Map-aided Fusion Using Evidential Grids for Mobile Perception in Urban Environment

TL;DR

This paper introduces a novel perception scheme that fuses prior geographic map knowledge with sensor data using evidential grids and Dempster-Shafer theory, enhancing mobile object detection in urban environments.

Contribution

It proposes a new map-aided fusion method that integrates prior map information with sensor data using adapted Dempster-Shafer rules and contextual discounting.

Findings

Effective distinction between stationary and mobile objects.

Improved perception accuracy demonstrated on real-world data.

Enhanced fusion of prior map and sensor information.

Abstract

Evidential grids have been recently used for mobile object perception. The novelty of this article is to propose a perception scheme using prior map knowledge. A geographic map is considered an additional source of information fused with a grid representing sensor data. Yager's rule is adapted to exploit the Dempster-Shafer conflict information at large. In order to distinguish stationary and mobile objects, a counter is introduced and used as a factor for mass function specialisation. Contextual discounting is used, since we assume that different pieces of information become obsolete at different rates. Tests on real-world data are also presented.