Robots in Retirement Homes: Applying Off-the-Shelf Planning and Scheduling to a Team of Assistive Robots (Extended Abstract)

This paper investigates three different technologies for solving a planning and scheduling problem of deploying multiple robots in a retirement home environment to assist elderly residents. The models proposed make use of standard techniques and solvers developed in AI planning and scheduling, with two primary motivations. First, to find a planning and scheduling solution that we can deploy in our real-world application. Second, to evaluate planning and scheduling technology in terms of the ``model-and-solve'' functionality that forms a major research goal in both domain-independent planning and constraint programming. Seven variations of our application are studied using the following three technologies: PDDL-based planning, time-line planning and scheduling, and constraint-based scheduling. The variations address specific aspects of the problem that we believe can impact the performance of the technologies while also representing reasonable abstractions of the real world application. We evaluate the capabilities of each technology and conclude that a constraint-based scheduling approach, specifically a decomposition using constraint programming, provides the most promising results for our application. PDDL-based planning is able to find mostly low quality solutions while the timeline approach was unable to model the full problem without alterations to the solver code, thus moving away from the model-and-solve paradigm. It would be misleading to conclude that constraint programming is ``better'' than PDDL-based planning in a general sense, both because we have examined a single application and because the approaches make different assumptions about the knowledge one is allowed to embed in a model. Nonetheless, we believe our investigation is valuable for AI planning and scheduling researchers as it highlights these different modelling assumptions and provides insight into avenues for the application of AI planning and scheduling for similar robotics problems. In particular, as constraint programming has not been widely applied to robot planning and scheduling in the literature, our results suggest significant untapped potential in doing so.

[1]  Erlendur S. Thorsteinsson.  Branch-and-Check: A Hybrid Framework Integrating Mixed Integer Programming and Constraint Logic Programming , 2001, CP.

[2]  J. Christopher Beck,et al.  itSIMPLE: towards an integrated design system for real planning applications , 2013, The Knowledge Engineering Review.

[3]  W. Banks,et al.  Animal-assisted therapy and loneliness in nursing homes: use of robotic versus living dogs. , 2008, Journal of the American Medical Directors Association.

[4]  Joelle Pineau,et al.  Towards robotic assistants in nursing homes: Challenges and results , 2003, Robotics Auton. Syst..

[5]  J. Christopher Beck,et al.  Using dual presolving reductions to reformulate cumulative constraints , 2013, Constraints.

[6]  Andrea Lodi,et al.  Optimization-Oriented Global Constraints , 2004, Constraints.

[7]  J. Christopher Beck,et al.  Mixed-Integer and Constraint Programming Techniques for Mobile Robot Task Planning , 2016, IEEE Robotics and Automation Letters.

[8]  Michael Pinedo,et al.  Scheduling: Theory, Algorithms, and Systems , 1994 .

[9]  Goldie Nejat,et al.  A user-study with Tangy the Bingo facilitating robot and long-term care residents , 2016, 2016 IEEE International Symposium on Robotics and Intelligent Sensors (IRIS).

[10]  Eugene Levner,et al.  Parametric algorithms for 2-cyclic robot scheduling with interval processing times , 2011, J. Sched..

[11]  Dimitris Bertsimas,et al.  Optimization over integers , 2005 .

[12]  Subbarao Kambhampati,et al.  When is Temporal Planning Really Temporal? , 2007, IJCAI.

[13]  Craig A. Knoblock,et al.  PDDL-the planning domain definition language , 1998 .

[14]  G. Mcnicoll.  World Population Ageing 1950-2050. , 2002 .

[15]  Manuela M. Veloso,et al.  Dynamic User Task Scheduling for Mobile Robots , 2011, Automated Action Planning for Autonomous Mobile Robots.

[16]  Peter J. Stuckey,et al.  MiniZinc: Towards a Standard CP Modelling Language , 2007, CP.

[17]  Martha E. Pollack,et al.  Intelligent Technology for an Aging Population: The Use of AI to Assist Elders with Cognitive Impairment , 2005, AI Mag..

[18]  Blai Bonet,et al.  Planning as heuristic search , 2001, Artif. Intell..

[19]  Goldie Nejat,et al.  A focus group study on the design considerations and impressions of a socially assistive robot for long-term care , 2014, The 23rd IEEE International Symposium on Robot and Human Interactive Communication.

[20]  J. Christopher Beck,et al.  An autonomous assistive robot for planning, scheduling and facilitating multi-user activities , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[21]  Olivier Buffet,et al.  Learning Pruning Rules for Heuristic Search Planning , 2014, ECAI.

