Sensor Data Fusion in Top-View Grid Maps using Evidential Reasoning with Advanced Conflict Resolution

TL;DR

This paper introduces an advanced evidential reasoning method for fusing heterogeneous sensor data in top-view grid maps, improving conflict resolution and reliability estimation to enhance fusion robustness.

Contribution

It proposes a novel data-driven reliability estimation approach and an improved conflict resolution technique for sensor data fusion in top-view grid maps.

Findings

Robust fusion of LiDAR and stereo camera data demonstrated

Enhanced conflict resolution in highly conflicting sensor inputs

Quantitative and qualitative evaluation confirms improved fusion quality

Abstract

We present a new method to combine evidential top-view grid maps estimated based on heterogeneous sensor sources. Dempster's combination rule that is usually applied in this context provides undesired results with highly conflicting inputs. Therefore, we use more advanced evidential reasoning techniques and improve the conflict resolution by modeling the reliability of the evidence sources. We propose a data-driven reliability estimation to optimize the fusion quality using the Kitti-360 dataset. We apply the proposed method to the fusion of LiDAR and stereo camera data and evaluate the results qualitatively and quantitatively. The results demonstrate that our proposed method robustly combines measurements from heterogeneous sensors and successfully resolves sensor conflicts.