SAFERad: A Framework to Enable Radar Data for Safety-Relevant Perception Tasks

TL;DR

This paper introduces SAFERad, a novel radar data filtering framework that adapts based on collision risk, enhancing safety in automated driving perception systems by reducing false positives while maintaining critical object detection.

Contribution

SAFERad's adaptive filtering approach varies thresholds based on collision criticality, improving detection reliability for safety-critical scenarios in automated driving.

Findings

High recall rates for critical object detection.

74.8% reduction in non-clustered critical points.

Effective evaluation using adapted trajectories for vulnerable road users.

Abstract

Radar sensors play a crucial role for perception systems in automated driving but suffer from a high level of noise. In the past, this could be solved by strict filters, which remove most false positives at the expense of undetected objects. Future highly automated functions are much more demanding with respect to error rate. Hence, if the radar sensor serves as a component of perception systems for such functions, a simple filter strategy cannot be applied. In this paper, we present a modified filtering approach which is characterized by the idea to vary the filtering depending on the potential of harmful collision with the object which is potentially represented by the radar point. We propose an algorithm which determines a criticality score for each point based on the planned or presumable trajectory of the automated vehicle. Points identified as very critical can trigger manifold actions to confirm or deny object presence. Our pipeline introduces criticality regions. The filter threshold in these criticality regions is omitted. Commonly known radar data sets do not or barely feature critical scenes. Thus, we present an approach to evaluate our framework by adapting the planned trajectory towards vulnerable road users, which serve as ground truth critical points. Evaluation of the criticality metric prove high recall rates. Besides, our post-processing algorithm lowers the rate of non-clustered critical points by 74.8 % in an exemplary setup compared to a moderate, generic filter.