How far should self-driving cars see? Effect of observation range on vehicle self-localization

TL;DR

This paper investigates the impact of observation range on autonomous vehicle self-localization, proposing a dynamic framework to optimize range for accuracy and efficiency, validated with real-world data.

Contribution

It introduces a novel framework that dynamically adjusts the observation range for vehicle localization, balancing accuracy and computational efficiency.

Findings

Reduced average matching time from 142.2 ms to 39.3 ms

Maintained localization accuracy around 8.1 cm

Validated framework with field data

Abstract

Accuracy and time efficiency are two essential requirements for the self-localization of autonomous vehicles. While the observation range considered for simultaneous localization and mapping (SLAM) has a significant effect on both accuracy and computation time, its effect is not well investigated in the literature. In this paper, we will answer the question: How far should a driverless car observe during self-localization? We introduce a framework to dynamically define the observation range for localization to meet the accuracy requirement for autonomous driving, while keeping the computation time low. To model the effect of scanning range on the localization accuracy for every point on the map, several map factors were employed. The capability of the proposed framework was verified using field data, demonstrating that it is able to improve the average matching time from 142.2 ms to 39.3 ms while keeping the localization accuracy around 8.1 cm.