An LSTM-based Test Selection Method for Self-Driving Cars

TL;DR

This paper presents an LSTM-based method for selecting challenging tests in self-driving car systems, improving testing efficiency by focusing on unsafe scenarios through sequence classification of road features.

Contribution

It introduces a novel deep learning approach using LSTM for classifying road segments as safe or unsafe, enhancing test selection accuracy in self-driving car validation.

Findings

LSTM outperforms traditional machine learning methods in accuracy and precision.

The approach effectively identifies unsafe road segments for testing.

Comparable recall and F1 scores to existing methods.

Abstract

Self-driving cars require extensive testing, which can be costly in terms of time. To optimize this process, simple and straightforward tests should be excluded, focusing on challenging tests instead. This study addresses the test selection problem for lane-keeping systems for self-driving cars. Road segment features, such as angles and lengths, were extracted and treated as sequences, enabling classification of the test cases as "safe" or "unsafe" using a long short-term memory (LSTM) model. The proposed model is compared against machine learning-based test selectors. Results demonstrated that the LSTM-based method outperformed machine learning-based methods in accuracy and precision metrics while exhibiting comparable performance in recall and F1 scores. This work introduces a novel deep learning-based approach to the road classification problem, providing an effective solution for self-driving car test selection using a simulation environment.