Kartik csig talk

494 views

Published on

Cognitive Systems Institute Group Speaker Series call April 23, 2015 by Subbarao Kambhampati (Arizona State University) and Kartik Talamadupula (IBM Watson Research)

Published in: Technology
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total views
494
On SlideShare
0
From Embeds
0
Number of Embeds
4
Actions
Shares
0
Downloads
3
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

Kartik csig talk

  1. 1. Human-in-the-Loop Planning and Decision Support Subbarao Kambhampati Arizona State University 1 CSIG Speaker Series Adapted from a AAAI 2015 Tutorial rakaposhi.eas.asu.edu/hilp-tutorial/index.htm Kartik Talamadupula IBM T.J. Watson Research Center
  2. 2. AI’s Curious Ambivalence to Humans.. You want to help humanity, it is the people that you just can’t stand… • Our systems seem happiest .. • …either far away from humans • …or in an adversarial stance with humans
  3. 3. What happened to Co-existence? • Whither McCarthy’s advice taker? • ..or Janet Kolodner’s house wife? • …or even Dave’s HAL? • (with hopefully a less sinister voice) THIS TALK HAAI in Planning
  4. 4. AI Planning: The Canonical View 4 A fully specified problem --Initial state --Goals (each non-negotiable) --Complete Action Model The Plan
  5. 5. Human-in-the-Loop Planning • In many scenarios, humans are part of the planning loop, because the planner: • Needs to plan to avoid them • Human-Aware Planning • Needs to provide decision support to humans • Because “planning” in some scenarios is too important to be left to automated planners • “Mixed-initiative Planning”; “Human-Centered Planning”; “Crowd-Sourced Planning” • Needs help from humans • Mixed-initiative planning; “Symbiotic autonomy” • Needs to team with them • Human-robot teaming; Collaborative planning 5
  6. 6. A Brief History of HILP • Beginnings of significant interest in the 90’s • Under the aegis of ARPA Planning Initiative (and NASA) • Several of the critical challenges were recognized • Trains project [Ferguson/Allen; Rochester] • Overview of challenges [Burstein/McDermott + ARPI Cohort] • MAPGEN work at NASA • At least some of the interest in HILP then was motivated by the need to use humans as a “crutch” to help the planner • Planners were very inefficient back then; and humans had to “enter the land of planners” and help their search.. • In the last ~15 years, much of the mainstream planning research has been geared towards improving the speed of of plan generation • Mostly using reachability and other heuristics • Renaissance of interest in HILP thanks to the realization that HILP is critical in many domains even with “fast” planners 6
  7. 7. Dimensions of HIL Planning 7 Cooperation Modality Communication Modality What is Communicated Knowledge Level Crowdsourcing Interaction (Advice from planner to humans) Custom Interface Critiques, subgoals Incomplete Preferences Incomplete Dynamics Human-Robot Teaming Teaming/Collaborat ion Natural Language Speech Goals, Tasks, Model information Incomplete Preferences Incomplete Dynamics (Open World) “Grandpa Hates Robots” Awareness (pre- specified constraints) Prespecified (Safety / Interaction Constraints) No explicit communication Incomplete Preferences Complete Dynamics MAPGEN Interaction (Planner takes binding advice from human) Direct Modification of Plans Direct modifications, decision alternatives Incomplete Preferences Complete Dynamics
  8. 8. How do we adapt/adopt modern planning technology for HILP? 8
  9. 9. Planning The Canonical View 9 Plan (Handed off for Execution) Full Problem Specification PLANNER Fully Specified Action Model Fully Specified Goals Completely Known (Initial) World StateAssumption: Complete Action Descriptions Fully Specified Preferences All objects in the world known up front One-shot planning Allows planning to be a pure inference problem  But humans in the loop can ruin a really a perfect day  Violated Assumptions: Complete Action Descriptions (Split knowledge) Fully Specified Preferences (uncertain users) Packaged planning problem (Plan Recognition) One-shot planning (continual revision) Planning is no longer a pure inference problem 
  10. 10. 00000000000000000000 00000000000000000000 00000000000000000000 0000000000000 Human-in-the-Loop Planning 10 Coordinate with Humans [IROS14, PlanRob15] Replan for the Robot [AAAI10, DMAP13] Communicate with Human(s) in the Loop OpenWorld Goals [IROS09,AAAI10,TIST10] Action Model Information [HRI12] Handle Human Instructions [ACS13, IROS14] Assimilate Sensor Information Full Problem Specification PLANNER Fully Specified Action Model Fully Specified Goals Completely Known (Initial) World State Sapa Replan Problem Updates [TIST10] Human-in-the-Loop Planning and Decision Support Goal Manager
  11. 11. Challenges for the Planner 1. Interpret what humans are doing • Plan/goal/intent recognition 2. Decision Support • Continual planning/Replanning • Commitment sensitive to ensure coherent interaction • Handle constraints on plan • Plan with incompleteness • Incomplete Preferences • Incomplete domain models • Robust planning with “lite” models • (Learn to improve domain models) 3. Communication • Explanations/Excuses • Excuse generation can be modeled as the (conjugate of) planning problem • Asking for help/elaboration • Reason about the information value
