Map-Aided Evidential Grids for Driving Scene Understanding

Abstract

Evidential grids have recently been shown to have interesting properties for mobile object perception. Possessing only partial information is a frequent situation when driving in complex urban areas, and by making use of the Dempster-Shafer framework, evidential grids are able to handle partial information efficiently. This article deals with a lidar perception scheme that is enhanced by geo-referenced maps used as an additional source of information in a multi-grid fusion framework. The paper looks at the key stages of such a data fusion process and presents an adaptation of the conjunctive combination rule for refining the analysis of conflicting information. This method relies on temporal accumulation to distinguish between stationary and moving objects, and applies contextual discounting for modeling information obsolescence. As a result, the method is able to better characterize the state of the occupied cells by differentiating moving objects, parked cars, urban infrastructure and buildings. Another advantage of this approach is its ability to separate the drivable from the non-drivable free space. Experiments carried out in real traffic conditions with a specially equipped car illustrate the performance of this approach.