Geri Dön

Multi-target tracking for swarm vs. swarm UAV systems

Başlık çevirisi mevcut değil.

  1. Tez No: 401787
  2. Yazar: ÜMİT SOYLU
  3. Danışmanlar: DR. TIMOTHY H. CHUNG
  4. Tez Türü: Yüksek Lisans
  5. Konular: Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrol, Havacılık ve Uzay Mühendisliği, Bilim ve Teknoloji, Computer Engineering and Computer Science and Control, Aeronautical Engineering, Science and Technology
  6. Anahtar Kelimeler: Belirtilmemiş.
  7. Yıl: 2012
  8. Dil: İngilizce
  9. Üniversite: The Naval Postgraduate School
  10. Enstitü: Yurtdışı Enstitü
  11. Ana Bilim Dalı: Bilgisayar Bilimleri Ana Bilim Dalı
  12. Bilim Dalı: Belirtilmemiş.
  13. Sayfa Sayısı: Belirtilmemiş.

Özet

Özet yok.

Özet (Çeviri)

Unmanned systems, including unmanned aerial vehicles (UAVs), are increasingly critical developing technologies. The advantage of preventing human causalities makes unmanned systems demanding technologies of near future. Given the development of unmanned systems worldwide, swarm vs. swarm UAV conflicts are probable near future scenario. For swarms to succeed, the common operational picture (COP) of each members must be accurate. This paper proposes methods for generating a COP for each member of the swarm. There exists different methodologies applicable to different parts of the problem. These methodologies are evaluated according to the accuracy of the generated COP for each agent. A simulation is generated for testing realistic scenarios and providing statistical analysis of COP accuracy. The simulation is capable of generating swarm vs. swarm systems and generating statistics for each UAV in the swarm. In this paper, we assume that UAVs are in the air, have knowledge of opposing force members and can share their knowledge with swarm members via networking. The simulation generates detections according to the targets in the environments and uses Gaussian and uniform distributions. Both occlusions of the agents and possibilities for false detections are implemented. The simulation is flexible and allows different scenarios with different parameter sets. The affects of false detections are investigated. There exists predetermined simulation borders and agents bounce back from these borders. Also, agents move randomly. The results shows the efficiency and drawbacks of different methodologies applied. The future works section discuss possible improvements for generating more accurate COP, associating targets in discrete time steps, and factoring network constraints into COP generation.

Benzer Tezler

  1. Çoklu amaçların çözümlemesinde amaç programlaması ile genelleştirilmiş ters yaklaşımı ve yem sanayiinde bir uygulama

    Goal programming and generalieed inverse approaches in the multi-objective analysis and application in feed industry

    HASAN BAL

    Doktora

    Türkçe

    Türkçe

    1986

    İstatistikGazi Üniversitesi

    İstatistik Ana Bilim Dalı

    DOÇ. DR. FEVZİ KUTAY

  2. Oditoryumlarda akustik önlemler ve çoklu kullanım

    Accoustical precautions and milti purpose usage of auditorums

    ÇİĞDEM YÜCEL

    Yüksek Lisans

    Türkçe

    Türkçe

    1987

    MimarlıkGazi Üniversitesi

    Mimarlık Ana Bilim Dalı

    DOÇ.DR. MUTBUL KAYILI

  3. Çok bileşenli distilasyon sistemlerinin optimal dizilişinin sentezi

    Synthesis of optimum sequencing of multicomponent distillatron systems

    İRFAN AR

    Yüksek Lisans

    Türkçe

    Türkçe

    1987

    KimyaGazi Üniversitesi

    Kimya Mühendisliği Ana Bilim Dalı

    YRD. DOÇ. DR. AHMET BİÇER