Loading...
Loading...
Self-driving perception, LiDAR/camera fusion, trajectory prediction, drone perception, robot manipulation
1,663 datasets
A single wind-powered saildrone autonomously collected a 60-day multivariate dataset during a cruise from San Francisco to Guadalupe Island. The dataset provides high-resolution, near real-time surface observations at 1-minute intervals and current profiles to 100m depth at 5-minute resolution. Its scientific objectives targeted upwelling dynamics, air-sea interactions, and validating satellite data and ocean models.
Gobinda Chandra Sarker's dataset, last updated in April 2026, contains configuration data for a vision-based UAV navigation system. The 5.5 KB dataset, stored in XLS format, relates to a method integrating depthmap estimation with Vision-Language Models for obstacle avoidance and path planning. The system's performance was validated in AirSim simulations using the Blocks and Downtown West environments.
Gobinda Chandra Sarker published this dataset on figshare in April 2026. It contains simulation results for a novel vision-based Unmanned Aerial Vehicle (UAV) navigation system that integrates depthmap estimation with a Vision-Language Model for obstacle avoidance and path planning. The system was validated in AirSim using Blocks and the Downtown West environment, achieving a reported task completion rate of 0.98.
Overall navigation performance of VLM-Nav, a vision-based UAV navigation method integrating depthmap estimation with Vision-Language Models. The dataset, authored by Gobinda Chandra Sarker and last updated in April 2026, contains simulation results from AirSim using Blocks and Downtown West environments. The system achieved a near-perfect task completion rate of 0.98.
Simulation results for a novel vision-based UAV navigation method integrating depthmap estimation with a Vision-Language Model. The dataset, 9.5 KB in size, was authored by Gobinda Chandra Sarker and last updated in April 2026. It likely contains metrics from tests in AirSim environments evaluating obstacle avoidance and path planning performance.
A 5.5 KB dataset by Gobinda Chandra Sarker, last updated in April 2026, containing inference time measurements for a vision-based UAV navigation system. The system integrates depthmap estimation from RGB images with Vision-Language Models for obstacle avoidance and path planning, validated in AirSim simulations.
A hyperparameter dataset for a Fully Connected Network (FCN) model used in autonomous UAV navigation research. The model integrates depth maps from the DepthAnything-V2 estimator with Vision-Language Model (VLM) outputs and relative heading angles to predict navigation actions. The dataset, 5.5 KB in size, was authored by Gobinda Chandra Sarker and last updated on April 3, 2026.
22 sites on the Upper Brazos River were surveyed monthly, resulting in a 206.8 MB composite dataset. David Hoeinghaus published this collection, which includes instream environmental conditions, drone imagery, fish assemblage data, and eDNA metabarcoding data. The dataset was last updated on April 22, 2026.
Geospatial boundaries and conservation metadata for terrestrial and marine protected areas in Iran are provided by the UN Environment Programme World Conservation Monitoring Centre (UNEP-WCMC). The collection integrates the World Database on Protected Areas (WDPA) and Other Effective Area-based Conservation Measures (WD-OECM) into a unified repository updated monthly.
Contours over the entire Ipswich City Council authority area at a 5-metre interval. The data was compiled from a 2019 Airborne Laser Scanning (LiDAR) project and is provided by the Ipswich City Council. The dataset was last updated on the platform in April 2026.
Vicmap Elevation 1m DEM Footprints represent the boundaries of the LiDAR DEM Collection datasets used in the Vicmap 1m DEM product. This spatial metadata dataset belongs to the Vicmap 1m DEM product and is maintained by the Department of Energy, Environment and Climate Action. The footprints are also available as spatial web services (WFS).
Bathymetric light detection and ranging (lidar) data for depths from 0 to 50 meters around the island of Saipan, Commonwealth of the Northern Mariana Islands. The package contains .LAS 1.4 files with 16 Lidar Waveform Metrics (LWFM) describing the shape of the seafloor return, developed through a partnership between NOAA NCCOS, Oregon State University, and other agencies. This data was used to predict the distribution of key coral reef taxa and habitats west of Saipan.
The Department of Primary Industries created this dataset of coastal levees for the Future Coasts Program in 2011. It was captured using aerial imagery and a topographic LiDAR Digital Elevation Model (DEM). The dataset is provided by the Department of Energy, Environment and Climate Action and was last updated in April 2026.
Elevation data for the Wimmera CMA region in Australia, derived from a 2004 lidar survey. The dataset includes 1.0-meter contour coverage across the entire region and higher-resolution 0.5-meter contours along the Wimmera River Trench. It was created and provided by the Wimmera Catchment Management Authority.
Elevation data for the Wimmera CMA region in Australia, derived from a 2004 lidar survey. The dataset includes 1.0-meter contour coverage across the entire region and higher-resolution 0.5-meter contours along the Wimmera River Trench. It was created and provided by the Wimmera Catchment Management Authority.
A dataset of real-world testing for LiDAR-based stair and elevation change detection. It was created by Nikhil Herdt and published on figshare in May 2026. The dataset is stored in an XLSX file and is 18.0 KB in size.
Anila Johnson published a 5.5 KB Excel file on figshare in April 2026. The dataset contains the standard deviation of point density for the KITTI and ModelNet40 datasets. The specific number of rows and column definitions are not provided.
Velodyne LiDAR point cloud dataset in PLY format, collected using a Velodyne sensor for a specific study. The dataset is 92.5 MB in size, authored by Anila Johnson, and was last updated on April 28, 2026. It is distributed under a CC-BY 4.0 license.
Central and eastern U.S. airborne campaigns collected column-average carbon dioxide concentrations using a Multi-functional Fiber Laser Lidar (MFLL) aboard a C-130 Hercules aircraft. The dataset covers four seasonal campaigns from Summer 2016 to Spring 2018, with measurements recorded at a 0.1-second frequency up to 8 km altitude. This Level 2 'Lite' subset is provided by the Atmospheric Carbon and Transport (ACT-America) project.
ELDOR is a benchmark dataset for detecting illegal gold mining activities in the Amazon Rainforest. The dataset consists of drone-captured orthomosaic imagery and corresponding labels, organized into train, validation, and test splits. It was created by IRSC and documented in a 2026 research paper.