A Framework for Robot Self-Assessment of Expected Task Performance

We propose a self-assessment framework which enables a robot to estimate how well it will be able to perform a known or possibly novel task. The robot simulates the task to generate a state distribution of possible outcomes and determines (1) the likelihood of overall success, (2) the most probable...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE robotics and automation letters Jg. 7; H. 4; S. 1 - 8
Hauptverfasser: Frasca, Tyler, Scheutz, Matthias
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Piscataway IEEE 01.10.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Human-robot interaction
Human-Robot Teaming
Methods and Tools for Robot System Design
Navigation
Predictive models
Probability distribution
Robot sensing systems
Robots
Self assessment
Simulation and Animation
Symbols
Task analysis
ISSN:2377-3766, 2377-3766
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We propose a self-assessment framework which enables a robot to estimate how well it will be able to perform a known or possibly novel task. The robot simulates the task to generate a state distribution of possible outcomes and determines (1) the likelihood of overall success, (2) the most probable failure location, and (3) the expected time to task completion. We evaluate the framework on the "FetchIt!" mobile manipulation challenge which requires the robot to fetch a variety of parts around a small enclosed arena. By comparing the simulated and actual task resulting state distributions, we show that the robot can effectively assess its expected performance which can be communicated to humans.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2022.3219024