Embedding human expert cognition and real-time trajectory planning in autonomous UAS
Narayan, Pritesh Praneet (2011) Embedding human expert cognition and real-time trajectory planning in autonomous UAS. PhD thesis, Queensland University of Technology.
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.
Citation countsare sourced monthly fromand citation databases.
These databases contain citations from different subsets of available publications and different time periods and thus the citation count from each is usually different. Some works are not in either database and no count is displayed. Scopus includes citations from articles published in 1996 onwards, and Web of Science® generally from 1980 onwards.
Citations counts from theindexing service can be viewed at the linked Google Scholar™ search.
Full-text downloadsdisplays the total number of times this work’s files (e.g., a PDF) have been downloaded from QUT ePrints as well as the number of downloads in the previous 365 days. The count includes downloads for all files if a work has more than one.
|Item Type:||QUT Thesis (PhD)|
|Keywords:||human expert cognition, real-time trajectory planning, autonomous UAS|
|Divisions:||Current > Research Centres > Australian Research Centre for Aerospace Automation|
Current > QUT Faculties and Divisions > Science & Engineering Faculty
|Institution:||Queensland University of Technology|
|Deposited On:||13 Aug 2012 12:36|
|Last Modified:||13 Aug 2012 14:30|
Repository Staff Only: item control page