  12. 12. Challenge: Interpretation •Recognize and interpret what the human needs (goal, intent) and is currently doing (plan) •Structure of “plans”: • Assume Structure: Plan/Goal Recognition • Exploit/assume structured representation (plan) • Easier to match planner’s expectation of structured input • Restricts flexibility of humans; less knowledge specified • Extract/Infer Structure: Infer Human Plans • Allow humans to use natural language • Semi-structured and unstructured text • Extract information from human-generated input • Validate against (partial) model • Iteratively refine recognized goals and plan 12
  13. 13. Plan/Goal Recognition for Human-Robot Teaming Talamadupula et al. – Arizona State University & Tufts University Coordination in Human-Robot Teams Using Mental Modeling & Plan Recognition BELIEF IN GOAL
  14. 14. Planning Conversation Robot Task Plans Go here Inferring Human (Team) Task Plans • Integrate robots seamlessly in time-critical domains • Lessen burden of programming and deploying robots • Leverage the use of web-based planning tool (NICS) 14 Inferring Robot Task Plans from Human Team Meetings Been Kim, Caleb Chacha and Julie Shah – MIT
  15. 15. Challenge: Decision Support • Need to generate (and maintain) plans in the presence of human quirks and real- world considerations – Partially specified preferences • Diverse plans – Fully specified constraints / preferences • “Grandpa hates robots” – Partially specified model of the world • Robust plans – Changing world state and goals • Replanning 15
  16. 16. Problem Statement:  Given  the objectives Oi,  the vector w for convex combination of Oi  the distribution h(w) of w,  Return a set of k plans with the minimum ICP value.  Solution Approaches:  Sampling: Sample k values of w, and approximate the optimal plan for each value.  ICP-Sequential: Drive the search to find plans that will improve ICP  Hybrid: Start with Sampling, and then improve the seed set with ICP-Sequential  [Baseline]: Find k diverse plans using the distance measures from [IJCAI 2007] paper; LPG-Speed. 1616 Generating diverse plans to handle unknown and partially known user preferences Nguyen, Do, Gerevini, Serina, Srivastava & Kambhampati, 2012 Handling Partially Specified Preferences
  17. 17. 17 Grandpa Hates Robots Köckemann, Karlsson & Pecora Fully Specified Constraints
  18. 18. • Compilation approach: Compile into a (Probabilistic) Conformant Planning problem • One “unobservable” variable per each possible effect/precondition • Significant initial state uncertainty • Can adapt a probabilistic conformant planner such as POND [JAIR, 2006; AIJ 2008] • Direct approach: Bias a planner’s search towards more robust plans • Heuristically assess the robustness of partial plans • Need to use the (approximate) robustness assessment procedures [Bryce et. Al., ICAPS 2012; Nguyen et al; NIPS 2013; Nguyen & Kambhampati, ICAPS 2014 Handling Partial Models of the World
  19. 19. 19 Replanning for Changes in the World A Theory of Intra-Agent Replanning Talamadupula, Smith, Cushing & Kambhampati
  20. 20. 20 Challenge: Communication • Planner has to communicate with humans to: • Provide explanations • Ask for help • Providing Explanations • Excuses for failures • Explanations for state facts • Asking for Help • Symbiotic autonomy – humans doing what robots cannot • Generating detailed utterances to elicit effective help
  21. 21. 21 Coming up With Good Excuses Göbelbecker, Keller, Eyerich, Brenner & Nebel (2010) Generating Excuses
  22. 22. 22 Preferred Explanations Sohrabi, Baier & McIlraith (2011)
  23. 23. Carnegie Mellon University Stephanie Rosenthal and Manuela Veloso 23 [Rosenthal, Veloso ,Dey: Ro-Man 2009, IUI 2010, JSORO 2012] People are great sources of information for robots ‘Humans as Sensors and Effectors’ Symbiotic Autonomy Rosenthal, Veloso et al. Asking for Help – Symbiotic Autonomy “Can you hold the elevator door open for me?” “Can you point to where on this map?” “Can you tell me when we reach the 4th floor?” “Can you transfer this item from my basket?”
  24. 24. 24 Asking for Help Using Inverse Semantics Tellex, Knepper, Li, Rus & Roy Generating Utterances to Elicit Help
  25. 25. Case Study Human-Robot Teaming + Crowdsourcing PLANNING FOR HUMAN-ROBOT TEAMING PLANNING FOR CROWDSOURCING INTERPRETATION Open World Goals Continual (Re)Planning Plan & Intent Recognition Activity Suggestions Activity Critiques Ordering Constraints DECISION SUPPORT Continual (Re)Planning Plan & Intent Recognition Sub-goal Generation Constraint Violations Continual Improvement COMMUNICATION Model Updates Sub-goal Generation 25
  26. 26. Dimensions of HIL Planning 26 Cooperation Modality Communication Modality What is Communicated Knowledge Level Crowdsourcing Interaction (Advice from planner to humans) Custom Interface Critiques, subgoals Incomplete Preferences Incomplete Dynamics Human-Robot Teaming Teaming/Collaborat ion Natural Language Speech Goals, Tasks, Model information Incomplete Preferences Incomplete Dynamics (Open World) “Grandpa Hates Robots” Awareness (pre- specified constraints) Prespecified (Safety / Interaction Constraints) No explicit communication Incomplete Preferences Complete Dynamics MAPGEN Interaction (Planner takes binding advice from human) Direct Modification of Plans Direct modifications, decision alternatives Incomplete Preferences Complete Dynamics
  27. 27. Recap 27 • HILP raises several open challenges for planning systems, depending on the modality of interaction between human and planner • This talk: – Discussed dimensions of variation of HILP tasks – Identified the planning challenges posed by HILP scenarios • Interpretation, Decision Support and Communication – Outlined a few current approaches for addressing these challenges rakaposhi.eas.asu.edu/hilp-tutorial

×