Credibilist SLAM performances with different laser set-ups

Abstract

Abstract-Navigation in the Intelligent Transportation Systems (ITS) domain is still divided between reliable solutions that require heavy and costly set-ups and affordable solutions that still lack performances. By proposing a new method for Simultaneous Localisation and Mapping (SLAM) based on Transferable Belief Model (TBM), the authors aimed at finding a reasonable compromise for urban environment [1]. This article supports this choice and proposes a comparison between different laser set-ups to expose advantages and drawbacks of this solution.

On line mapping and global positioning for autonomous driving in urban environment based on evidential SLAM

“…6 show the drift which affects the map and illustrate that it is under 5 % in displacement and 0, 03 deg/m in rotation. Those results are similar to the ones obtained with the Evidential SLAM in terms of local positioning [11], [10]. An example of the tested series is plotted Fig.…”

“…Using evidential theory in a Simultaneous Localization And Mapping algorithm has been proposed by the authors in [10] and validated in [11]. The contribution was to propose to switch from the classic probabilistic framework to the Transferable Belief Model (TBM) framework enables to bypass the static world assumption in most of the current SLAM processes.…”

Static and Dynamic Objects Analysis as a 3D Vector Field

“…In the context of Simultaneous Localization and Mapping with Moving Object Tracking (SLAM-MOT), [1,13,14,15,34,35,36] proposed to detect the moving objects by a probabilistic model which requires prior map information and relatively long term observations. Pomerleau et al [11] and Ambrucs et al [37] proposed to detect dynamic objects by comparing the current map with the known model.…”