Towards an architecture for discovering domain dynamics: affordances, causal laws, and executability conditions

Mohan Sridharan, Ben Meadows

Research output: Chapter in Book/Report/Conference proceedingConference contribution

33 Downloads (Pure)

Abstract

Robots assisting humans in complex domains often have to reason with different descriptions of incomplete domain knowledge. It is difficult to equip such robots with comprehensive knowledge about the domain and axioms governing
the domain dynamics. This paper presents a combined architecture that enables interactive and cumulative discovery of axioms governing action capabilities, and the preconditions and effects of actions in the domain. Specifically, Answer
Set Prolog is used to represent the incomplete domain knowledge, and to reason with this knowledge for planning and diagnostics. Unexpected outcomes observed during plan execution trigger reinforcement learning to interactively discover specific instances of previously unknown axioms and to revise the existing axioms. Furthermore, a decision tree induction approach based on the relational domain representation constructs generic versions of the discovered axioms, which are then used for subsequent reasoning. The architecture’s
capabilities are illustrated and evaluated in a simulated domain of a robot moving objects to specific places or people in an indoor domain.
Original languageEnglish
Title of host publicationInternational Workshop on Planning and Robotics (PlanRob) at the International Conference on Automated Planning and Scheduling (ICAPS 2017))
PublisherAAAI Press
Number of pages12
Publication statusPublished - 20 Jun 2017
EventInternational Workshop on Planning and Robotics (PlanRob) at ICAPS 2017 -
Duration: 20 Jun 201720 Jun 2017

Conference

ConferenceInternational Workshop on Planning and Robotics (PlanRob) at ICAPS 2017
Period20/06/1720/06/17

Fingerprint

Dive into the research topics of 'Towards an architecture for discovering domain dynamics: affordances, causal laws, and executability conditions'. Together they form a unique fingerprint.

Cite this