Use of deterministic AI and a multi-user virtual test environment for drone inspection mission safety

Hirad Goudarzi; Conor Marsh; Arthur G Richards; William Crowther; Ben Parslew

doi:10.31256/Vv1Jg2J

Use of deterministic AI and a multi-user virtual test environment for drone inspection mission safety

Hirad Goudarzi^*
, Conor Marsh (Contributor)
, Arthur G Richards
, William Crowther
, Ben Parslew

^*Corresponding author for this work

Research output: Contribution to conference › Conference Paper › peer-review

Abstract

One of the major challenges of integrating AI in UAV control is the ability of the pilot to effectively interact with the system. Inspired by process-control and vigilance devices, this work employs a predictable and deterministic form of AI to enable single-crew (i.e. pilot) operation in an unconstrained dynamic environment. A multi-user simulation environment was developed in Unity to validate the mission and to train and evaluate pilot-automation interactions. Preliminary simulation results for an inspection case study at the Clifton Suspension Bridge are reported.

Original language	English
Pages	24
Number of pages	25
DOIs	https://doi.org/10.31256/Vv1Jg2J
Publication status	Published - 2022
Event	UKRAS22 Conference “Robotics for Unconstrained Environments” Proceedings - Aberystwyth University Duration: 26 Aug 2022 → …

Conference

Conference	UKRAS22 Conference “Robotics for Unconstrained Environments” Proceedings
Period	26/08/22 → …

Access to Document

10.31256/Vv1Jg2J

Handle.net

Persistent link

CASCADE: Complex Autonomous aircraft Systems Configuration, Analysis and Design Exploratory
Richards, A. G. (Principal Investigator), Richardson, T. S. (Co-Investigator), Goudarzi, H. (Student), Upadhyay, S. (Researcher) & Hine, D. (Technician)
1/02/18 → 31/10/23
Project: Research

Cite this

@conference{68cfa1de5b6941bb97405295da09a060,

title = "Use of deterministic AI and a multi-user virtual test environment for drone inspection mission safety",

abstract = "One of the major challenges of integrating AI in UAV control is the ability of the pilot to effectively interact with the system. Inspired by process-control and vigilance devices, this work employs a predictable and deterministic form of AI to enable single-crew (i.e. pilot) operation in an unconstrained dynamic environment. A multi-user simulation environment was developed in Unity to validate the mission and to train and evaluate pilot-automation interactions. Preliminary simulation results for an inspection case study at the Clifton Suspension Bridge are reported.",

author = "Hirad Goudarzi and Conor Marsh and Richards, \{Arthur G\} and William Crowther and Ben Parslew",

year = "2022",

doi = "10.31256/Vv1Jg2J",

language = "English",

pages = "24",

note = "UKRAS22 Conference “Robotics for Unconstrained Environments” Proceedings ; Conference date: 26-08-2022",

}

TY - CONF

T1 - Use of deterministic AI and a multi-user virtual test environment for drone inspection mission safety

AU - Goudarzi, Hirad

AU - Richards, Arthur G

AU - Crowther, William

AU - Parslew, Ben

A2 - Marsh, Conor

PY - 2022

Y1 - 2022

N2 - One of the major challenges of integrating AI in UAV control is the ability of the pilot to effectively interact with the system. Inspired by process-control and vigilance devices, this work employs a predictable and deterministic form of AI to enable single-crew (i.e. pilot) operation in an unconstrained dynamic environment. A multi-user simulation environment was developed in Unity to validate the mission and to train and evaluate pilot-automation interactions. Preliminary simulation results for an inspection case study at the Clifton Suspension Bridge are reported.

AB - One of the major challenges of integrating AI in UAV control is the ability of the pilot to effectively interact with the system. Inspired by process-control and vigilance devices, this work employs a predictable and deterministic form of AI to enable single-crew (i.e. pilot) operation in an unconstrained dynamic environment. A multi-user simulation environment was developed in Unity to validate the mission and to train and evaluate pilot-automation interactions. Preliminary simulation results for an inspection case study at the Clifton Suspension Bridge are reported.

U2 - 10.31256/Vv1Jg2J

DO - 10.31256/Vv1Jg2J

M3 - Conference Paper

SP - 24

T2 - UKRAS22 Conference “Robotics for Unconstrained Environments” Proceedings

Y2 - 26 August 2022

ER -

Use of deterministic AI and a multi-user virtual test environment for drone inspection mission safety

Abstract

Conference

Access to Document

Handle.net

Fingerprint

Projects

CASCADE: Complex Autonomous aircraft Systems Configuration, Analysis and Design Exploratory

Cite this