Safety-Critical Control with Offline-Online Neural Network Inference

TL;DR

This paper introduces a safety-critical control framework that combines offline and online neural network inference with adaptive uncertainty quantification to ensure safe navigation of an ego agent among others.

Contribution

It proposes a novel RBFNN-based inference method with online adaptation and conformal prediction for uncertainty quantification integrated into CBF-based safety control.

Findings

Effective inference of other agents' dynamics demonstrated in simulations.

Enhanced safety guarantees with probabilistic confidence levels.

Online adaptation improves generalization without persistent excitation.

Abstract

This paper presents a safety-critical control framework for an ego agent moving among other agents. The approach infers the dynamics of the other agents, and incorporates the inferred quantities into the design of control barrier function (CBF)-based controllers for the ego agent. The inference method combines offline and online learning with radial basis function neural networks (RBFNNs). The RBFNNs are initially trained offline using collected datasets. To enhance the generalization of the RBFNNs, the weights are then updated online with new observations, without requiring persistent excitation conditions in order to enhance the applicability of the method. Additionally, we employ adaptive conformal prediction to quantify the estimation error of the RBFNNs for the other agents' dynamics, generating prediction sets to cover the true value with high probability. Finally, we formulate a CBF-based controller for the ego agent to guarantee safety with the desired confidence level by accounting for the prediction sets of other agents' dynamics in the sampled-data CBF conditions. Simulation results are provided to demonstrate the effectiveness of the proposed method.