Benchmarking Visual Odometry & VSLAM for AMRs in Real-World Logistics
This work presents a comprehensive benchmark evaluation of visual odometry (VO) and visual SLAM (VSLAM) systems for mobile robot navigation in real-world logistical environments. We compare multiple visual odometry approaches across controlled trajectories covering translational, rotational, and mixed motion patterns, as well as a large-scale production facility dataset spanning approximately 1.7 km. Performance is evaluated using Absolute Pose Error (APE) against ground truth from a Vicon motion capture system and a LiDAR-based SLAM reference. Our results show that a hybrid stack combining the cuVSLAM front-end with a custom SLAM back-end achieves the strongest mapping accuracy, motivating a deeper integration of cuVSLAM as the core VO component in our robotics stack. We further validate this integration by deploying and testing the cuVSLAM-based VO stack on an NVIDIA Jetson platform.
VO approaches are evaluated on controlled translational, rotational and mixed-motion trajectories against Vicon ground truth, and on a ~1.7 km production facility run against a LiDAR-SLAM reference.
TODO: caption.
@misc{abihana2026cuvslam,
author={Abi Hana, Charbel and Amareen, Kameel and Mostafa, Mohamad and Slepichev, Dmitry
and Rabeti, Hesam and Wang, Zheng and Acharya, Mihir and Rizk, Anthony},
title={Industrial cuVSLAM Benchmark \& Integration},
year={2026},
eprint={2603.16240},
archivePrefix={arXiv},
primaryClass={cs.RO}
}