# Towards a Framework to Manage Perceptual Uncertainty for Safe Automated Driving

## TL;DR

This paper discusses the importance of perceptual uncertainty in autonomous vehicle perception, proposing a framework to measure and control it to enhance safety in ML-based perception systems.

## Contribution

It introduces a novel framework for quantifying and managing perceptual uncertainty in autonomous vehicle perception systems, linking it to safety requirements.

## Key findings

- Perceptual uncertainty is a key safety performance measure.
- Factors influencing perceptual uncertainty are identified.
- A preliminary framework for managing uncertainty is proposed.

## Abstract

Perception is a safety-critical function of autonomous vehicles and machine learning (ML) plays a key role in its implementation. This position paper identifies (1) perceptual uncertainty as a performance measure used to define safety requirements and (2) its influence factors when using supervised ML. This work is a first step towards a framework for measuring and controling the effects of these factors and supplying evidence to support claims about perceptual uncertainty.