Radar detection rate comparison through a mobile robot platform at the ZalaZONE proving ground

TL;DR

This paper compares the detection capabilities of two automotive radars using a custom mobile robot platform at the ZalaZONE proving ground, highlighting differences in their object sensing performance for ADAS/AD systems.

Contribution

It introduces a novel comparison methodology for automotive radars using a self-developed robot platform in a real testing environment.

Findings

Different radars show varying detection accuracies for specific objects.

The mobile robot platform enables controlled and repeatable radar testing.

Results inform sensor selection for ADAS/AD systems.

Abstract

Since an automotive driving vehicle is controlled by Advanced Driver-Assistance Systems (ADAS) / Automated Driving (AD) functions, the selected sensors for the perception process become a key component of the system. Therefore, the necessity of ensuring precise data is crucial. But the correctness of the data is not the only part that has to be ensured, the limitations of the different technologies to accurately sense the reality must be checked for an error-free decision making according to the current scenario. In this context, this publication presents a comparison between two different automotive radars through our self-developed robot mobile platform called SPIDER, and how they can detect different kinds of objects in the tests carried out at the ZalaZONE proving ground.