Transcript Computational Discovery of Communicable Knowledge

A Cognitive Architecture
for Physical Agents
Pat Langley
Computational Learning Laboratory
Center for the Study of Language and Information
Stanford University, Stanford, California USA
http://cll.stanford.edu/
Thanks to D. Choi, K. Cummings, N. Nejati, S. Rogers, S. Sage, and D. Shapiro for their
contributions. This talk reports research. funded by grants from DARPA IPTO and the
National Science Foundation, which are not responsible for its contents.
Cognitive Systems
The original goal of artificial intelligence was to design and
implement computational artifacts that:
 handled difficult tasks that require cognitive processing;
 combined many capabilities into integrated systems;
 provided insights into the nature of mind and intelligence.
Instead, modern AI has divided into many subfields that care
little about cognition, systems, or intelligence.
But the challenge remains and we need far more research on
cognitive systems.
The Fragmentation of AI Research
language
planning
perception

reasoning
action
learning
The Domain of In-City Driving
Consider driving a vehicle
in a city, which requires:
 selecting routes
 obeying traffic lights
 avoiding collisions
 being polite to others
 finding addresses
 staying in the lane
 parking safely
 stopping for pedestrians
 following other vehicles
 delivering packages
These tasks range from
low-level execution to
high-level reasoning.
Newell’s Critique
In 1973, Allen Newell argued “You can’t play twenty questions
with nature and win”. Instead, he proposed that we:
 move beyond isolated phenomena and capabilities to develop
complete models of intelligent behavior;
 demonstrate our systems’ intelligence on the same range of
domains and tasks as humans can handle;
 view artificial intelligence and cognitive psychology as close
allies with distinct but related goals;
 evaluate these systems in terms of generality and flexibility
rather than success on a single class of tasks.
However, there are different paths toward achieving such systems.
A System with Communicating Modules
language
planning
perception
reasoning
action
learning
software engineering / multi-agent systems
A System with Shared Short-Term Memory
language
planning
perception
short-term
beliefs and goals
reasoning
action
learning
blackboard architectures
Integration vs. Unification
Newell’s vision for research on theories of intelligence was that:
 cognitive systems should make strong theoretical assumptions
about the nature of the mind;
 theories of intelligence should change only gradually, as new
structures or processes are determined necessary;
 later design choices should be constrained heavily by earlier
ones, not made independently.
A successful framework is all about mutual constraints, and it
should provide a unified theory of intelligent behavior.
He associated these aims with the idea of a cognitive architecture.
A System with Shared Long-Term Memory
language
perception
planning
short-term
beliefs and goals
long-term memory
structures
action
learning
cognitive architectures
reasoning
A Constrained Cognitive Architecture
language
perception
planning
short-term
beliefs and goals
long-term memory
structures
action
learning
reasoning
The ICARUS Architecture
In this talk I will use one such framework  ICARUS  to illustrate
the advantages of cognitive architectures.
ICARUS incorporates a variety of assumptions from psychological
theories; the most basic are that:
1.
2.
3.
4.
5.
Short-term memories are distinct from long-term stores
Memories contain modular elements cast as list structures
Long-term structures are accessed through pattern matching
Cognition occurs in retrieval/selection/action cycles
Performance and learning compose elements in memory
These claims give ICARUS much in common with other cognitive
architectures like ACT-R, Soar, and Prodigy.
Architectural Commitment to Memories
A cognitive architecture makes a specific commitment to:
 long-term memories that store knowledge and procedures;
 short-term memories that store beliefs and goals;
 sensori-motor memories that hold percepts and actions.
For each memory, a cognitive architecture also commits to:
 the encoding of contents in that memory;
 the organization of structures within the memory;
 the connections among structures across memories.
Each memory holds different content the agent uses in activities.
Ideas about Representation
Cognitive psychology makes important representational claims:
 concepts and skills encode different aspects of knowledge
that are stored as distinct cognitive structures;
 cognition occurs in a physical context, with concepts and
skills being grounded in perception and action;
 many mental structures are relational in nature, in that they
describe connections or interactions among objects;
 long-term memories have hierarchical organizations that
define complex structures in terms of simpler ones;
 each element in a short-term memory is an active version of
some structure in long-term memory.
ICARUS adopts these assumptions about the contents of memory.
ICARUS’ Memories
Perceptual
Buffer
Long-Term
Conceptual
Memory
Short-Term
Belief Memory
Environment
Long-Term
Skill Memory
Short-Term
Goal Memory
Motor
Buffer
Representing Long-Term Structures
ICARUS encodes two forms of general long-term knowledge:
 Conceptual clauses: A set of relational inference rules with
perceived objects or defined concepts in their antecedents;
 Skill clauses: A set of executable skills that specify:
 a head that indicates a goal the skill achieves;
 a single (typically defined) precondition;
 a set of ordered subgoals or actions for achieving the goal.
