Learning Inverse Kinodynamics for Accurate High-Speed Off-Road Navigation on Unstructured Terrain

This letter presents a learning-based approach to consider the effect of unobservable world states in kinodynamic motion planning in order to enable accurate high-speed off-road navigation on unstructured terrain. Existing kinodynamic motion planners either operate in structured and homogeneous envi...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE robotics and automation letters Jg. 6; H. 3; S. 6054 - 6060
Hauptverfasser:	Xiao, Xuesu, Biswas, Joydeep, Stone, Peter
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Piscataway IEEE 01.07.2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Autonomous vehicle navigation High speed Indoor environments Learning machine learning for robot control motion and path planning Motion control Motion planning Navigation Planning Robots Semantics Sensors Terrain Training
ISSN:	2377-3766, 2377-3766
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!