Performance analysis of a vision only sense and avoid system for small UAVs

Bálint Vanek, Tamás Péni, A. Zarándy, József Bokorx, Tamás Zsedrovits, T. Roska

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Citations (Scopus)

Abstract

This paper investigates the real world feasibility of a purely vision based sense and avoid system, required for small unmanned aerial vehicles (UAV) to routinely access the national airspace. No information is exchanged between aircraft, only passive 2-D vision information is available to estimate the encountering traffic. The viability of the system is demonstrated on several estimation approaches, using Extended Kalman filter (EKF) and Unscented Kalman filter (UKF) implementations. Since it is shown that for certain type of observer movements the estimation process remains unobservable in bearings-only problems, the sensitivity of the estimation performance with respect to the self motion of the own craft is investigated. The system is tested on a high fidelity Hardware-in-the-Loop (HIL) simulation platform, where fight control algorithms, scene rendering, image processing and estimation algorithms are implemented individually over a network of computers with special emphasis on parallel implementation of computationally intensive tasks. Representative encounter scenarios are presented to provide performance measures, including detection time and miss distance of distinctive approaches to assess the applicability of the results.

Original languageEnglish
Title of host publicationAIAA Guidance, Navigation, and Control Conference 2011
Publication statusPublished - 2011
EventAIAA Guidance, Navigation and Control Conference 2011 - Portland, OR, United States
Duration: Aug 8 2011Aug 11 2011

Other

OtherAIAA Guidance, Navigation and Control Conference 2011
CountryUnited States
CityPortland, OR
Period8/8/118/11/11

Fingerprint

Unmanned aerial vehicles (UAV)
Bearings (structural)
Extended Kalman filters
Kalman filters
Image processing
Aircraft
Hardware

ASJC Scopus subject areas

  • Aerospace Engineering
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Vanek, B., Péni, T., Zarándy, A., Bokorx, J., Zsedrovits, T., & Roska, T. (2011). Performance analysis of a vision only sense and avoid system for small UAVs. In AIAA Guidance, Navigation, and Control Conference 2011

Performance analysis of a vision only sense and avoid system for small UAVs. / Vanek, Bálint; Péni, Tamás; Zarándy, A.; Bokorx, József; Zsedrovits, Tamás; Roska, T.

AIAA Guidance, Navigation, and Control Conference 2011. 2011.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Vanek, B, Péni, T, Zarándy, A, Bokorx, J, Zsedrovits, T & Roska, T 2011, Performance analysis of a vision only sense and avoid system for small UAVs. in AIAA Guidance, Navigation, and Control Conference 2011. AIAA Guidance, Navigation and Control Conference 2011, Portland, OR, United States, 8/8/11.
Vanek B, Péni T, Zarándy A, Bokorx J, Zsedrovits T, Roska T. Performance analysis of a vision only sense and avoid system for small UAVs. In AIAA Guidance, Navigation, and Control Conference 2011. 2011
Vanek, Bálint ; Péni, Tamás ; Zarándy, A. ; Bokorx, József ; Zsedrovits, Tamás ; Roska, T. / Performance analysis of a vision only sense and avoid system for small UAVs. AIAA Guidance, Navigation, and Control Conference 2011. 2011.
@inproceedings{ecc013fc89494dafb2892ab711f71655,
title = "Performance analysis of a vision only sense and avoid system for small UAVs",
abstract = "This paper investigates the real world feasibility of a purely vision based sense and avoid system, required for small unmanned aerial vehicles (UAV) to routinely access the national airspace. No information is exchanged between aircraft, only passive 2-D vision information is available to estimate the encountering traffic. The viability of the system is demonstrated on several estimation approaches, using Extended Kalman filter (EKF) and Unscented Kalman filter (UKF) implementations. Since it is shown that for certain type of observer movements the estimation process remains unobservable in bearings-only problems, the sensitivity of the estimation performance with respect to the self motion of the own craft is investigated. The system is tested on a high fidelity Hardware-in-the-Loop (HIL) simulation platform, where fight control algorithms, scene rendering, image processing and estimation algorithms are implemented individually over a network of computers with special emphasis on parallel implementation of computationally intensive tasks. Representative encounter scenarios are presented to provide performance measures, including detection time and miss distance of distinctive approaches to assess the applicability of the results.",
author = "B{\'a}lint Vanek and Tam{\'a}s P{\'e}ni and A. Zar{\'a}ndy and J{\'o}zsef Bokorx and Tam{\'a}s Zsedrovits and T. Roska",
year = "2011",
language = "English",
isbn = "9781600869525",
booktitle = "AIAA Guidance, Navigation, and Control Conference 2011",

}

TY - GEN

T1 - Performance analysis of a vision only sense and avoid system for small UAVs

AU - Vanek, Bálint

AU - Péni, Tamás

AU - Zarándy, A.

AU - Bokorx, József

AU - Zsedrovits, Tamás

AU - Roska, T.

PY - 2011

Y1 - 2011

N2 - This paper investigates the real world feasibility of a purely vision based sense and avoid system, required for small unmanned aerial vehicles (UAV) to routinely access the national airspace. No information is exchanged between aircraft, only passive 2-D vision information is available to estimate the encountering traffic. The viability of the system is demonstrated on several estimation approaches, using Extended Kalman filter (EKF) and Unscented Kalman filter (UKF) implementations. Since it is shown that for certain type of observer movements the estimation process remains unobservable in bearings-only problems, the sensitivity of the estimation performance with respect to the self motion of the own craft is investigated. The system is tested on a high fidelity Hardware-in-the-Loop (HIL) simulation platform, where fight control algorithms, scene rendering, image processing and estimation algorithms are implemented individually over a network of computers with special emphasis on parallel implementation of computationally intensive tasks. Representative encounter scenarios are presented to provide performance measures, including detection time and miss distance of distinctive approaches to assess the applicability of the results.

AB - This paper investigates the real world feasibility of a purely vision based sense and avoid system, required for small unmanned aerial vehicles (UAV) to routinely access the national airspace. No information is exchanged between aircraft, only passive 2-D vision information is available to estimate the encountering traffic. The viability of the system is demonstrated on several estimation approaches, using Extended Kalman filter (EKF) and Unscented Kalman filter (UKF) implementations. Since it is shown that for certain type of observer movements the estimation process remains unobservable in bearings-only problems, the sensitivity of the estimation performance with respect to the self motion of the own craft is investigated. The system is tested on a high fidelity Hardware-in-the-Loop (HIL) simulation platform, where fight control algorithms, scene rendering, image processing and estimation algorithms are implemented individually over a network of computers with special emphasis on parallel implementation of computationally intensive tasks. Representative encounter scenarios are presented to provide performance measures, including detection time and miss distance of distinctive approaches to assess the applicability of the results.

UR - http://www.scopus.com/inward/record.url?scp=84880606673&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84880606673&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84880606673

SN - 9781600869525

BT - AIAA Guidance, Navigation, and Control Conference 2011

ER -