These define a specialized class of hierarchical task networks in
which each task corresponds to a goal concept.
ICARUS’ syntax is very similar to Nau et al.’s SHOP2 formalism
for hierarchical task networks.
ICARUS Concepts for In-City 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)))
((in-segment ?self ?seg)
:percepts ((self ?self segment ?seg) (segment ?seg)))
ICARUS Skills for In-City 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)))
Representing Short-Term Beliefs/Goals
(current-street me A)
(lane-to-right g599 g601)
(last-lane g599)
(at-speed-for-u-turn 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)
(buildings-on-right g287 g279)
Encoding Perceived Objects
(self me speed 5 angle-of-road -0.5 steering-wheel-angle -0.1)
(segment g562 street 1 dist -5.0 latdist 15.0)
(line g564 length 100.0 width 0.5 dist 35.0 angle 1.1 color white segment g562)
(line g565 length 100.0 width 0.5 dist 15.0 angle 1.1 color white segment g562)
(line g563 length 100.0 width 0.5 dist 25.0 angle 1.1 color yellow segment g562)
(segment g550 street A dist oor latdist nil)
(line g600 length 100.0 width 0.5 dist -15.0 angle -0.5 color white segment g550)
(line g601 length 100.0 width 0.5 dist 5.0 angle -0.5 color white segment g550)
(line g599 length 100.0 width 0.5 dist -5.0 angle -0.5 color yellow segment g550)
(intersection g522 street A cross 1 dist -5.0 latdist nil)
(building g431 address 99 street A c1dist 38.2 c1angle -1.4 c2dist 57.4 c2angle -1.0)
(building g425 address 25 street A c1dist 37.8 c1angle -2.8 c2dist 56.9 c2angle -3.1)
(building g389 address 49 street 1 c1dist 49.2 c1angle 2.7 c2dist 53.0 c2angle 2.2)
(sidewalk g471 dist 15.0 angle -0.5)
(sidewalk g474 dist 5.0 angle 1.07)
(sidewalk g469 dist -25.0 angle -0.5)
(sidewalk g470 dist 45.0 angle 1.07)
(stoplight g538 vcolor green hcolor red))
Hierarchical Structure of Long-Term Memory
ICARUS organizes both concepts and skills in a hierarchical manner.
concepts
Each concept is defined in terms of other concepts and/or percepts.
skills
Each skill is defined in terms of other skills, concepts, and percepts.
Hierarchical Structure of Long-Term Memory
ICARUS interleaves its long-term memories for concepts and skills.
concepts
skills
For example, the skill highlighted here refers directly to
the highlighted concepts.
Architectural Commitment to Processes
In addition, a cognitive architecture makes commitments about:
 performance processes for:
 retrieval, matching, and selection
 inference and problem solving
 perception and motor control
 learning processes that:
 generate new long-term knowledge structures
 refine and modulate existing structures
In most cognitive architectures, performance and learning are
tightly intertwined.
Ideas about Performance
Cognitive psychology makes clear claims about performance:
 humans can handle multiple goals with different priorities,
which can interrupt tasks to which attention returns later;
 conceptual inference, which typically occurs rapidly and
unconsciously, is more basic than problem solving;
 humans often resort to means-ends analysis to solve novel,
unfamiliar problems;
 mental problem solving requires greater cognitive resources
than execution of automatized skills;
 problem solving often occurs in a physical context, with
mental processing being interleaved with execution.
ICARUS embodies these ideas in its performance mechanisms.
ICARUS’ Functional Processes
Perceptual
Buffer
Long-Term
Conceptual
Memory
Long-Term
Skill Memory
Conceptual
Inference
Problem Solving
Skill Learning
Short-Term
Belief
Memory
Perception
Skill Retrieval
and Selection
Environment
Short-Term
Goal Memory
Skill
Execution
Motor
Buffer
ICARUS’ Inference-Execution Cycle
On each successive execution cycle, the ICARUS architecture:
1. places descriptions of sensed objects in the perceptual buffer;
2. infers instances of concepts implied by the current situation;
3. finds paths through the skill hierarchy from top-level goals;
4. selects one or more applicable skill paths for execution;
5. invokes the actions associated with each selected path.
ICARUS agents are teleoreactive (Nilsson, 1994) in that they are
executed reactively but in a goal-directed manner.
Basic ICARUS Processes
ICARUS matches patterns to recognize concepts and select skills.
concepts
Concepts are matched bottom up, starting from percepts.
skills
Skill paths are matched top down, starting from intentions.
