Ali Punjani and Pieter Abbeel

EECS Department, University of California, Berkeley

Technical Report No. UCB/EECS-2014-219

December 16, 2014

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2014/EECS-2014-219.pdf

We consider the problem of system identification of helicopter dynamics. Helicopters are complex systems, coupling rigid body dynamics with aerodynamics, engine dynamics, vibration, and other phenomena. Resultantly, they pose a challenging system identification problem, especially when considering non-stationary flight regimes.

We pose the dynamics modeling problem as direct high-dimensional regression, and take inspiration from recent results in Deep Learning to represent the helicopter dynamics with a Rectified Linear Unit (ReLU) Network Model, a hierarchical neural network model. We provide a simple method for initializing the parameters of the model, and optimization details for training. We describe three baseline models and show that they are significantly outperformed by the ReLU Network Model in experiments on real data, indicating the power of the model to capture useful structure in system dynamics across a rich array of aerobatic maneuvers. Specifically, the ReLU Network Model improves 58\% overall in RMS acceleration prediction over state-of-the-art methods. Predicting acceleration along the helicopter's up-down axis is empirically found to be the most difficult, and the ReLU Network Model improves by 60\% over the prior state-of-the-art. We discuss explanations of these performance gains, and also investigate the impact of hyperparameters in the novel model.

Advisors: Pieter Abbeel

---

BibTeX citation:

@mastersthesis{Punjani:EECS-2014-219,
    Author= {Punjani, Ali and Abbeel, Pieter},
    Title= {Machine Learning for Helicopter Dynamics Models},
    School= {EECS Department, University of California, Berkeley},
    Year= {2014},
    Month= {Dec},
    Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2014/EECS-2014-219.html},
    Number= {UCB/EECS-2014-219},
    Abstract= {We consider the problem of system identification of
helicopter dynamics.  Helicopters are complex systems,
coupling rigid body dynamics with aerodynamics, engine
dynamics, vibration, and other phenomena.  Resultantly,
they pose a challenging system identification problem,
especially when considering non-stationary flight regimes.

We pose the dynamics modeling problem as direct
high-dimensional regression, and take inspiration from
recent results in Deep Learning to represent the helicopter
dynamics with a Rectified Linear Unit (ReLU) Network Model,
a hierarchical neural network model. We provide a simple
method for initializing the parameters of the model, and
optimization details for training. We describe three
baseline models and show that they are significantly
outperformed by the ReLU Network Model in experiments on
real data, indicating the power of the model to capture
useful structure in system dynamics across a rich array of
aerobatic maneuvers.  Specifically, the ReLU Network Model
improves 58\% overall in RMS acceleration prediction over
state-of-the-art methods. Predicting acceleration along the
helicopter's up-down axis is empirically found to be the
most difficult, and the ReLU Network Model improves by 60\%
over the prior state-of-the-art. We discuss explanations of
these performance gains, and also investigate the impact of
hyperparameters in the novel model.},
}

EndNote citation:

%0 Thesis
%A Punjani, Ali 
%A Abbeel, Pieter 
%T Machine Learning for Helicopter Dynamics Models
%I EECS Department, University of California, Berkeley
%D 2014
%8 December 16
%@ UCB/EECS-2014-219
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2014/EECS-2014-219.html
%F Punjani:EECS-2014-219