ABSTRACT Simultaneous localization and mapping (SLAM) is fundamental to reliable navigation in unmanned ground vehicles (UGVs), particularly in campus environments. In this paper, we present VISTA‐Campus, a multimodal dataset collected across a university campus with dual LiDARs, a stereo camera, and surround‐view cameras featuring extensive overlapping coverage. The dataset spans diverse temporal conditions, illumination changes, pedestrian densities, and geographic zones, and is designed to support both current and emerging perception modalities. It incorporates multiple loop closure detection conditions while providing long‐distance sequences, making it particularly suitable for long‐term SLAM evaluation. We also provide partial annotations for object detection and drivable area segmentation. The dataset's quality is validated by benchmarking popular SLAM algorithms. We expect VISTA‐Campus to advance SLAM and autonomous driving research in diverse campus‐like settings. The dataset is available at https: //github. com/VISTA‐Campus/VISTACampus.
Zhang et al. (Sun,) studied this question.