Loading...
Loading...
Self-driving perception, LiDAR/camera fusion, trajectory prediction, drone perception, robot manipulation
2,000 datasets
112 ground-based lidar scans from the Echidna Validation Instrument capture forest structure across three U.S. campaigns. The dataset pairs these near-infrared canopy images with manual field measurements of tree species, DBH, height, and crown base. A validation file directly compares lidar-derived metrics like stem density and leaf area index to physical measurements from the 2007 New England campaign.
University of Colorado Boulder researchers collected this dataset using Windcube v1 Doppler lidars during the 2018 LAPSE-RATE field campaign. Measurements were taken at two sites in Colorado's San Luis Valley between July 14-21, 2018, to profile the lower atmosphere. The data includes wind measurements, with missing or bad values flagged as -9999.0.
SensoDat is a dataset of 32,580 executed simulation-based test cases for self-driving cars, generated with state-of-the-art test generators. It provides trajectory logs and time-series data from 81 different simulated sensors, such as rpm, wheel speed, brake thermals, and transmission. The dataset was created by Christian Birchler at the University of Bern to reduce dependency on expensive hardware and software for autonomous systems research.
NASA/JPL's UAVSAR data provides daily high-resolution (about 5 meters) full-polarized L-band Synthetic Aperture Radar observations collected between September 18th and 23rd, 2018, during Hurricane Florence. The dataset contains flood inundation extent information for four UAVSAR flight lines covering the Neuse, Cape Fear, and Lumbee Rivers in Eastern North Carolina. The data was used by Chao Wang et al. (2021) to construct a detection framework combining polarimetric decomposition and a Random Forest classifier, achieving a Kappa statistic of 91.4%.
RFUAV is a benchmark dataset presented in the paper 'RFUAV: A Benchmark Dataset for Unmanned Aerial Vehicle Detection and Identification'. It provides approximately 1.3 TB of raw frequency data collected from 37 distinct UAVs. The dataset was uploaded by author 'surdhum' and last updated on July 7, 2026.
U.S. Geological Survey research quantifies bathymetric changes along the Florida Reef Tract from Miami to Key West. The data release includes elevation-change point data, TIN surface models, lidar DEMs, and change statistics for 17 habitat types within a 939.4 square-kilometer area. Data were derived from NOAA lidar surveys conducted in 2016, 2017, and 2019.
Raw and processed data from two unmanned aerial vehicles (UAVs) sampling a controlled methane release. The dataset includes positional, wind, and mole fraction measurements from UAVs and ground stations, along with derived wind-height profiles and flux quantification results. Adil Shah from the University of Manchester compiled this data for a 2018 field campaign, supporting the journal article 'Testing the near-field Gaussian plume inversion flux quantification technique using unmanned aerial vehicle sampling'.
The Australian Lithospheric Architecture Magnetotelluric Project (AusLAMP) dataset provides a 3D resistivity model of the Earth's lithosphere. The model integrates processed data from 224 stations released in phase one (2020), 73 stations in phase two (2023), and two new stations in phase three, concluding in June 2025. This release from Geoscience Australia includes the model in SGrid and geo-referenced TIFF formats, accompanied by a report detailing data acquisition, processing, and inversion methodologies.
513,788 people were impacted within 50km of a magnitude 5.4 earthquake near Aliabad-E Katul on July 19, 2025. The dataset, provided by the World Food Programme's Automated Disaster Analysis and Mapping (ADAM) system, contains geospatial and socio-economic information for rapid humanitarian response. It was last updated on May 21, 2026.
Iran experienced a magnitude 5.4 earthquake on August 05, 2025, with an epicenter 70km south of Mohammadabad-E Rigan. The dataset, produced by the WFP's Automated Disaster Analysis and Mapping (ADAM) system, provides geospatial and socio-economic impact analysis, including an estimate of 37,403 people affected within a 50km radius. It was last updated on May 21, 2026.
Northern Great Barrier Reef bathymetry data acquired during a 47-day survey from September 30 to November 17, 2020. The survey used Kongsberg EM302 multibeam sonar on the RV Falkor to map the seabed of the Cape York Peninsula region, the Swain slide, and reefs in the eastern Coral Sea Marine Park. This dataset contains fifteen geotiff files at resolutions from 4m to 32m, published by Geoscience Australia via the Australian Ocean Data Network.
CALIPSO satellite data provides monthly mean vertical profiles of aerosol optical properties, specifically the aerosol extinction coefficient at 532 nm and aerosol optical depth (AOD), on a uniform spatial grid. The dataset is derived from the Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP) instrument and reports data only below 12 km altitude, focusing on the troposphere. It includes separate data products for different sky conditions: All Sky, Cloud-Free, Cloudy-Sky Transparent, and Cloud-Sky Opaque.
Perth Metro LiDAR acquisition capture dates are indexed on a 1km by 1km grid. The dataset is provided by the Western Australian Land Information Authority (Landgate) and was last updated on 2026-06-29. LiDAR data or derivative datasets cannot be accessed or downloaded from this site.
The Udhruh Archaeological Project dataset covers fieldwork seasons from 2011 to 2014 in southern Jordan. It focuses on a Roman legionary fortress and its continuity into later periods, studied within a landscape context. The project was led by researchers from Leiden University and Al-Hussein Bin Talal University.
215 participants provided electromyographic data from 13 lower-limb muscles during treadmill walking and running. The dataset includes raw EMG signals, gait event timings, and processed muscle synergy coefficients to investigate sex and age differences in motor control. It supports analysis of modular muscle activation patterns for human locomotion.
David Sacramento Lechado, David Pisinger, and Stefan Røpke published 112 computational instances for the Vehicle Routing Problem with Drones in Transportation Research Part C. The data includes scenarios with varying customer counts, grid dimensions, and clustered or sensitivity analysis configurations. Each instance file contains customer coordinates and demand, with a separate file detailing truck and drone operational parameters like speed, capacity, and service times.
Eight high-resolution digital elevation models from the lateral moraines of the debris-covered Lirung Glacier in Nepal, created using structure from motion based on UAV images captured between May 2013 and April 2018. The data, presented by Teun van Woerkom of Utrecht University, shows elevation changes with an average rate of -0.31 +/- 0.26 m/year, analyzed by season and moraine segment. This dataset supports the study of debris supply sources and melt rate controls on Himalayan glaciers.
Seabed landform features classified from the New South Wales statewide marine lidar dataset acquired in 2018. The dataset covers 4060 km2 of the NSW coast, extending from the shoreline to a 50-meter depth, and was created by the NSW Department of Climate Change, Energy, the Environment and Water using a publicly available ArcGIS toolset. It includes classified features such as reefs, plains, peaks, scarps, depressions, and channels.
Nan Zhang's research dataset contains performance metrics for a novel 3D object detection method evaluated on the KITTI and NuScenes benchmarks. The dataset, last updated in June 2026, includes segmentation and detection accuracy percentages, processing times, and frames-per-second metrics. The method integrates a Cloth Simulation Filter, an improved Euclidean clustering algorithm, and an enhanced PointNet architecture.
A study by Nan Zhang introduces a 3D object detection method for autonomous driving, evaluated on the KITTI and NuScenes benchmarks. The method integrates a Cloth Simulation Filter and an enhanced PointNet architecture, achieving segmentation accuracies of 94.96% and 93.12% with real-time processing speeds. The dataset, last updated in June 2026, contains the experimental setup and parameter configurations for this research.