Loading...
Loading...
Self-driving perception, LiDAR/camera fusion, trajectory prediction, drone perception, robot manipulation
1,664 datasets
NOAA Coastal Services Center contracted Woolpert, Inc. to collect high-resolution LiDAR elevation data for Burke, Richmond, Lincoln, and Columbia counties in Georgia in 2011. The data includes classified LAS point clouds and hydrologically flattened raster DEMs with a nominal pulse spacing of 1.0 meter and a 4-foot pixel resolution. Final products were delivered in ESRI Floating Point Grid and later converted to GeoTIFF format with vertical units in feet.
Florida's coastal region from Miami to the Marquesas Keys is covered by this 1-meter resolution topobathymetric digital elevation model (DEM). The data were collected by Quantum Spatial, Inc. for NOAA across 85 missions between November 2018 and March 2019, covering approximately 1,381,270 acres. The final dataset consists of 300 tiled DEMs derived from classified LiDAR points for ground, bathymetric bottom, and submerged objects.
The Hayabusa spacecraft's LIDAR altimeter measured the range between the spacecraft and asteroid Itokawa. This dataset includes Experiment Data Records (EDRs) and Calibrated Data Records (CDRs) from the mission. Version 2.0 features a new CDR optimized by minimizing offsets between the LIDAR data and a high-resolution shape model.
A multi-modal driving dataset focused on extreme, critical, and adverse-condition driving scenarios. It was released by the Intelligent Chassis Team at Tsinghua University's School of Vehicle and Mobility. The dataset includes human driving data as well as autonomous driving data, last updated on the platform in April 2026.
Natural hazard statistics for the Islamic Republic of Iran aggregated by year and disaster subtype, produced by the Centre for Research on the Epidemiology of Disasters (CRED). The records track human impact and economic damage from events occurring within the country, with updates maintained through March 2026.
A dataset from the Autonomous Space Robotics Laboratory (ASRL) for developing aquatic autonomous navigation algorithms. It includes synchronized data from a 360-degree radar, a 128-beam lidar, a stereo camera, imaging sonar, motor inputs, and GNSS, collected on lakes and reservoirs in Ontario, Canada. The data is hosted on AWS Open Data and released under a CC-BY-4.0 license.
OCHA Field Information Services Section (FISS) provides geospatial boundaries for Iran at two administrative levels. The dataset contains 31 provinces (Admin 1) and 429 districts (Admin 2). It was last reviewed for accuracy in October 2024 and is part of the global subnational administrative boundaries collection.
Arabic speech data comprising 7,168 hours of validated audio across approximately 3,957,670 segments from 1,229 books. The dataset, created by AlgoRythmetic, was last updated on April 21, 2026. Audio is provided in 16 kHz mono FLAC format and is organized into 2,639 parquet shards.
Building outlines representing roof areas for the City of Greater Geelong, derived from LiDAR and photogrammetry. The dataset includes attributes for approximate building height in metres and year of construction. It is published and maintained by the City of Greater Geelong, with a last recorded update in April 2026.
St. Croix, U.S. Virgin Islands, was the location for this radiosonde dataset collected during the Convective Processes Experiment – Aerosols & Winds (CPEX-AW) field campaign from August 19 to September 14, 2021. It provides vertical profiles of atmospheric pressure, temperature, relative humidity, wind speed, and wind direction from DFM-09 instruments. The primary purpose was the post-launch calibration and validation of the European Space Agency's ADM-Aeolus wind Lidar satellite.
A performance comparison between the CORE-Net method and baseline models on the DroneVehicle dataset. The dataset is a 5.5 KB Excel file authored by Daoze Tang and last updated on April 21, 2026. It is shared under a CC-BY-4.0 license on the figshare platform.
Roof area outlines for buildings were identified and measured using LiDAR analysis and photogrammetry. The dataset includes attributes for approximate building height in meters and the year of construction. It is produced and maintained by the City of Greater Geelong, with a recent update in April 2026.
Data from the NASA Cold Land Processes Experiment (CLPX) includes color infrared orthophotography at 6-inch pixel resolution, raw and filtered lidar elevation returns, and 0.5-meter elevation and 0.1-meter snow depth contours. The dataset is produced by the National Snow and Ice Data Center (NSIDC) and was last updated on the platform in March 2026. It supports research into snowpack properties and terrain modeling.
A collection of results from ablation experiments on the UAVid dataset for a semantic segmentation network called CRDFNet. The experiments validated the network's performance on remote sensing imagery, which is characterized by complex boundary shapes and dense small targets. The data is stored in an XLS file with a size of 5.5 KB.
A component ablation study for the CORE-Net model, conducted on the DroneVehicle dataset. The study was authored by Daoze Tang and published on figshare under a CC-BY-4.0 license. It was last updated on April 21, 2026.
Performance comparison between CORE-Net and baseline methods on the DroneVehicle dataset under edge deployment constraints. The 5.5 KB Excel file was authored by Daoze Tang and last updated on April 21, 2026. It is shared under a CC-BY-4.0 license on the figshare platform.
A paper compares sampling-based algorithms for mobile robot navigation, including A*, Bidirectional RRT, Artificial Potential Field, PRM, and RRT. Performance metrics like shortest path and processing time were determined in a MATLAB environment. The author is Sivaranjani Arthanari.
A human-in-the-loop, multi-view bimanual robot manipulation dataset for tabletop spill cleanup tasks. The dataset includes synchronized video, state and action trajectories, phase annotations, and success or failure labels, structured for compatibility with the LeRobot framework. It was created by ExylosAi and last updated on May 5, 2026.
Puerto Rico's landslide source areas were identified using the Multiscale Model-to-Model Cloud Comparison (M3C2) method on pre- and post-Hurricane María LiDAR data. The dataset contains over 96,100 filtered landslide events across four watersheds, resulting from a master's thesis at the University of Puerto Rico at Mayagüez. Initial detection identified over 180,000 areas, which were filtered to remove those with an average depth less than 0.5 m or area smaller than 25 m².
Drone survey data collected from November 2017 to October 2018 around Oahu, Hawaii for validating aerial estimates of akule school size. The dataset includes timestamps, school size estimates, fish life stage, environmental data, and catch information from fished schools. It was published by the National Oceanic and Atmospheric Administration.