UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

An Intelligent Autopilot System that Learns Flight Emergency Procedures by Imitating Human Pilots

Baomar, HAO; Bentley, PJ; (2017) An Intelligent Autopilot System that Learns Flight Emergency Procedures by Imitating Human Pilots. In: 2016 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE Green open access

[img]
Preview
Text
RP2.pdf - Accepted version

Download (1MB) | Preview

Abstract

We propose an extension to the capabiliti es of the Intelligent Autopilot System (IAS) from our previou s work, to be able to learn handling emergencies by observing and imitating human pilots. The IAS is a potential solution to th e current problem of Automatic Flight Control Systems of bein g unable to handle flight uncertainties, and the need to constr uct control models manually. A robust Learning by Imitation app roach is proposed which uses human pilots to demonstrate the task to be learned in a flight simulator while training datase ts are captured from these demonstrations. The datasets are then us ed by Artificial Neural Networks to generate control models automati cally. The control models imitate the skills of the human pilo t when handling flight emergencies including engine(s) failure or f ire, Rejected Take Off (RTO), and emergency landing, while a flig ht manager program decides which ANNs to be fired given the cu rrent condition. Experiments show that, even after being presented with limited examples, the IAS is able to handle such fl ight emergencies with high accuracy.

Type: Proceedings paper
Title: An Intelligent Autopilot System that Learns Flight Emergency Procedures by Imitating Human Pilots
Event: SSCI 2016, IEEE Symposium Series on Computational Intelligence, 6-9 December 2016, Athens, Greece
Location: Athens, Greece
Dates: 06 December 2016 - 09 December 2016
ISBN-13: 9781509042418
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/SSCI.2016.7849881
Publisher version: https://doi.org/10.1109/SSCI.2016.7849881
Language: English
Additional information: © 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Keywords: Artificial neural networks, Training, Aerospace control, Circuit faults, Databases, Fires, Data collection
UCL classification: UCL > Provost and Vice Provost Offices
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/1520870
Downloads since deposit
242Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item