ICARUS Interleaves Execution and Problem Solving
Skill Hierarchy
Problem
Reactive
Execution
?
no
impasse?
Primitive Skills
yes
Problem
Solving
Executed plan
Interleaving Reactive Control and Problem Solving
Solve(G)
Push the goal literal G onto the empty goal stack GS.
On each cycle,
If the top goal G of the goal stack GS is satisfied,
Then pop GS.
Else if the goal stack GS does not exceed the depth limit,
Let S be the skill instances whose heads unify with G.
If any applicable skill paths start from an instance in S,
Then select one of these paths and execute it.
Else let M be the set of primitive skill instances that have not already failed in which G is an effect.
If the set M is nonempty,
Then select a skill instance Q from M.
Push the start condition C of Q onto goal stack GS.
Else if G is a complex concept with the unsatisfied subconcepts H and with satisfied subconcepts F,
Then if there is a subconcept I in H that has not yet failed,
Then push I onto the goal stack GS.
Else pop G from the goal stack GS and store information about failure with G's parent.
Else pop G from the goal stack GS.
Store information about failure with G's parent.
This is traditional means-ends analysis, with three exceptions: (1) conjunctive
goals must be defined concepts; (2) chaining occurs over both skills/operators
and concepts/axioms; and (3) selected skills are executed whenever applicable.
A Successful Problem-Solving Trace
initial state
(clear C)
(hand-empty)
(unst. C B)
(unstack C B)
(clear B)
(on C B)
goal
(unst. B A)
(ontable A T)
(holding C)
(putdown C T)
(clear A)
(unstack B A)
(hand-empty)
(on B A)
(holding B)
C
B
B
A
A
C
Claims about Learning
Cognitive psychology has also developed ideas about learning:
 efforts to overcome impasses during problem solving can lead
to the acquisition of new skills;
 learning can transform backward-chaining heuristic search
into more informed forward-chaining behavior;
 learning is incremental and interleaved with performance;
 structural learning involves monotonic addition of symbolic
elements to long-term memory;
 transfer to new tasks depends on the amount of structure
shared with previously mastered tasks.
ICARUS incorporates these assumptions into its basic operation.
ICARUS Learns Skills from Problem Solving
Skill Hierarchy
Problem
Reactive
Execution
?
no
impasse?
Primitive Skills
yes
Problem
Solving
Skill
Learning
Executed plan
ICARUS’ Constraints on Skill Learning
 What determines the hierarchical structure of skill memory?
 The structure emerges the subproblems that arise during
problem solving, which, because operator conditions and
goals are single literals, form a semilattice.
 What determines the heads of the learned clauses/methods?
 The head of a learned clause is the goal literal that the
planner achieved for the subproblem that produced it.
 What are the conditions on the learned clauses/methods?
 If the subproblem involved skill chaining, they are the
conditions of the first subskill clause.
 If the subproblem involved concept chaining, they are the
subconcepts that held at the subproblem’s outset.
Constructing Skills from a Trace
(clear C)
skill chaining
1
(hand-empty)
(unst. C B)
(unstack C B)
(clear B)
(on C B)
(unst. B A)
(ontable A T)
(holding C)
(putdown C T)
(clear A)
(unstack B A)
(hand-empty)
(on B A)
(holding B)
C
B
B
A
A
C
Constructing Skills from a Trace
(clear C)
1
(hand-empty)
(unst. C B)
(unstack C B)
(clear B)
(on C B)
(unst. B A)
(clear A)
(unstack B A)
skill chaining
2
(ontable A T)
(holding C)
(putdown C T)
(hand-empty)
(on B A)
(holding B)
C
B
B
A
A
C
Constructing Skills from a Trace
concept chaining
(clear C)
3
1
(hand-empty)
(unst. C B)
(unstack C B)
(clear B)
(on C B)
(unst. B A)
(clear A)
(unstack B A)
2
(ontable A T)
(holding C)
(putdown C T)
(hand-empty)
(on B A)
(holding B)
C
B
B
A
A
C
Constructing Skills from a Trace
skill chaining
(clear C)
1
(hand-empty)
(unst. C B)
(unstack C B)
4
3
(clear B)
(on C B)
(unst. B A)
(clear A)
(unstack B A)
2
(ontable A T)
(holding C)
(putdown C T)
(hand-empty)
(on B A)
(holding B)
C
B
B
A
A
C
Learned Skills in the Blocks World
(clear (?C)
:percepts ((block ?D) (block ?C))
:start
((unstackable ?D ?C))
:skills
((unstack ?D ?C)))
(clear (?B)
:percepts ((block ?C) (block ?B))
:start
((on ?C ?B) (hand-empty))
:skills
((unstackable ?C ?B) (unstack ?C ?B)))
(unstackable (?C ?B)
:percepts ((block ?B) (block ?C))
:start
((on ?C ?B) (hand-empty))
:skills
((clear ?C) (hand-empty)))
(hand-empty ( )
:percepts ((block ?D) (table ?T1))
:start
((putdownable ?D ?T1))
:skills
((putdown ?D ?T1)))
Hierarchical skills are
generalized traces of
successful means-ends
problem solving
Cumulative Curves for Blocks World
Cumulative Curves for Blocks World
Cumulative Curves for FreeCell
Learning Skills for In-City Driving
We have also trained
ICARUS to drive in our
in-city environment.
