Universal Formulas for Safe Control and Their Neural Network Approximations

TL;DR

This paper introduces a neural network-based universal formula for designing smooth controllers satisfying multiple affine constraints, applicable across various control objectives like safety and stability.

Contribution

It proposes a novel neural network approximation method that provides a universal, smooth control formula independent of state dimension, simplifying controller design.

Findings

Neural network approximations can effectively represent controllers satisfying multiple affine constraints.

The proposed method reduces real-time computational burden compared to quadratic programming solutions.

Training the neural network requires data only from a bounded state space set.

Abstract

We study the problem of designing a controller that satisfies an arbitrary number of affine inequalities at every point in the state space. This is motivated by the fact that a variety of key control objectives, such as stability, safety, and input saturation, are guaranteed by closed-loop systems whose controllers satisfy such inequalities. Many works in the literature design such controllers as the solution to a state-dependent quadratic program (QP) whose constraints are precisely the inequalities. When the input dimension and number of constraints are high, computing a solution of this QP in real time can become computationally burdensome. Additionally, the solution of such optimization problems is not smooth in general, which can degrade the performance of the system. This paper provides a novel method to design a smooth controller that satisfies an arbitrary number of affine constraints. The controller is given at every state as the minimizer of a strictly convex function. To avoid computing the minimizer of such function in real time, we introduce a method based on neural networks (NN) to approximate the controller. Remarkably, this NN can be used to solve the controller design problem for any task with less than a fixed input dimension and number of affine constraints, and is completely independent of the state dimension. This is why we refer to such NN approximation as a NN-based universal formula for control. Additionally, we show that the NN-based controller only needs to be trained with datapoints from a bounded set in the state space, which significantly simplifies the training process.