Loading...
Loading...
Self-driving perception, LiDAR/camera fusion, trajectory prediction, drone perception, robot manipulation
2,003 datasets
Victoria, Australia's river condition was assessed using the Index of Stream Condition (ISC) between 2010 and 2013. The Department of Environment and Primary Industries (DEPI) developed this dataset using remote sensing data, specifically 15cm aerial photography and multi-pulse LiDAR, to map Physical Form and Riparian Vegetation metrics. The full package includes all spatial vector features and aspatial statistical summary tables derived from this mapping project.
33,116 short, atomic manipulation episodes collected for pretraining vision-language-action models. The dataset contains 1.52 million frames and 9,532 language tasks, formatted for the LeRobot v2.1 framework and derived from Franka robot demonstrations. It was created by MINT-SJTU and last updated on July 8, 2026.
NASA's Airborne Snow Observatory (ASO) OLYMPEX dataset provides high-resolution snow depth, bare earth surface, land surface classification, and RGB composite imagery at 3-meter spatial resolution. These data were collected via a Riegl Q1560 scanning LiDAR and an ITRES CASI-1500 imaging spectrometer during the Olympic Mountains Experiment (OLYMPEX) field campaign in the Pacific Northwest. The dataset includes measurements from two snow-on periods in February and March 2016, using a September 2014 flight as a no-snow baseline for depth derivation.
SIS-Bench is a comprehensive benchmark constructed from three diverse UAV video sources for evaluating multimodal large language models. It assesses spatial cognition and self-awareness across three cognitive levels of increasing difficulty: perception, memory, and reasoning. The benchmark was created by choucsan and last updated on July 13, 2026.
Gender statistics from the World Bank covering the Islamic Republic of Iran. The data includes sex-disaggregated indicators across demography, education, health, economic opportunities, public life, and agency. It was last updated on 2026-04-28 and is licensed under CC-BY-4.0.
CRSLP is a benchmark dataset for evaluating cooperative roadside LiDAR placement strategies. It covers 13 sites, over 100 traffic scenarios, and more than 900 placement plans with corresponding long IoU sequences. The dataset, created by Yang Ma and last updated in 2026, includes over 3600 frames of point cloud data per test configuration, totaling 1.6 GB.
NASA's AfriSAR dataset provides forest vertical structure and uncertainty products for Gabonese forests, derived from multi-baseline Polarimetric Interferometric SAR and Polarimetric Coherence Tomographic SAR techniques. Data were collected during multiple UAVSAR flights in February-March 2016 as part of a joint NASA/ESA campaign. Supplementary products include radar backscatter, coherence, and viewing and terrain geometry data.
TDWB_19_2_MassBalance_Morphology data are used to reproduce results from the paper 'Marsh sedimentation controls delta top morphology, slope, and mass balance' by Sanks et al., 2022. The data include processed LiDAR scans, channel maps, stratigraphic marsh fraction from control and treatment experiments, and elevation data from four global deltas. Author Kelly Sanks provides the data and code via a GitHub repository.
HABIT is a large-scale robot demonstration dataset designed for human-present environments. The dataset, created by configinc, is intended to teach robot policies human-aware behaviors. It was last updated on July 1, 2026.
GEDIMetrics is a QGIS plugin for accessing and integrating multi-product GEDI spaceborne LiDAR data. The dataset includes version 1.0.2 of the plugin, test inputs, study areas, and exported outputs from an evaluation workflow. It was authored by Alexander Cotrina-Sanchez and last updated on May 21, 2026.
Digital Terrain Models derived from terrestrial lidar scans collected during the SnowEx 2023 campaign at the Bonanza Creek Experimental Forest near Fairbanks, Alaska. Data were captured in October 2022 (snow-off) and March 2023 (snow-on) and are provided as GeoTIFF files, each corresponding to a unique survey site. The dataset is part of a larger collection, with unprocessed point cloud data available separately.
Dafei Wu published source code and raw experimental data for the NEL-MSCPSO algorithm on figshare in 2026. The 150.8 MB repository includes results from CEC2022 benchmark tests and multi-amphibious UAV path planning experiments. Materials such as convergence curves, displacement-time trajectories, and optimization results are provided to reproduce the paper's findings.
Forest biomass, canopy height, and tree cover estimates at 30-meter resolution for Sonoma County, California, USA, for the nominal year 2013. The dataset was produced by NASA using LiDAR data, field plot measurements, and random forest modeling. It includes estimates of above-ground biomass uncertainty alongside the primary metrics.
Project funding allocations from OCHA's Central Emergency Response Fund (CERF) for Iran (Islamic Republic of). The dataset is provided by the Central Emergency Response Fund organization and was last updated on 2026-06-05. It lists allocations made for rapid response to sudden-onset or deteriorating emergencies and for underfunded humanitarian activities.
A set of network parameter configurations for a lightweight YOLOv11-based detection model designed for unmanned aerial vehicle (UAV) rooftop photovoltaic (PV) inspection. The dataset likely contains parameters describing the model architecture, such as layer configurations and module specifications. It was authored by Jiajun Zhu and last updated on May 6, 2026.
NASA's GOES-R PLT Cloud Physics Lidar dataset contains multi-wavelength lidar measurements of cirrus clouds and aerosols collected from the ER-2 high-altitude aircraft. The data, gathered from April 13 to May 14, 2017, was used for post-launch validation of the GOES-R Advanced Baseline Imager and Geostationary Lightning Mapper instruments. It includes parameters like backscatter coefficient, depolarization ratio, layer heights, and ice water content.
Chuanxi Zhao from the Chinese Academy of Sciences created this dataset of UAV-derived orthomosaics and digital elevation models (DEMs) for the 23K and 24K glaciers in the southeastern Tibetan Plateau. The data was collected during four field campaigns in August and October of 2019 and 2020. It provides high-resolution geospatial data for monitoring glacier dynamics.
Copper depositions onto corrugated substrates representative of ~100-200 GHz waveguides are presented. Cross-sectional micrographs, material porosity, and surface roughness are reported for various spray parameters, post-deposition treatments, and substrate materials. The data was produced by James Ridzon et al. at the Plasma Science and Fusion Center and last updated on 2026-06-20.
Fourteen native forest plots in New South Wales, Australia, measured in April 2021. The data includes tree height, diameter, canopy cover, species composition, coarse woody debris, fuel hazard, and Biodiversity Assessment Method structure, along with raw and processed terrestrial LiDAR scans. It was collected as a pilot for the NSW Forest Monitoring and Improvement Program and is provided by the Terrestrial Ecosystem Research Network's Data Discovery.
CALIPSO satellite data provides calibrated radiance and bidirectional reflectance measurements from its Wide Field Camera, registered to a 1 km Earth grid centered on the lidar track. The dataset, part of the international A-Train constellation launched on April 28, 2006, is designed to study clouds and aerosols for climate research. Version 3.01 includes metadata for improved subsetting and bug corrections.