Log In Sign Up

Stability Analysis of Complementarity Systems with Neural Network Controllers

by   Alp Aydinoglu, et al.

Complementarity problems, a class of mathematical optimization problems with orthogonality constraints, are widely used in many robotics tasks, such as locomotion and manipulation, due to their ability to model non-smooth phenomena (e.g., contact dynamics). In this paper, we propose a method to analyze the stability of complementarity systems with neural network controllers. First, we introduce a method to represent neural networks with rectified linear unit (ReLU) activations as the solution to a linear complementarity problem. Then, we show that systems with ReLU network controllers have an equivalent linear complementarity system (LCS) description. Using the LCS representation, we turn the stability verification problem into a linear matrix inequality (LMI) feasibility problem. We demonstrate the approach on several examples, including multi-contact problems and friction models with non-unique solutions.


page 1

page 2

page 3

page 4


Neural network controllers for uncertain linear systems

We consider the design of reliable neural network (NN)-based approximati...

Reachable Set Computation and Safety Verification for Neural Networks with ReLU Activations

Neural networks have been widely used to solve complex real-world proble...

Scaling Up Exact Neural Network Compression by ReLU Stability

We can compress a neural network while exactly preserving its underlying...

Training for Faster Adversarial Robustness Verification via Inducing ReLU Stability

We explore the concept of co-design in the context of neural network ver...

Stabilization of Complementarity Systems via Contact-Aware Controllers

We propose a framework for provably stable local control of multi-contac...

Real World Large Scale Recommendation Systems Reproducibility and Smooth Activations

Real world recommendation systems influence a constantly growing set of ...

Robust Optimization through Neuroevolution

We propose a method for evolving solutions that are robust with respect ...