Model-Based Meta-Reinforcement Learning for Flight With Suspended Payloads

Transporting suspended payloads is challenging for autonomous aerial vehicles because the payload can cause significant and unpredictable changes to the robot's dynamics. These changes can lead to suboptimal flight performance or even catastrophic failure. Although adaptive control and learning...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE robotics and automation letters Jg. 6; H. 2; S. 1471 - 1478
Hauptverfasser: Belkhale, Suneel, Li, Rachel, Kahn, Gregory, McAllister, Rowan, Calandra, Roberto, Levine, Sergey
Format: Journal Article
Sprache:Englisch
Veröffentlicht: IEEE 01.04.2021
Schlagworte:
Adaptation models
Data models
Heuristic algorithms
Machine learning for robot control
Mathematical model
Payloads
probabilistic inference
reinforcement learning
Robots
Task analysis
ISSN:2377-3766, 2377-3766
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Transporting suspended payloads is challenging for autonomous aerial vehicles because the payload can cause significant and unpredictable changes to the robot's dynamics. These changes can lead to suboptimal flight performance or even catastrophic failure. Although adaptive control and learning-based methods can in principle adapt to changes in these hybrid robot-payload systems, rapid mid-flight adaptation to payloads that have a priori unknown physical properties remains an open problem. We propose a meta-learning approach that "learns how to learn" models of altered dynamics within seconds of post-connection flight data. Our experiments demonstrate that our online adaptation approach outperforms non-adaptive methods on a series of challenging suspended payload transportation tasks. Videos and other supplemental material are available on our website: https://sites.google.com/view/meta-rl-for-flight
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2021.3057046