3D Registration of Aerial and Ground Robots for Disaster Response: An Evaluation of Features, Descriptors, and Transformation Estimation

TL;DR

This paper evaluates various methods for globally registering 3D point-cloud data from ground and aerial robots in disaster scenarios, focusing on features, descriptors, and transformation estimation techniques to improve localization accuracy.

Contribution

The study provides a comprehensive comparison of feature, descriptor, and transformation estimation approaches for 3D registration in challenging disaster environments, including new datasets.

Findings

FGR and RANSAC outperform ICP in registration accuracy.

Segment-based features yield better results than keypoints.

Computational cost varies significantly across methods.

Abstract

Global registration of heterogeneous ground and aerial mapping data is a challenging task. This is especially difficult in disaster response scenarios when we have no prior information on the environment and cannot assume the regular order of man-made environments or meaningful semantic cues. In this work we extensively evaluate different approaches to globally register UGV generated 3D point-cloud data from LiDAR sensors with UAV generated point-cloud maps from vision sensors. The approaches are realizations of different selections for: a) local features: key-points or segments; b) descriptors: FPFH, SHOT, or ESF; and c) transformation estimations: RANSAC or FGR. Additionally, we compare the results against standard approaches like applying ICP after a good prior transformation has been given. The evaluation criteria include the distance which a UGV needs to travel to successfully localize, the registration error, and the computational cost. In this context, we report our findings on effectively performing the task on two new Search and Rescue datasets. Our results have the potential to help the community take informed decisions when registering point-cloud maps from ground robots to those from aerial robots.