Recursive Feasibility Guided Optimal Parameter Adaptation of Differential Convex Optimization Policies for Safety-Critical Systems

TL;DR

This paper introduces a recursive feasibility guided gradient descent method to adapt parameters of quadratic program-based controllers, ensuring safety and performance in safety-critical systems with complex constraints.

Contribution

It proposes a novel bi-level optimization framework that uses sensitivity analysis and backpropagation to adapt QP parameters while guaranteeing recursive feasibility.

Findings

The method maintains QP feasibility during parameter updates.

It improves control performance over a time horizon.

The approach effectively handles multiple control barrier functions.

Abstract

Quadratic Program(QP) based state-feedback controllers, whose inequality constraints bound the rate of change of control barrier(CBFs) and lyapunov function with a class-$\mathcal{K}$ function of their values, are sensitive to the parameters of these class-$\mathcal{K}$ functions. The construction of valid CBFs, however, is not straightforward, and for arbitrarily chosen parameters of the QP, the system trajectories may enter states at which the QP either eventually becomes infeasible, or may not achieve desired performance. In this work, we pose the control synthesis problem as a differential policy whose parameters are optimized for performance over a time horizon at high level, thus resulting in a bi-level optimization routine. In the absence of knowledge of the set of feasible parameters, we develop a Recursive Feasibility Guided Gradient Descent approach for updating the parameters of QP so that the new solution performs at least as well as previous solution. By considering the dynamical system as a directed graph over time, this work presents a novel way of optimizing performance of a QP controller over a time horizon for multiple CBFs by (1) using the gradient of its solution with respect to its parameters by employing sensitivity analysis, and (2) backpropagating these as well as system dynamics gradients to update parameters while maintaining feasibility of QPs.