Tustin neural networks: a class of recurrent nets for adaptive MPC of mechanical systems

by   Simone Pozzoli, et al.

The use of recurrent neural networks to represent the dynamics of unstable systems is difficult due to the need to properly initialize their internal states, which in most of the cases do not have any physical meaning, consequent to the non-smoothness of the optimization problem. For this reason, in this paper focus is placed on mechanical systems characterized by a number of degrees of freedom, each one represented by two states, namely position and velocity. For these systems, a new recurrent neural network is proposed: Tustin-Net. Inspired by second-order dynamics, the network hidden states can be straightforwardly estimated, as their differential relationships with the measured states are hardcoded in the forward pass. The proposed structure is used to model a double inverted pendulum and for model-based Reinforcement Learning, where an adaptive Model Predictive Controller scheme using the Unscented Kalman Filter is proposed to deal with parameter changes in the system.


page 1

page 2

page 3

page 4


Observer-Feedback-Feedforward Controller Structures in Reinforcement Learning

The paper proposes the use of structured neural networks for reinforceme...

State-Denoised Recurrent Neural Networks

Recurrent neural networks (RNNs) are difficult to train on sequence proc...

Estimating Forces of Robotic Pouring Using a LSTM RNN

In machine learning, it is very important for a robot to be able to esti...

Visualizing RNN States with Predictive Semantic Encodings

Recurrent Neural Networks are an effective and prevalent tool used to mo...

Physical Modeling using Recurrent Neural Networks with Fast Convolutional Layers

Discrete-time modeling of acoustic, mechanical and electrical systems is...

About Learning in Recurrent Bistable Gradient Networks

Recurrent Bistable Gradient Networks are attractor based neural networks...

A Recurrent Neural Network Approach to Roll Estimation for Needle Steering

Steerable needles are a promising technology for delivering targeted the...

Please sign up or login with your details

Forgot password? Click here to reset