CU-Multi: A Dataset for Multi-Robot Data Association

TL;DR

CU-Multi is a new multi-robot dataset that provides realistic, synchronized multi-day RGB-D, GPS, and LiDAR data with controlled trajectory overlaps, enabling better evaluation of multi-robot data association methods.

Contribution

The paper introduces CU-Multi, a multi-robot dataset with realistic trajectories, synchronized multi-day data, and controlled overlaps, addressing limitations of previous simulation-based evaluation strategies.

Findings

Provides a realistic multi-robot dataset with synchronized multi-day data.

Includes controlled trajectory overlaps for robust evaluation.

Offers dense LiDAR annotations and geospatial data for comprehensive analysis.

Abstract

Multi-robot systems (MRSs) are valuable for tasks such as search and rescue due to their ability to coordinate over shared observations. A central challenge in these systems is aligning independently collected perception data across space and time, i.e., multi-robot data association. While recent advances in collaborative SLAM (C-SLAM), map merging, and inter-robot loop closure detection have significantly progressed the field, evaluation strategies still predominantly rely on splitting a single trajectory from single-robot SLAM datasets into multiple segments to simulate multiple robots. Without careful consideration to how a single trajectory is split, this approach will fail to capture realistic pose-dependent variation in observations of a scene inherent to multi-robot systems. To address this gap, we present CU-Multi, a multi-robot dataset collected over multiple days at two locations on the University of Colorado Boulder campus. Using a single robotic platform, we generate four synchronized runs with aligned start times and deliberate percentages of trajectory overlap. CU-Multi includes RGB-D, GPS with accurate geospatial heading, and semantically annotated LiDAR data. By introducing controlled variations in trajectory overlap and dense lidar annotations, CU-Multi offers a compelling alternative for evaluating methods in multi-robot data association. Instructions on accessing the dataset, support code, and the latest updates are publicly available at https://arpg.github.io/cumulti