UCL logo

UCL Discovery

UCL home » Library Services » Electronic resources » UCL Discovery

Autonomous Navigation and Landing of Airliners Using Artificial Neural Networks and Learning by Imitation

Baomar, HAO; Bentley, PJ; (2017) Autonomous Navigation and Landing of Airliners Using Artificial Neural Networks and Learning by Imitation. In: (Proceedings) 2017 IEEE Symposium Series on Computational Intelligence (SSCI). (In press).

[img] Text
RP3 Final.pdf - ["content_typename_Accepted version" not defined]
Access restricted to UCL open access staff until 14 May 2018.

Download (1MB)

Abstract

We introduce the Intelligent Autopilot System (IAS) which is capable of autonomous navigation and landing of large jets such as airliners by observing and imitating human pilots using Artificial Neural Networks and Learning by Imitation. The IAS is a potential solution to the current problem of Automatic Flight Control Systems of being unable to perform full flights that start with takeoff from a given airport, and end with landing in another. A navigation technique, and a robust Learning by Imitation approach are proposed. Learning by Imitation uses human pilots to demonstrate the task to be learned in a flight simulator while training datasets are captured from these demonstrations. The datasets are then used by Artificial Neural Networks to generate control models automatically. The control models imitate the skills of the human pilot when banking to navigate between waypoints, and when performing final approach and landing, while a flight manager program generates the flight course, and decides which ANNs to be fired given the current flight phase. Experiments show that, even after being presented with limited examples, the IAS can handle such flight tasks with high accuracy. The proposed IAS is a novel approach towards achieving full control autonomy of large jets using ANN models that match the skills and abilities of experienced human pilots.

Type: Proceedings paper
Title: Autonomous Navigation and Landing of Airliners Using Artificial Neural Networks and Learning by Imitation
Event: 2017 IEEE Symposium Series on Computational Intelligence (SSCI)
Location: Hawaii, USA
Dates: 27 November 2017 - 01 December 2017
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL > School of BEAMS
UCL > School of BEAMS > Faculty of Engineering Science
URI: http://discovery.ucl.ac.uk/id/eprint/1574498
Downloads since deposit
1Download
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item