Measuring Novelty in Autonomous Vehicles Motion Using Local Outlier Factor Algorithm

TL;DR

This paper introduces a real-time novelty detection method for autonomous vehicle motion using the Local Outlier Factor algorithm on IMU sensor data, aiming to improve safety under unexpected scenarios.

Contribution

The paper presents a novel application of LOF for real-time novelty measurement in autonomous vehicle motion based on IMU data, with validation on real-world datasets.

Findings

The LOF-based metric can quantify motion novelty to some extent.

The model performs practically in real-world vehicle scenarios.

The approach helps identify abnormal vehicle behaviors in real-time.

Abstract

Under unexpected conditions or scenarios, autonomous vehicles (AV) are more likely to follow abnormal unplanned actions, due to the limited set of rules or amount of experience they possess at that time. Enabling AV to measure the degree at which their movements are novel in real-time may help to decrease any possible negative consequences. We propose a method based on the Local Outlier Factor (LOF) algorithm to quantify this novelty measure. We extracted features from the inertial measurement unit (IMU) sensor's readings, which captures the vehicle's motion. We followed a novelty detection approach in which the model is fitted only using the normal data. Using datasets obtained from real-world vehicle missions, we demonstrate that the suggested metric can quantify to some extent the degree of novelty. Finally, a performance evaluation of the model confirms that our novelty metric can be practical.