Learning the Scope of Applicability for Task Planning Knowledge in Experience-Based Planning Domains

Experience-based planning domains (EBPDs) have been proposed to improve problem solving by learning from experience. They rely on acquiring and using task knowledge, i.e., activity schemata, for generating solutions to problem instances in a class of tasks. Using Three-Valued Logic Analysis (TVLA), we extend our previous work to generate a set of conditions that determine the scope of applicability of an activity schema. The inferred scope is an abstract representation of a potentially unbounded set of problems, in the form of a 3-valued logical structure, which is used to test the applicability of the respective activity schema for solving different task problems. We validate this work on two classical planning domains and a simulated PR2 in Gazebo.

[1]  Eugene W. Myers,et al.  Suffix arrays: a new method for on-line string searches , 1993, SODA '90.

[2]  Richard Fikes,et al.  Learning and Executing Generalized Robot Plans , 1993, Artif. Intell..

[3]  Richard Fikes,et al.  STRIPS: A New Approach to the Application of Theorem Proving to Problem Solving , 1971, IJCAI.

[4]  S. C. Kleene,et al.  Introduction to Metamathematics , 1952 .

[5]  David W. Aha,et al.  CaMeL: Learning Method Preconditions for HTN Planning , 2002, AIPS.

[6]  Armando J. Pinho,et al.  Experience-Based Planning Domains: an Integrated Learning and Deliberation Approach for Intelligent Robots , 2016, J. Intell. Robotic Syst..

[7]  Lukás Chrpa,et al.  Generation of macro-operators via investigation of action dependencies in plans , 2010, The Knowledge Engineering Review.

[8]  Luís Seabra Lopes,et al.  Failure recovery planning in assembly based on acquired experience: learning by analogy , 1999, Proceedings of the 1999 IEEE International Symposium on Assembly and Task Planning (ISATP'99) (Cat. No.99TH8470).

[9]  Hector Muñoz-Avila,et al.  Learning to Do HTN Planning , 2006, ICAPS.

[10]  Reinhard Wilhelm,et al.  Parametric shape analysis via 3-valued logic , 1999, POPL '99.

[11]  Armando J. Pinho,et al.  Experience-Based Robot Task Learning and Planning with Goal Inference , 2016, ICAPS.

[12]  Armando J. Pinho,et al.  An approach to robot task learning and planning with loops , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[13]  Manuela Veloso,et al.  Learning domain-specific planners from example plans , 2008 .

[14]  Ivan Serina,et al.  Progress in Case-Based Planning , 2015, ACM Comput. Surv..

[15]  Armando J. Pinho,et al.  Learning robot tasks with loops from experiences to enhance robot adaptability , 2017, Pattern Recognit. Lett..

[16]  Armando J. Pinho,et al.  Gathering and Conceptualizing Plan-Based Robot Activity Experiences , 2014, IAS.

[17]  Neil Immerman,et al.  A new representation and associated algorithms for generalized planning , 2011, Artif. Intell..

[18]  Gi Hyun Lim,et al.  Interactive teaching and experience extraction for learning about objects and robot activities , 2014, The 23rd IEEE International Symposium on Robot and Human Interactive Communication.

[19]  Tom Bylander,et al.  The Computational Complexity of Propositional STRIPS Planning , 1994, Artif. Intell..

[20]  Jussi Rintanen,et al.  Planning as satisfiability: Heuristics , 2012, Artif. Intell..

[21]  Roman Manevich,et al.  TVLA: A system for generating abstract interpreters , 2004, IFIP Congress Topical Sessions.

[22]  Hector Muñoz-Avila,et al.  Learning Hierarchical Task Models from Input Traces , 2016, Comput. Intell..

[23]  Tom M. Mitchell,et al.  Explanation-Based Generalization: A Unifying View , 1986, Machine Learning.

[24]  Shmuel Sagiv,et al.  TVLA: A System for Implementing Static Analyses , 2000, SAS.

[25]  Jianwei Zhang,et al.  The RACE Project , 2014, KI - Künstliche Intelligenz.