[22]  Nils J. Nilsson,et al.  Shakey the Robot , 1984 .

[23]  Eugene C. Freuder.  In Pursuit of the Holy Grail , 1996, CSUR.

[24]  J. Christopher Beck,et al.  The Implementation of a Planning and Scheduling Architecture for Multiple Robots Assisting Multiple Users in a Retirement Home Setting , 2015, AAAI Workshop: Artificial Intelligence Applied to Assistive Technologies and Smart Environments.

[25]  J. Christopher Beck,et al.  From Requirements and Analysis to PDDL in itSIMPLE3.0 , 2009 .

[26]  Philippe Laborie,et al.  Reasoning with Conditional Time-Intervals , 2008, FLAIRS.

[27]  J. Christopher Beck,et al.  Recent Improvements Using Constraint Integer Programming for Resource Allocation and Scheduling , 2013, CPAIOR.

[28]  Philippe Laborie,et al.  Temporal linear relaxation in IBM ILOG CP Optimizer , 2016, J. Sched..

[29]  Abhinandan Jain,et al.  ROAMS: planetary surface rover simulation environment , 2003 .

[30]  Michael Beetz,et al.  Planning, Scheduling, and Plan Execution for Autonomous Robot Office Couriers , 1998 .

[31]  Christian J. Muise,et al.  Computing Contingent Plans via Fully Observable Non-Deterministic Planning , 2014, AAAI.

[32]  David E. Smith,et al.  Bridging the gap between planning and scheduling , 2000, The Knowledge Engineering Review.

[33]  Andrew Coles,et al.  COLIN: Planning with Continuous Linear Numeric Change , 2012, J. Artif. Intell. Res..

[34]  Roman Barták.  Visopt ShopFloor: On the Edge of Planning and Scheduling , 2002, CP.

[35]  Chih-Wei Hsu.  The SGPlan Planning System in IPC-6 , 2008 .

[36]  J. Hooker,et al.  Logic-based Benders decomposition , 2003 .

[37]  Philippe Laborie,et al.  Algorithms for propagating resource constraints in AI planning and scheduling: Existing approaches and new results , 2003, Artif. Intell..

[38]  Robert C. Holte,et al.  Does Representation Matter in the Planning Competition? , 2011, SARA.

[39]  Warwick Harvey,et al.  Essence: A constraint language for specifying combinatorial problems , 2007, Constraints.

[40]  Bernhard Nebel,et al.  The FF Planning System: Fast Plan Generation Through Heuristic Search , 2011, J. Artif. Intell. Res..

[41]  Paolo Traverso,et al.  Automated Planning: Theory & Practice , 2004 .

[42]  Ivan Serina,et al.  LPG-TD : a Fully Automated Planner for PDDL 2 . 2 Domains , 2004 .

[43]  Tara A. Estlin,et al.  Increased Mars Rover Autonomy using AI Planning, Scheduling and Execution , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[44]  David E. Smith.  The Case for Durative Actions: A Commentary on PDDL2.1 , 2003, J. Artif. Intell. Res..

[45]  Jean-Charles Régin,et al.  Arc Consistency for Global Cardinality Constraints with Costs , 1999, CP.

[46]  Christian J. Muise,et al.  Flexible Execution of Partial Order Plans With Temporal Constraints , 2013, IJCAI.

[47]  Kenn Steger-Jensen,et al.  Scheduling a single mobile robot for part-feeding tasks of production lines , 2014, J. Intell. Manuf..

[48]  Laura Sebastia,et al.  On the Use of Temporal Landmarks for Planning with Deadlines , 2014, ICAPS.

[49]  José Reinaldo Silva,et al.  On the Use of UML.P for Modeling a Real Application as a Planning Problem , 2006, ICAPS.

[50]  Amedeo Cesta,et al.  Planning and Scheduling Ingredients for a Multi-Agent System , 2002 .

[51]  Tara Estlin,et al.  Opportunistic Planning and Execution for Planetary Exploration , 2006 .

[52]  Tristan B. Smith,et al.  EUROPA : A Platform for AI Planning, Scheduling, Constraint Programming, and Optimization , 2012 .

[53]  Rachid Alami,et al.  An Architecture for Autonomy , 1998, Int. J. Robotics Res..

[54]  Andrew Coles,et al.  Temporal Planning with Preferences and Time-Dependent Continuous Costs , 2012, ICAPS.

