Abstract
Towards realising autonomous UAVs, this paper investigates one of the fundamental autonomous flying research problems, i.e., the ability of a vehicle to control its flying behaviour autonomously, without reliance on external infrastructure like Instrument Landing Systems or GPS. In this paper we experiment with a physical UAV prototype with embedded intelligent control capabilities, utilising a Long Short Term Memory (LSTM) neural network, in order to learn lift-off control sequences using self-training. The initial results are promising and show potential for embedding LSTMs in the control systems of autonomous UAVs.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Journal of Ubiquitous Systems and Pervasive Networks
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
