Deep, spatially coherent Occupancy Maps based on Radar Measurements

TL;DR

This paper introduces a neural network-based method for creating dense, spatially coherent occupancy maps from sparse radar data, improving urban environment perception for driver assistance systems.

Contribution

It presents an end-to-end neural network approach that learns spatial priors to interpolate occupancy, outperforming traditional detection accumulation methods.

Findings

Effective dense occupancy prediction from sparse radar data

Suitable for complex urban scenarios

Enables large-scale environment mapping

Abstract

One essential step to realize modern driver assistance technology is the accurate knowledge about the location of static objects in the environment. In this work, we use artificial neural networks to predict the occupation state of a whole scene in an end-to-end manner. This stands in contrast to the traditional approach of accumulating each detection's influence on the occupancy state and allows to learn spatial priors which can be used to interpolate the environment's occupancy state. We show that these priors make our method suitable to predict dense occupancy estimations from sparse, highly uncertain inputs, as given by automotive radars, even for complex urban scenarios. Furthermore, we demonstrate that these estimations can be used for large-scale mapping applications.