Abstract
This paper 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 ReLU Network Model, a hierarchical neural network model.
This paper focuses on a method to learn a system dynamics model by leveraging captured state-action trajectories from expert demonstration.
Usually,the difficulties of system identification lie in three aspects:
- stochasticity in the system
- unstructured noise
- the presence of unobserved state variables (the difficulty in modeling helicopter)
Modeling systems with hidden latent state is often treated as a parameter learning problem in a graphical model.
Takens Theorem states that for a large class of nonlinear dynamical systems with d-dimensional state space, only 2d+1 previous measurements of a single system output are required to effectively reconstruct the system state.
The main contribution of this paper is proposing a novel ReLU Network Model, providing details about parameter initialization and optimization methods.
The Helicopter System
The task of system identification is to find a function F F F which maps from state-control space to state-derivative:
s ˙ = F ( s , u , θ ) \dot{s} = F(s, u, \theta) s˙=F(s,u,θ)
The helicopter state s s s is represented by a total of twelve degrees of freedom.
The control state u u