multiple top-level goals with priorities
Recent work on Torque driving agents has led to additional
changes to the architecture (Choi, 2010):
 Long-term memory for generic goals
 Reactive generation of specific short-term goals
 Resource-based execution of multiple skills per cycle
Our use of this complex environment has driven our cognitive
architecture research toward important new functionalities.
Synthetic Agents for American Football
We have also developed ICARUS agents to execute football plays in
Rush 2008 from Knexus Research.
This domain is
less complex in
some ways but
it still remains
highly reactive
and depends on
spatio-temporal
coordination
among players
on a team.
QuickTime™ and a
decompressor
are needed to see this picture.
Synthetic Agents for American Football
Our results in Rush 2008 are interesting because ICARUS learned
its football skills by observing other agents.
QuickTime™ and a
YUV420 codec decompressor
are needed to see this picture.
This and similar videos of the Oregon State football team provided
training examples to drive this process.
Synthetic Agents for American Football
Our efforts on Rush 2008 have motivated additional extensions
to the ICARUS architecture:
 Time stamps on beliefs to support episodic traces
 Ability to represent and recognize temporal concepts
 Adapting means-ends analysis to explain observed behavior
 Ability to control multiple agents in an environment
We have used the extended ICARUS to learn hierarchical skills for
20 distinct football plays (Li et al., AAIDE-2009).
These results utilized Oregon State’s image-processing system,
which extracted objects and simple events from the videos.
Synthetic Agents for Twig Scenarios
Most recently, we have used Horswill’s (2008) Twig simulator
to develop humanoid ICARUS agents.
This low-fidelity environment supports a few object types, along
with simple reactive behaviors for virtual characters.
Synthetic Agents for Twig Scenarios
We have developed a specific Twig scenario that involves four
types of synthetic characters:
 Innocents go from ball to ball, pausing to pick up any dolls they
encounter nearby.
 Collectors sit in chairs, buy dolls from anyone who offers at the
right price, and secure these purchases in safes.
 Producers stand by trees, produce new dolls, and guard them by
blocking any other agents who approach.
 Capitalists work in pairs, buying or stealing dolls from Innocents,
stealing them from Producers, and selling them to Collectors.
We have developed ICARUS agents for these character types to
demonstrate their interactions with each other.
This served as the final project for an ASU course on cognitive
systems and intelligent agents (http://circas.asu.edu/cogsys/).
Synthetic Agents for Twig Scenarios
QuickTime™ and a
Microsoft Video 1 decompressor
are needed to see this picture.
Reasoning about Others
We designed ICARUS to model intelligent embodied agents, but
our work has emphasized independent action.
• The framework can deal with other agents, but only by
viewing them as objects in the environment.
Yet humans can reason about the beliefs, goals, and intentions of
others, then use their inferences to make decisions.
• One might even argue that such deep social cognition is a key
feature of human intelligence.
Adding this capability to ICARUS will require extensions to its
representation, performance processes, and learning methods.
Ongoing ICARUS Extensions
To provide ICARUS with the capability to reason about others’
mental states, we are:
• Extending its representation to allow embedded modal literals
[e.g., (belief me (goal driver2 (in-right-lane driver2 seg6)))];
• Revising inference to support incremental abductive reasoning
that explains events in terms of mental states;
• Extending skill execution and problem solving to pursue goals
that change mental states (e.g., by communication); and
• Introducing learning mechanisms that make inference about
others more efficient with experience.
We are developing these abilities to construct conversational
agents for emergency medical assistance in the field.
Synthetic Environments / Architectural Testbeds
In an STTR collaboration, we are using SET Corp.’s CASTLE,
a flexible physics/simulation engine, to:
• Create an improved urban driving environment that supports a
richer set of objects, goals, and activities;
• Develop a ‘treasure hunt’ testbed in which players must follow
complex instructions and coordinate with other agents;
• Create interfaces to ICARUS, ACT-R, and other architectures;
• Design tasks of graded complexity that can aid in evaluating
architecture-based cognitive models.
Together, these will let the community evaluate its architectures
on common problems in shared testbeds.
These will support both extended, open-ended operations and
brief, hand-crafted scenarios.
CASTLE Screen Shots / Assumptions
Rigid body dynamics — solid objects, Newtonian physics, friction, joints,
springs; no flexible objects or fluids
Z-buffer graphics — solid objects, textures, lights; no shadows, motion
blur, or irradiance
Concluding Remarks
In this talk, I presented ICARUS, a unified theory of the human
cognitive architecture that:
• Grounds high-level cognition in perception and action
• Treats categories and skills as separate cognitive entities
• Views short-term structures as instances of long-term ones
• Organizes skills and concepts in a hierarchical manner
• Combines reactive control with deliberative problem solving
In addition, I reported a number of ICARUS agents that control
synthetic agents in simulated environments.
These efforts raised theoretical challenges, led to extensions, and
revealed insights about the nature of intelligence.
Other Research on Modeling / Simulation
Qualitative system-level
models of human aging
(Langley, NIA-2009)
Time
–
+
+
junk-protein
junk-protein
+
Quantitative process models
of ecological systems
(Bridewell et al., MLj, 2008)
Lysosome
Fe
–
Cytoplasm
+
ROS
+
+
membrane-damage
+
+
lipofuscin
oxidized-protein
+
lipofuscin
H202
–
lytic-enzyme
+
H202
End of Presentation