Loading...
Loading...
Self-driving perception, LiDAR/camera fusion, trajectory prediction, drone perception, robot manipulation
1,692 datasets
Engineering data on building damage from the 2018 Camp Fire in Paradise, California. Data was collected in Spring 2019 using Terrestrial Laser Scanning (LiDAR) and drone-based Structure from Motion (UAS) at specific sites including schools, a hospital, a Safeway, and residential structures. The project aims to quantify local and global structural damage and evaluate forest burn severity.
5 February 2014 orthophoto of a drainage area from a 1982 fuel spill at Old Casey station, Antarctica. The image was created by researchers from TerraLuma and the University of Tasmania for the Australian Antarctic Division's Terrestrial and Nearshore Ecosystems group. It was derived from UAV-acquired aerial photographs and georeferenced using differential GPS ground control points.
USC-PSI-Lab released Humanoid Everyday in 2025, providing over 260 tasks across 7 categories for open-world robotic learning. The collection includes between 1,000 and 10,000 video records of humanoid manipulation and locomotion-integrated activities. All data were captured through a human-supervised teleoperation pipeline to ensure high-quality demonstration trajectories.
Two CSV files contain data from a three-way comparison of cetacean detection methods in the Beaufort Sea. Observations were made by human observers, digital cameras on a manned aircraft, and cameras on an unmanned ScanEagle UAV. The Arctic Aerial Calibration Experiments were conducted by NOAA_NCEI from August 26 to September 7, 2015.
ABoVE provides Level 1 polarimetric radar backscattering coefficient data from the UAVSAR P-band SAR instrument. The dataset contains 139 data takes from flight campaigns conducted between May and August 2017, covering 74 study sites across Alaska and western Canada. Data products are polarimetrically calibrated, multi-look complex, and georeferenced.
AgriLiRa4D is a multi-sensor UAV dataset designed for robust Simultaneous Localization and Mapping (SLAM) in challenging agricultural environments. The dataset was created by Zhihao Zhan, Yuhang Ming, Shaobin Li, and Jie Yuan and was released in 2025. It is hosted on Hugging Face and was last updated on December 6, 2025.
UAVIT-1M is a large instruction tuning dataset designed to enhance visual understanding capabilities for low-altitude unmanned aerial vehicles (UAVs). It supports 11 image-level and region-level tasks. The dataset was created by ZhanYang-nwpu and released on Hugging Face in May 2025.
CALIPSO's CALIOP instrument provided global cloud distribution data on a uniform spatial grid with a monthly temporal average. This Level 3 product was generated from Level 2 data by NASA and CNES's LARC_CLOUD team, with collection ending in December 2016 due to instrument degradation. The mission launched in 2006 to study clouds and aerosols within the A-Train satellite constellation.
CALIPSO satellite lidar data provides monthly global distributions of ice cloud extinction and ice water content on a uniform grid. This Level 3 product is derived from CALIOP instrument Level 2 profiles and was produced by the NASA-CNES CALIPSO mission. Data collection for this specific version ended in December 2016 due to instrument degradation.
NASA's Pacific Exploratory Mission West A collected Differential Absorption Lidar (DIAL) data onboard a DC-8 aircraft in September-October 1991. The campaign aimed to study atmospheric chemistry over the northwestern Pacific region. Data collection for this product is complete.
Differential Absorption Lidar (DIAL) data was collected onboard a NASA DC-8 aircraft during the PEM-West B campaign in February-March 1994. The dataset provides vertical profiles of ozone and other atmospheric constituents over the northwestern Pacific region. It was created by the LARC_CLOUD organization as part of NASA's Global Tropospheric Experiment.
Remotely sensed ozone and lidar property data were collected by a Differential Absorption Lidar (DIAL) onboard a NASA DC-8 aircraft during the KORUS-AQ field campaign. The campaign was a joint NASA and Korean National Institute of Environmental Research (NIER) study conducted over South Korea in May-June 2016. Measurements support research on air quality factors like photochemistry, emissions, and satellite observation strategies.
CALIPSO satellite data provides a global record of blowing snow properties over Antarctica, derived from backscatter measurements by the CALIOP lidar instrument. This Level 2 product was produced by NASA and the French CNES from the CALIPSO mission, which launched in 2006 and completed data collection for this specific dataset. The version was updated to 1-01 due to a change in the operating system of the production cluster.
Satellite lidar data provides global distributions of stratospheric aerosol properties. The dataset contains monthly averaged parameters including 532nm total attenuated backscatter, extinction, attenuated scattering ratios, and aerosol optical depths. It is produced by NASA and the French CNES from the CALIPSO mission, which launched in 2006 and has ongoing data collection.
Griffin is a pioneering publicly available dataset for aerial-ground cooperative 3D perception. It features over 200 dynamic scenes, totaling more than 30,000 frames and 270,000 images, built using CARLA-AirSim co-simulation. The dataset was created by author wjh-svm and last updated on Hugging Face in September 2025.
A Minecraft map and data prototype of Cambridge, UK. It was created by combining LIDAR sensor data from the UK Environment Agency with human-sensed OpenStreetMap data. The dataset was last updated on 2018-09-27 and is associated with the Collusion Maker Challenge.
Wind profiles provide high spatial and vertical resolution three-dimensional wind vector retrievals from an airborne Doppler Wind Lidar instrument. The dataset was collected by NASA's G-III aircraft during the joint WHyMSIE and APEX field campaigns from September 20 to November 15, 2024, and is archived by the GHRC_DAAC.
Airborne lidar datasets collected in the Arctic Ocean during July 2022 as part of NASA's Calibration and Validation Campaign for ICESat-2. The data, published by researcher Kutalmis Saylam via the Texas Data Repository, were acquired using a Leica Chiroptera 4X system from Thule Air Force Base. It includes two sets of data for near-infrared (1064 nm) and green-wavelength (515 nm) light.
European spatially explicit data on forest canopy fuel load and canopy bulk density at a 1 km² grid resolution. The dataset comprises 4 maps, including the two fuel parameters and their associated uncertainties, generated using a multi-sensor approach integrating GEDI LiDAR, Landsat 8, and PALSAR SAR imagery with machine learning. It was created by Aragoneses, Elena and colleagues, with the supporting publication dated 2025.
1991 data from the FIRE Cirrus 2 field experiment contains altitude versus time images of cirrus clouds. The dataset was created by the LARC_ASDC organization using a Volume Imaging Lidar instrument. Images were sampled at 5 km intervals during cross-wind scans at Coffeyville, Kansas.