Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


41586.pdf (2.03 MB)

ETD Abstract Container

Abstract Header

Physics-Based Neural Networks for Modeling & Control of Aerial Vehicles

Breese, Bennett
http://rave.ohiolink.edu/etdc/view?acc_num=ucin1637052823504954

Abstract Details

2021, MS, University of Cincinnati, Engineering and Applied Science: Aerospace Engineering.
In recent years artificial intelligence (AI) and machine learning techniques have found immense success in the fields of pattern recognition, classification, and data analytics. These techniques also have shown to provide viable means of controlling and modeling of uncertain, nonlinear dynamic systems. However, such techniques have not yet found widespread adoption in controls due to concerns in reliability, interpretability, and stability. In the past, much of the work in the field of dynamics and controls has been based on well understood physical principles (i.e., Newtonian, Lagrangian, and Hamiltonian mechanics), as they adequately address the aforementioned concerns. The presented work attempts to retain the benefits of both AI and physics-based control, by using recently developed neural networks that incorporate Lagrangian mechanics into the learning scheme to create an inverse dynamic model of a quadcopter. Inverse dynamic model is utilized in developing a control scheme that is shown to be able to learn the changes in system parameters effectively in an online fashion. The proposed control scheme is validated with the help of extensive simulation studies performed on a quadcopter , and the performance is compared to traditional controllers for cases where mass changes in-flight for complex trajectories.
Manish Kumar, Ph.D. (Committee Chair)
Prashant Khare (Committee Member)
David Casbeer, Ph.D. (Committee Member)
Michael Bolender, Ph.D. (Committee Member)
52 p.
Aerospace Materials
Neural Network; Machine Learning; Physics; Quadcopter; Control; Modeling

Recommended Citations

Citations

  • Breese, B. (2021). Physics-Based Neural Networks for Modeling & Control of Aerial Vehicles [Master's thesis, University of Cincinnati]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1637052823504954

    APA Style (7th edition)

  • Breese, Bennett. Physics-Based Neural Networks for Modeling & Control of Aerial Vehicles. 2021. University of Cincinnati, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=ucin1637052823504954.

    MLA Style (8th edition)

  • Breese, Bennett. "Physics-Based Neural Networks for Modeling & Control of Aerial Vehicles." Master's thesis, University of Cincinnati, 2021. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1637052823504954

    Chicago Manual of Style (17th edition)

ucin1637052823504954
470
© 2020, all rights reserved.
This open access ETD is published by University of Cincinnati and OhioLINK.