DiTer++: Diverse Terrain and Multi-modal Dataset for Multi-Robot SLAM in Multi-session Environments

TL;DR

DiTer++ is a comprehensive multi-robot SLAM dataset capturing diverse terrains and multi-modal data across multi-session environments, facilitating research in large-scale, dynamic mapping scenarios.

Contribution

We introduce DiTer++, a novel dataset that includes multi-robot, multi-session, multi-modal data for SLAM in complex environments with dynamic and unstructured elements.

Findings

Dataset includes day and night scans for large-scale mapping.

Utilizes legged robots for terrain-agnostic traversal.

Provides ground-truth maps with dynamic objects removed.

Abstract

We encounter large-scale environments where both structured and unstructured spaces coexist, such as on campuses. In this environment, lighting conditions and dynamic objects change constantly. To tackle the challenges of large-scale mapping under such conditions, we introduce DiTer++, a diverse terrain and multi-modal dataset designed for multi-robot SLAM in multi-session environments. According to our datasets' scenarios, Agent-A and Agent-B scan the area designated for efficient large-scale mapping day and night, respectively. Also, we utilize legged robots for terrain-agnostic traversing. To generate the ground-truth of each robot, we first build the survey-grade prior map. Then, we remove the dynamic objects and outliers from the prior map and extract the trajectory through scan-to-map matching. Our dataset and supplement materials are available at https://sites.google.com/view/diter-plusplus/.