Landmark Attribute Analysis for a High-Precision Landmark-Based Local Positioning System

Abstract

GPS signals are not reliable in urban canyons or inside tunnels. In those situations, accurate local positioning is possible through local landmarks. This paper presents the potential accuracy of such a landmark-based local positioning system and the desired attributes of landmarks influencing positioning accuracy. The analysis of the achievable accuracy and the sensitivity of the factors for precise vehicle positioning is performed using LiDAR sensor measurements in a controlled environment and a generic positioning method. The landmark-based positioning can achieve better than 0.2 m accuracy. The diameter and geometric configuration of the landmarks are the most important factors for higher accuracy. The results presented can guide the design and construction of a local positioning system in urban areas.

Localization and Mapping for Self-Driving Vehicles: A Survey

“…Ref. [32] is another method that uses the pole landmarks, providing a high-precision method to localize self-driving vehicles. The method assumed five robust conditions: common urban objects, time-invariant location, time-invariant appearance, viewpoint-invariant observability, and high frequency of occurrence.…”

“…-Semantic -General -The height of curbs between 10 cm and 15 cm -RANSAC -Curves -Consume a lot -High -Hard -Passable [26,27], [28,29], [30,31], [32,33], [40].…”

On the Design of High Accuracy Rail Digital Maps based on Sensor Fusion

“…To perform this task, artificial landmarks have been placed in known locations. Moreover, in [7], the authors propose a landmark-based positioning framework which exploits on-board LIDAR for the road environment. Concerning the railway scenario, in [8] the use of a set of Radio-Frequency IDentification (RFID) tags deployed along the railway has been investigated to realize a projection-based map matching positioning procedure.…”

“…In this work, we deal with natural landmarks, so that no additional infrastructure has to be deployed along the track, and with computing their position by exploiting on board visual sensors. As described in [7], landmarks have to show at least the following properties: they have to be common objects, they have to be time-invariant both in terms of location and appearance, their observability has to be viewpoint invariant (i.e., their centroid computation has to be always possible), and their frequency of occurrence has to be high. To satisfy these requirements, in [7], the pole-like objects (i.e., traffic lights, street signs, streetlamps) are selected as primary landmarks.…”

“…As described in [7], landmarks have to show at least the following properties: they have to be common objects, they have to be time-invariant both in terms of location and appearance, their observability has to be viewpoint invariant (i.e., their centroid computation has to be always possible), and their frequency of occurrence has to be high. To satisfy these requirements, in [7], the pole-like objects (i.e., traffic lights, street signs, streetlamps) are selected as primary landmarks. The same assumption holds for the analysis reported in the following.…”