Collaborative Learning of Hierarchical Task Networks from Demonstration and Instruction

Collaborative Learning of Hierarchical Task Networks from Demonstration and InstructionAnahita Mohseni-Kabir, Sonia Chernova and Charles RichWorcester Polytechnic Institute1Project Objectives and ContributionsMain Goal: Learning complex procedural tasks from human demonstration and instruction in the form of hierarchical task networks and applying it to car maintenance domainProject Contributions:Unified system that integrates hierarchical task networks (HTNs) and collaborative discourse theory into the learning from demonstrationLearning task model from a small number of demonstrations Generalization techniquesIntegration of mixed-initiative interaction into the learning process through question asking2Related WorkCollaborative Discourse TheoryDisco (ANSI/CEA-2018 standard) (Grosz and Sidner, 1986 and Rich et al., 2001)Learning from DemonstrationMix LfD and planning (Nicolescu and Mataric, 2003)Integrate HTN and LfD (Rybski et al., 2007)Learn from Instruction (Mohan and Laird, 2011)Learn the HTN from tasks traces (Garland et al., 2001)Segmentation (Niekum et al., 2012)Active learning (Cakmak and Thomaz, 2012)

3System Architecture4

Primitive actions

Primitive and Non-primitive actionsTask model visualizationQuestions and answersTask Structure LearningTask HierarchyTop-DownBottom-UpMix of Top-Down and Buttom-Up

Temporal ConstraintsSingle demonstrationData flow

5

System Overview6

GeneralizationInput GeneralizationPart/whole generalization

Type generalization

Merging multiple demonstrations

7

Ontology

System Overview8

Question Asking9Question TypeExampleRepeated stepsShould I(robot) execute UnscrewStud on other objects of type Stud of LFhub?Grouping stepsShould I add a new task with Unscrew and PutDown as its steps?Applicability condition of alternative recipesWhat is the applicability condition of Rotates recipe with these steps?New task nameWhat is the best name that describes this new task?Input of a taskPlease specify the input of Unscrew.Execution of one of the alternative recipesShould I achieve Rotate by executing recipe1 or recipe2?

10PerformanceTire rotation taskSix primitive actions: Unscrew, Screw, Hang, Unhang, PutDown and PickUpComplete execution of two recipes of tire rotation requires 128 stepsComplete teaching of the HTN (two recipes) on average requires 26 demonstration interactionsE.g., 15 demonstrations, 11 instructions, 11 question responses

11

Conclusion and Future WorkMake the interaction as natural as possible by making the UI and robot look like a unified systemDo user study and use the real robot instead of the simulationLearn applicability conditions and pre/postconditions of the tasksFailure detection and recovery12This work is supported in part by ONR contract N00014-13-1-0735, in collaboration with Dmitry Berenson, Jim Mainprice , Artem Gritsenko, and Daniel Miller.ReferencesBarbara J. Grosz and Candace L. Sidner. Attention, intentions, and the structure of discourse. Comput. Linguist., 12(3):175204, July 1986.Charles Rich, Candace L Sidner, and Neal Lesh. Collagen: applying collaborative discourse theory to human-computer interaction. AI Magazine, 22 (4):15, 2001.Brenna D Argall, Sonia Chernova, Manuela Veloso, and Brett Browning. A survey of robot learning from demonstration. Robotics and Autonomous Systems, 57(5):469483, 2009.Paul E Rybski, Kevin Yoon, Jeremy Stolarz, and Manuela M Veloso. Interactive robot task training through dialog and demonstration. In ACM/IEEE Int. Conf. on Human-Robot Interaction, pages 4956, 2007.

13ReferencesScott Niekum, Sarah Osentoski, George Konidaris, and Andrew G Barto. Learning and generalization of complex tasks from unstructured demonstrations. In IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, pages 52395246, 2012.Maya Cakmak and Andrea L Thomaz. Designing robot learners that ask good questions. In ACM/IEEE International Conference on Human-Robot Interaction, pages 1724. ACM, 2012.Monica N Nicolescu and Maja J Mataric. Natural methods for robot task learning: Instructive demonstrations, generalization and practice. In AAMAS, pages 241248, 2003.14Merging15