Affordance Template Registration via Human-in-the-loop Corrections

Affordance Templates (ATs) are a method for parameterizing objects for autonomous robot manipulations. In this approach, instances of an object are registered by positioning a model in a 3D environment, which requires a large amount of user input. We instead propose a registration method which combi...

Full description

Saved in:
Bibliographic Details
Main Authors Hagenow, Michael, Zinn, Michael, Fong, Terrence, Laske, Evan, Hambuchen, Kimberly
Format Journal Article
LanguageEnglish
Published 28.09.2021
Subjects
Computer Science - Robotics
Online AccessGet full text

Cover

More Information
Summary:Affordance Templates (ATs) are a method for parameterizing objects for autonomous robot manipulations. In this approach, instances of an object are registered by positioning a model in a 3D environment, which requires a large amount of user input. We instead propose a registration method which combines autonomy and user corrections. For selected objects, the system determines both the model and corresponding pose autonomously. The user makes corrections only if the model or pose is incorrect. This method increases the level of autonomy compared to existing approaches which can reduce user input and time on task. In this paper, we present an overview of existing methods, a description of our method, preliminary results, and planned future work.
DOI:10.48550/arxiv.2109.13649