Litcius/Paper detail

Long-Horizon Planning and Execution With Functional Object-Oriented Networks

David Paulius, Alejandro Agostini, Dongheui Lee

2023IEEE Robotics and Automation Letters11 citationsDOI

Abstract

Following work on joint object-action representations, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">functional object-oriented networks</i> (FOON) were introduced as a knowledge graph representation for robots. A FOON contains symbolic concepts useful to a robot's understanding of tasks and its environment for <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">object-level planning</i> . Prior to this work, little has been done to show how plans acquired from FOON can be executed by a robot, as the concepts in a FOON are too abstract for execution. We thereby introduce the idea of exploiting object-level knowledge as a FOON for task planning and execution. Our approach automatically transforms FOON into PDDL and leverages off-the-shelf planners, action contexts, and robot skills in a hierarchical planning pipeline to generate executable task plans. We demonstrate our entire approach on long-horizon tasks in CoppeliaSim and show how learned action contexts can be extended to never-before-seen scenarios.

Topics & Concepts

ExecutableComputer scienceTask (project management)Object (grammar)Pipeline (software)RobotArtificial intelligenceAction (physics)Representation (politics)Knowledge representation and reasoningProgramming languageHuman–computer interactionPolitical sciencePoliticsEconomicsManagementPhysicsLawQuantum mechanicsAI-based Problem Solving and PlanningRobot Manipulation and LearningReinforcement Learning in Robotics