Learning by Cheating : An End-to-End Zero Shot Framework for Autonomous Drone Navigation

Drone End-to-end principle
DOI: 10.48550/arxiv.2111.06056 Publication Date: 2021-01-01
ABSTRACT
This paper proposes a novel framework for autonomous drone navigation through cluttered environment. Control policies are learnt in low-level environment during training and applied to complex inference. The controller the is tricked into believing that robot still when it actually navigating more presented this can be adapted reuse simple tasks. We also show used as an interpretation tool reinforcement learning algorithms.
SUPPLEMENTAL MATERIAL
Coming soon ....
REFERENCES ()
CITATIONS ()
EXTERNAL LINKS
PlumX Metrics
RECOMMENDATIONS
FAIR ASSESSMENT
Coming soon ....
JUPYTER LAB
Coming soon ....