Subbarao Kambhampati

1
Human-Aware AI(aka Darned HumansCant Live
with them. Cant Live without them)
Future of AI

• Subbarao Kambhampati
• Arizona State University

Given at U. Washington on 11/2/2007
2
51 year old field of unknown gender Birth date
unclear Mother unknown Many purported
fathers Constantly confuses holy grail with
daily progress Morose disposition
3
So lets see if the future is going in quite
the right direction
4
What is missing in this picture?
(Static vs. Dynamic)
(Observable vs. Partially Observable)
Environment
perception
(perfect vs. Imperfect)
(Full vs. Partial satisfaction)
(Instantaneous vs. Durative)
action
Goals
(Deterministic vs. Stochastic)
The Question
What action next?
5
(No Transcript)
6
AIs Curious Ambivalence to humans..

• Our systems seem happiest
• either far away from humans
• or in an adversarial stance with humans

You want to help humanity, it is the people that
you just cant stand
7
What happened to Co-existence?

• Whither McCarthys advice taker?
• ..or Janet Kolodners house wife?
• or even Daves HAL?
• (with hopefully a less sinister voice)

HAAI
Human-aware AI
8
Why arent we doing HAAI?

• ..to some extent we are
• Assistive technology Intelligent user
  interfaces Augmented cognition, Human-Robot
  Interaction
• But it is mostly smuggled under the radar..
• And certainly doesnt get no respect..
• Rodney Dangerfield of AI?
• Is it time to bring it to the center stage?
• Having them as applied side of AI makes them seem
  peripheral, and little formal attention gets paid
  to them by the main-stream

9
(Some) Challenges of HAAI

• Communication
• Human-level communication/interfacing
• Need to understand what makes natural
  interfaces..
• Explanations
• Humans want explanations (even if fake..)
• Teachability
• Advice Taking (without lobotomy)
• Elaboration tolerance
• Dealing with evolving models
• You rarely tell everything at once to your
  secretary..
• Need to operate in an any-knowledge mode
• Recognizing Humans state
• Recognizing intent activity
• Detecting/handling emotions/affect

Human-aware AI may necessitate acting human
(which is not necessary for non-HAAI)
10
Caveats Worries about HAAI

• Are any of these challenges really new?
• HAAI vs. HDAI (human-dependent AI)
• Human dependent AI can be enormously lucrative if
  you find the right sweet spot..
• But will it hamper eventual progress to (HA)AI?
• Advice taking can degenerate to advice-needing..
• Designing HAAI agents may need competence beyond
  computer science..

11
Are the challenges really new? Are they too hard?

• Isnt any kind of feedback advice giving? Isnt
  reinforcement learning already foregrounding
  evolving domain models
• A question of granularity. There is no need to
  keep the interactions mono-syllabic..
• Wont communication require NLP and thus become
  AI-complete?
• There could well be a spectrum of communication
  modalities that could be tried
• Doesnt recognition of human activity/emotional
  state really AI?
• ..it is if we want HAAI (you want to work with
  humans, you need to have some idea of their
  state..)

12
HDAI FindingSweet Spots in computer-mediated
cooperative work

• It is possible to get by with techniques blithely
  ignorant of semantics, when you have humans in
  the loop
• All you need is to find the right sweet spot,
  where the computer plays a pre-processing role
  and presents potential solutions
• and the human very gratefully does the in-depth
  analysis on those few potential solutions
• Examples
• The incredible success of Bag of Words model!
  
• Bag of letters would be a disaster -)
• Bag of sentences and/or NLP would be good
• ..but only to your discriminating and irascible
  searchers -)
• Concern
• Will pursuit of HDAI inhibit progress towards
  eventual AI?
• By inducing perpetual dependence on (rather than
  awareness of) the human in the loop?

13
Delusions of Advice TakingGive me Advice that I
can easily use

• Planners that expect advice that is expressed
  in terms of their internal choice points
• HSTS, a NASA planner, depended on this type of
  knowledge..

• Learners that expect advice that can be easily
  included into their current algorithm
• Must link/ Must-not Link constraints used in
  semi-supervised clustering algorithms

Moral It is wishful to expect advice that will
be tailored to your program internals.
Operationalizing high-level advice is your (AI
programs) responsibility
14
HAAI pushes us beyond CS

• By dubbing acting rational as the definition of
  AI, we carefully separated the AI enterprise from
  psychology, cognitive science etc.
• But pursuit of HAAI pushes us right back into
  these disciplines (and more)
• Making an interface that improves interaction
  with humans requires understanding of human
  psychology..
• E.g. studies showing how programs that have even
  a rudimentary understanding of human emotions
  fare much better in interactions with humans
• Are we ready to do HAAI despite this push beyond
  comfort zone?

15
How are sub-areas doing on HAAI?
Ill focus on teachability aspect in two areas
that I know something about

• Automated Planning
• Full autonomy through complete domain models
• Can take prior knowledge in the form of
• Domain physics
• Control knowledge
• ..but seems to need it

• Machine Learning..
• Full autonomy through tabula rasa learning over
  gazillion samples
• Seems incapable of taking much prior knowledge
• Unless sneaked in through features and kernels..

• Automated Planning
• Full autonomy through complete domain models
• Can take prior knowledge in the form of
• Domain physics
• Control knowledge
• ..but seems to need it

• Machine Learning..
• Full autonomy through tabula rasa learning over
  gazillion samples
• Seems incapable of taking much prior knowledge
• Unless sneaked in through features and kernels..

