Uncertainty Quantification with Statistical Guarantees in End-to-End Autonomous Driving Control

TL;DR

This paper develops a framework for quantifying and calibrating uncertainty in Bayesian neural network controllers for autonomous driving, providing safety guarantees and aiding decision making.

Contribution

It introduces a method to compute real-time uncertainty measures with statistical guarantees and estimates collision probabilities in autonomous driving scenarios.

Findings

Uncertainty measures can be computed in real time with statistical guarantees.

Calibrated uncertainty estimates improve collision avoidance decisions.

Bayesian inference methods vary in uncertainty estimation quality.

Abstract

Deep neural network controllers for autonomous driving have recently benefited from significant performance improvements, and have begun deployment in the real world. Prior to their widespread adoption, safety guarantees are needed on the controller behaviour that properly take account of the uncertainty within the model as well as sensor noise. Bayesian neural networks, which assume a prior over the weights, have been shown capable of producing such uncertainty measures, but properties surrounding their safety have not yet been quantified for use in autonomous driving scenarios. In this paper, we develop a framework based on a state-of-the-art simulator for evaluating end-to-end Bayesian controllers. In addition to computing pointwise uncertainty measures that can be computed in real time and with statistical guarantees, we also provide a method for estimating the probability that, given a scenario, the controller keeps the car safe within a finite horizon. We experimentally evaluate the quality of uncertainty computation by several Bayesian inference methods in different scenarios and show how the uncertainty measures can be combined and calibrated for use in collision avoidance. Our results suggest that uncertainty estimates can greatly aid decision making in autonomous driving.