[55]  Juan Fernández-Olivares,et al.  OncoTheraper: Clinical Decision Support for Oncology Therapy Planning Based on Temporal Hierarchical Tasks Networks , 2009, K4HelP.

[56]  Yu Zhang,et al.  Task allocation with executable coalitions in multirobot tasks , 2012, 2012 IEEE International Conference on Robotics and Automation.

[57]  Dana S. Nau,et al.  SHOP2: An HTN Planning System , 2003, J. Artif. Intell. Res..

[58]  Carl Hewitt,et al.  Procedural Embedding of knowledge in Planner , 1971, IJCAI.

[59]  David K. Smith.  Theory of Linear and Integer Programming , 1987 .

[60]  Helmut Simonis,et al.  A resource cost aware cumulative , 2009 .

[61]  Amedeo Cesta,et al.  Unifying planning and scheduling as timelines in a component-based perspective , 2008 .

[62]  James A. Hendler,et al.  AI Planning: Systems and Techniques , 1990, AI Mag..

[63]  Maria Fox,et al.  Temporal Plan Quality Improvement and Repair using Local Search , 2014, STAIRS.

[64]  Milind Tambe,et al.  SAVES: a sustainable multiagent application to conserve building energy considering occupants , 2012, AAMAS.

[65]  Peter J. Stuckey,et al.  Approximate Uni-directional Benders Decomposition , 2015, AAAI 2015.

[66]  Joelle Pineau,et al.  Online Planning Algorithms for POMDPs , 2008, J. Artif. Intell. Res..

[67]  Yu Zhang,et al.  Multi-robot task scheduling , 2013, 2013 IEEE International Conference on Robotics and Automation.

[68]  Fahiem Bacchus,et al.  Using temporal logics to express search control knowledge for planning , 2000, Artif. Intell..

[69]  Andrew Coles,et al.  Forward-Chaining Partial-Order Planning , 2010, ICAPS.

[70]  Patrick Doherty,et al.  TALplanner: A temporal logic based forward chaining planner , 2001, Annals of Mathematics and Artificial Intelligence.

[71]  Hector Geffner,et al.  Branching and pruning: An optimal temporal POCL planner based on constraint programming , 2004, Artif. Intell..

[72]  David E. Smith,et al.  The ANML Language , 2007 .

[73]  Sheila A. McIlraith,et al.  Planning in The Face of Frequent Exogenous Events , 2008 .

[74]  Raquel Fuentetaja,et al.  Scaling up Heuristic Planning with Relational Decision Trees , 2014, J. Artif. Intell. Res..

[75]  Malik Ghallab,et al.  A Flexible ANML Actor and Planner in Robotics , 2014 .

[76]  Goldie Nejat,et al.  Did Anyone Say BINGO: A Socially Assistive Robot to Promote Stimulating Recreational Activities at Long-Term Care Facilities , 2013 .

[77]  David E. Wilkins,et al.  Domain-Independent Planning: Representation and Plan Generation , 1984, Artif. Intell..

[78]  Héctor Palacios,et al.  Temporal Planning With Required Concurrency Using Classical Planning , 2015, ICAPS.

[79]  Maria Fox,et al.  Modelling Mixed Discrete-Continuous Domains for Planning , 2006, J. Artif. Intell. Res..

[80]  Amedeo Cesta,et al.  MONITORING ELDERLY PEOPLE WITH THE ROBOCARE DOMESTIC ENVIRONMENT: INTERACTION SYNTHESIS AND USER EVALUATION , 2011, Comput. Intell..

[81]  A. Jónsson,et al.  Planning and Monitoring Solar Array Operations on the ISS , 2008 .

[82]  Austin Tate,et al.  O-Plan2: an Open Architecture for Command, Planning and Control , 2006 .

[83]  Andrew Coles,et al.  A Hybrid LP-RPG Heuristic for Modelling Numeric Resource Flows in Planning , 2014, J. Artif. Intell. Res..

[84]  Carmel Domshlak,et al.  Simple Regret Optimization in Online Planning for Markov Decision Processes , 2012, J. Artif. Intell. Res..

[85]  J. Christopher Beck,et al.  Constraint-directed techniques for scheduling alternative activities , 2000, Artif. Intell..

[86]  Peter Nightingale,et al.  Essence' Description , 2016, ArXiv.

[87]  Philippe Laborie,et al.  IBM ILOG CP Optimizer for Detailed Scheduling Illustrated on Three Problems , 2009, CPAIOR.

[88]  Patrik Haslum,et al.  Optimal Planning with Global Numerical State Constraints , 2014, ICAPS.