Embedding human expert cognition and real-time trajectory planning in autonomous UAS

No Altmetrics are currently available for this publication.

Narayan, P. P. (2012) Embedding human expert cognition and real-time trajectory planning in autonomous UAS. PhD, Queensland University of Technology. Available from: http://eprints.uwe.ac.uk/18327

Full text not available from this repository.


This thesis presents a new approach to compute and optimize feasible three dimensional (3D) flight trajectories using aspects of Human Decision Making (HDM) strategies, for fixed wing Unmanned Aircraft (UA) operating in low altitude environments in the presence of real time planning deadlines. The underlying trajectory generation strategy involves the application of Manoeuvre Automaton (MA) theory to create sets of candidate flight manoeuvres which implicitly incorporate platform dynamic constraints. Feasible trajectories are formed through the concatenation of predefined flight manoeuvres in an optimized manner. During typical UAS operations, multiple objectives may exist, therefore the use of multi-objective optimization can potentially allow for convergence to a solution which better reflects overall mission requirements and HDM preferences. A GUI interface was developed to allow for knowledge capture from a human expert during simulated mission scenarios. The expert decision data captured is converted into value functions and corresponding criteria weightings using UTilite Additive (UTA) theory. The inclusion of preferences elicited from HDM decision data within an Automated Decision System (ADS) allows for the generation of trajectories which more closely represent the candidate HDM{'}s decision strategies. A novel Computationally Adaptive Trajectory Decision optimization System (CATDS) has been developed and implemented in simulation to dynamically manage, calculate and schedule system execution parameters to ensure that the trajectory solution search can generate a feasible solution, if one exists, within a given length of time. The inclusion of the CATDS potentially increases overall mission efficiency and may allow for the implementation of the system on different UAS platforms with varying onboard computational capabilities. These approaches have been demonstrated in simulation using a fixed wing UAS operating in low altitude environments with obstacles present.

Item Type: Thesis (PhD)
Uncontrolled Keywords: human expert cognition, real-time trajectory planning, autonomous UAS
Faculty/Department: Faculty of Environment and Technology > Department of Engineering Design and Mathematics
Depositing User: Dr P. Narayan
Date Deposited: 16 Jan 2013 09:23
Last Modified: 08 Oct 2018 13:04
URI: http://eprints.uwe.ac.uk/id/eprint/18327


Activity Overview
Origin of downloads

Additional statistics for this repository are available via IRStats2

Actions (login required)

View Item View Item