We provide the system
with tasks of increasing
complexity.
Learning transforms the
problem-solving traces
into hierarchical skills.
The agent uses these
skills to change lanes,
turn, and park using
only reactive control.
Skill Clauses Learning for In-City Driving
((parked ?me ?g1152)
:percepts ( (lane-line ?g1152) (self ?me))
:start
( )
:subgoals ( (in-rightmost-lane ?me ?g1152)
(stopped ?me)) )
((in-rightmost-lane ?me ?g1152)
:percepts ( (self ?me) (lane-line ?g1152))
:start
( (last-lane ?g1152))
:subgoals ( (driving-well-in-segment ?me ?g1101 ?g1152)) )
((driving-well-in-segment ?me ?g1101 ?g1152)
:percepts ( (lane-line ?g1152) (segment ?g1101) (self ?me))
:start
( (steering-wheel-straight ?me))
:subgoals ( (in-lane ?me ?g1152)
(centered-in-lane ?me ?g1101 ?g1152)
(aligned-with-lane-in-segment ?me ?g1101 ?g1152)
(steering-wheel-straight ?me)) )
Learning Curves for In-City Driving
Transfer of Skills in ICARUS
The architecture also supports the transfer of knowledge in that:
 skills acquired later can build on those learned earlier;
 skill clauses are indexed by the goals they achieve;
 conceptual inference supports mapping across domains.
We are exploring such effects in ICARUS as part of a DARPA
program on the transfer of learned knowledge.
Testbeds include first-person shooter games, board games, and
physics problem solving.
Transfer Effects in FreeCell
On 16-card FreeCell tasks, prior training aids solution probability.
Transfer Effects in FreeCell
However, it also lets the system solve problems with less effort.
Architectures as Programming Languages
Cognitive architectures come with a programming language that:
 includes a syntax linked to its representational assumptions
 inputs long-term knowledge and initial short-term elements
 provides an interpreter that runs the specified program
 incorporates tracing facilities to inspect system behavior
Such programming languages ease construction and debugging
of knowledge-based systems.
For this reason, cognitive architectures support far more efficient
development of software for intelligent systems.
Programming in ICARUS
The programming language associated with ICARUS comes with:
 a syntax for concepts, skills, beliefs, and percepts
 the ability to load and parse such programs
 an interpreter for inference, execution, planning, and learning
 a trace package that displays system behavior over time
We have used this language to develop adaptive intelligent
agents in a variety of domains.
An ICARUS Agent for Urban Combat
Intellectual Precursors
ICARUS’ design has been influenced by many previous efforts:
 earlier research on integrated cognitive architectures
 especially ACT, Soar, and Prodigy
 earlier frameworks for reactive control of agents
 research on belief-desire-intention (BDI) architectures
 planning/execution with hierarchical transition networks
 work on learning macro-operators and search-control rules
 previous work on cumulative structure learning
However, the framework combines and extends ideas from its
various predecessors in novel ways.
Directions for Future Research
Future work on ICARUS should introduce additional methods for:
 forward chaining and mental simulation of skills;
 learning expected utilities from skill execution histories;
 learning new conceptual structures in addition to skills;
 probabilistic encoding and matching of Boolean concepts;
 flexible recognition of skills executed by other agents;
 extension of short-term memory to store episodic traces.
Taken together, these features should make ICARUS a more general
and powerful cognitive architecture.
Contributions of ICARUS
ICARUS is a cognitive architecture for physical agents that:
 includes separate memories for concepts and skills;
 organizes both memories in a hierarchical fashion;
 modulates reactive execution with goal seeking;
 augments routine behavior with problem solving; and
 learns hierarchical skills in a cumulative manner.
These ideas have their roots in cognitive psychology, but they
are also effective in building flexible intelligent agents.
Concluding Remarks
We need more research on integrated intelligent systems that:
 are embedded within a unified cognitive architecture;
 incorporate modules that provide mutual constraints;
 demonstrate a wide range of intelligent behavior;
 are evaluated on multiple tasks in challenging testbeds.
For more information about the ICARUS architecture, see:
http://cll.stanford.edu/research/ongoing/icarus/
End of Presentation