16
Whats Rao doing in HAAI?

• Model-lite planning
• Planning in HRI scenarios
• Human-aware information integration

17
Motivations for Model-lite
Is the only way to get more applications is to
tackle more and more expressive domains?

• There are many scenarios where domain modeling is
  the biggest obstacle
• Web Service Composition
• Most services have very little formal models
  attached
• Workflow management
• Most workflows are provided with little
  information about underlying causal models
• Learning to plan from demonstrations
• We will have to contend with incomplete and
  evolving domain models..
• ..but our approaches assume complete and correct
  models..

18
Model-Lite Planning is Planning with incomplete
models
From Any Time to Any Model Planning

• ..incomplete ? not enough domain knowledge to
  verify correctness/optimality
• How incomplete is incomplete?

• Missing a couple of preconditions/effects or user
  preferences?

• Knowing no more than I/O types?

19
(No Transcript)
20
Challenges in Realizing Model-Lite Planning

1. Planning support for shallow domain models ICAC
   2005
2. Plan creation with approximate domain models
   IJCAI 2007, ICAPS Wkshp 2007
3. Learning to improve completeness of domain models
   ICAPS Wkshp 2007

21
Challenge Planning Support for Shallow Domain
Models

• Provide planning support that exploits the
  shallow model available
• Idea Explore wider variety of domain knowledge
  that can either be easily specified interactively
  or learned/mined. E.g.
• I/O type specifications (e.g. Woogle)
• Task Dependencies (e.g. workflow specifications)
• Qn Can these be compiled down to a common
  substrate?
• Types of planning support that can be provided
  with such knowledge
• Critiquing plans in mixed-initiative scenarios
• Detecting incorrectness (as against verifying
  correctness)

22
Challenge Plan Creation with Approximate Domain
Models

• Support plan creation despite missing details in
  the model. The missing details may be (1) action
  models (2) cost/utility models
• Example Generate robust line plans in the face
  of incompleteness of action description
• View model incompleteness as a form of
  uncertainty (e.g. work by Amir et. al.)
• Example Generate Diverse/Multi-option plans in
  the face of incompleteness of cost model
• Our IJCAI-2007 work can be viewed as being
  motivated this way..

Note Model-lite planning aims to reduce the
modeling burden the planning itself may actually
be harder
23
Imprecise Intent Diversity
24
Challenge Learning to Improve Completeness of
Domain Models

• In traditional model-intensive planning
  learning is mostly motivated for speedup
• ..and it has gradually become less and less
  important with the advent of fast heuristic
  planners
• In model-lite planning, learning (also) helps in
  model acquisition and model refinement.
• Learning from a variety of sources
• Textual descriptions plan traces expert
  demonstrations
• Learning in the presence of background knowledge
• The current model serves as background knowledge
  for additional refinements for learning
• Example efforts
• Much of DARPA IL program (including our LSP
  system) PLOW etc.
• Stochastic Explanation-based Learning (ICAPS
  2007 wkhop)

Make planning Model-lite ?? Make learning
knowledge (model) rich
25
Learning Planning with incomplete models A
proposal..

• Represent incomplete domain with (relational)
  probabilistic logic
• Weighted precondition axiom
• Weighted effect axiom
• Weighted static property axiom

DARPA Integrated Learning Project

• Address learning and planning problem
• Learning involves
• Updating the prior weights on the axioms
• Finding new axioms
• Planning involves
• Probabilistic planning in the presence of
  precondition uncertainty
• Consider using MaxSat to solve problems in the
  proposed formulation

26
MURI 2007 Effective Human-Robot Interaction
under Time Pressure
Indiana Univ ASU Stanford, Notre Dame
27
Challenges in Querying Autonomous Databases
CIDR 07 VLDB 07

• Imprecise Queries
• Users needs are not clearly defined hence
• Queries may be too general
• Queries may be too specific

• Incomplete Data
• Databases are often populated by
• Lay users entering data
• Automated extraction

General Solution Expected Relevance Ranking
Challenge Automated Non-intrusive assessment
of Relevance and Density functions
However, how can we retrieve similar/ incomplete
tuples in the first place?
Once the similar/incomplete tuples have
been retrieved, why should users believe them?
Challenge Rewriting a users query to retrieve
highly relevant Similar/ Incomplete tuples
Challenge Provide explanations for the uncertain
answers in order to gain the users trust
QUIC Handling Query Imprecision Data
Incompleteness in Autonomous Databases
28
Summary Say Hi to HAAI

• We may want to take HAAI as seriously as we take
  autonomous agency
• My argument is not that everybody should do it,
  but rather that it should be seen as main
  stream rather than as some applied
• HAAI does emphasize specific technical
  challenges Communication Teachability Human
  state recognition
• Pursuit of HAAI involves pitfalls (e.g. need to
  differentiate HDAI and HAAI) as well as a
  broadening of focus (e.g. need to take interface
  issues seriously)
• Some steps towards HAAI in planning

29
Points to Ponder..

• Do we (you) agree that we might need human-aware
  AI?
• Do you think anything needs to change in your
  current area of interest as a consequence?
• (What)(Are there) foundational problems in
  human-aware AI?
• Is HAAI moot without full NLP?
• How do we make progress towards HAAI
• Is IUI considered progress towards HAAI?
• Is model-lite planning?
• Is learning by X (X demonstrations being
  told)?
• Is elicitation of utility models/recognition of
  intent?

30
Epilogue HAAI is Hard but Needed..

• The challenges posed by HAAI may take us out of
  the carefully circumscribed goals of AI
• Given a choice, us computer scientists would
  rather not think about messy human interactions..
• But, do we really have a choice?