Geri Dön

Pilot demonstration based reinforcement learning with application to low speed airship control

Başlık çevirisi mevcut değil.

PDF İndir

  1. Tez No: 602219
  2. Yazar: ONUR DAŞKIRAN
  3. Danışmanlar: PROF. ATİLLA DOĞAN, PROF. BRIAN HUFF
  4. Tez Türü: Doktora
  5. Konular: Uçak Mühendisliği, Havacılık ve Uzay Mühendisliği, Aeronautical Engineering, Aeronautical Engineering
  6. Anahtar Kelimeler: Belirtilmemiş.
  7. Yıl: 2016
  8. Dil: İngilizce
  9. Üniversite: The Unıversıty Of Texas At Arlıngton
  10. Enstitü: Yurtdışı Enstitü
  11. Ana Bilim Dalı: Belirtilmemiş.
  12. Bilim Dalı: Belirtilmemiş.
  13. Sayfa Sayısı: Belirtilmemiş.

Özet

Özet yok.

Özet (Çeviri)

Designing control systems for airship has unique challenges as compared to conventional aircraft. Highly nonlinear dynamics, di erent mass/inertia relations, vast uncertainties in the model parameters and underactuation are the main reasons behind this. Airship dynamics is greatly in uenced by the variations in the environmental (e.g., room temperature) and internal (e.g.,helium distribution in en- velope) factors that can completely change the response characteristics of the blimp and make it infeasible for a model-based controller to perform. On the other hand, a skilled RC pilot can operate the manual ight easily under these conditions. This makes LfD (learning from demonstration) and RL (reinforcement learning) techniques suitable candidates to address the issues that model-based control design fails to do. In general, LfD covers the methods that aim to learn a control policy directly from the previously provided expert demonstrations. In reinforcement learning, it is aimed to reach an optimal policy through trial and error while a reward function continuously describes whether the action taken in a speci c state creates good or bad outcome. iv This dissertation research develops a three stage LfD/RL method which uses continuous multi-dimensional states and actions. Stages and subroutines used in the method is rst explained in detail, then implemented on three simple example cases to show the performance and the convergence characteristics of exploration using discrete and continuous state-action spaces. The method is used for learning and executing 1D and 2D waypoint navigation tasks of a ground vehicle (UGV) for both simulation and hardware implementation. In order to apply the method to the motion of a low speed airship, a realistic airship ight simulator is designed by performing measurements and tests and pilot demonstrations are recorded with this simulator. Finally, the method used to learn and execute commanded position and orientation tasks demonstrated by the pilot, similar undemonstrated tasks and a case when these tasks are combined to represent a full mission. It is shown that selection of correct function approximator parameters are crucial in order to obtain satisfactory response when LfD/RL method is used.

Benzer Tezler

  1. Tez No

    605809

    A model based flight control system design approach for micro aerial vehicles using integrated flight testing and hil simulations

    Küçük boyutlu insansız hava araçları üzerinde sistem tanılama, uçuş kontrol sistem tasarımı ve donanım ile benzetim uygulamaları

    BURAK YÜKSEK

    Doktora

    İngilizce

    İngilizce

    2019

    Uçak Mühendisliğiİstanbul Teknik Üniversitesi

    Mekatronik Mühendisliği Ana Bilim Dalı

    PROF. DR. GÖKHAN İNALHAN

  2. Tez No

    434248

    Performance evaluations of single mode optical receiver for degraded visual field and photonic lantern based coherent detection

    Bozulmuş görsel alan ve fotonik fener tabanlı eş fazlı algılama için tek modlu optik alıcı performans değerlendirmesi

    ABDULLAH ORAN

    Yüksek Lisans

    İngilizce

    İngilizce

    2016

    Elektrik ve Elektronik MühendisliğiAbdullah Gül Üniversitesi

    Elektrik-Elektronik Mühendisliği Ana Bilim Dalı

    DOÇ. DR. İBRAHİM TUNA ÖZDÜR

    PROF. DR. EKMEL ÖZBAY

  3. Tez No

    318728

    Temel kimya laboratuvarı dersinin Web ortamı ile desteklenmesinin öğrencilerin başarısına ve derse yönelik tutumuna etkisi

    The effect of the Web to students success and attitude on the basic chemistry lesson

    DUYGU BİLEN KAYA

    Doktora

    Türkçe

    Türkçe

    2012

    KimyaDicle Üniversitesi

    Kimya Ana Bilim Dalı

    DOÇ. DR. BEHÇET ORAL

    PROF. DR. GİRAY TOPAL

  4. Tez No

    906108

    Çok kriterli karar verme ve hedef programlama ile eğitim uçağı seçimi

    Selection of training aircraft by multi-criteria decision making and goal programming

    ÖZGENUR YILMAZ

    Yüksek Lisans

    Türkçe

    Türkçe

    2024

    Endüstri ve Endüstri MühendisliğiGazi Üniversitesi

    Endüstri Mühendisliği Ana Bilim Dalı

    PROF. DR. MEHMET KABAK

  5. Tez No

    95799

    Harran ovasında karık ve damla sulama sistemlerinin ekonomik yönden karşılaştırılması

    Economical comparison of furrow and drip irrigation systems in Harran plain

    GONCA KARACA

    Yüksek Lisans

    Türkçe

    Türkçe

    2000

    ZiraatAnkara Üniversitesi

    Tarımsal Yapılar ve Sulama Ana Bilim Dalı

    DOÇ. DR. M. FATİH SELENAY

Geri Dön