Failure Prediction for Autonomous Driving

TL;DR

This paper introduces a method to predict potential failures in autonomous driving models by analyzing scene difficulty, aiming to enhance safety and timely human intervention.

Contribution

It presents a novel failure prediction approach that assesses scene difficulty to foresee driving model failures, improving safety in autonomous vehicles.

Findings

Failure scores can be learned and predicted effectively.

The method improves safety by providing early failure warnings.

Scene complexity correlates with higher failure likelihood.

Abstract

The primary focus of autonomous driving research is to improve driving accuracy. While great progress has been made, state-of-the-art algorithms still fail at times. Such failures may have catastrophic consequences. It therefore is important that automated cars foresee problems ahead as early as possible. This is also of paramount importance if the driver will be asked to take over. We conjecture that failures do not occur randomly. For instance, driving models may fail more likely at places with heavy traffic, at complex intersections, and/or under adverse weather/illumination conditions. This work presents a method to learn to predict the occurrence of these failures, i.e. to assess how difficult a scene is to a given driving model and to possibly give the human driver an early headsup. A camera-based driving model is developed and trained over real driving datasets. The discrepancies between the model's predictions and the human `ground-truth' maneuvers were then recorded, to yield the `failure' scores. Experimental results show that the failure score can indeed be learned and predicted. Thus, our prediction method is able to improve the overall safety of an automated driving model by alerting the human driver timely, leading to better human-vehicle collaborative driving.