Loading...
Loading...
Self-driving perception, LiDAR/camera fusion, trajectory prediction, drone perception, robot manipulation
2,003 datasets
Approximately 0.8963 million kilometers of roads in Iran are mapped, with AI-derived estimates classifying 16.1911% as paved and 7.6254% as unpaved. The dataset, created by the Heidelberg Institute for Geoinformation Technology (HeiGIT), combines OpenStreetMap data with deep learning predictions from Mapillary imagery and urban classification layers. It was last updated on March 17, 2026.
FLUID is a dataset of fine-grained trajectories with a focus on dense traffic conflicts at typical urban signalized intersections. It contains approximately 5 hours of drone-captured data covering over 20,000 traffic participants across three distinct intersection types. The dataset was authored by Yiyang Chen and last updated on 2026-05-02.
9.5 KB of analytical results for a multi-user UAV-assisted non-orthogonal multiple access system operating over Rician fading channels. The data, authored by Sk Thaherbasha and last updated in May 2026, includes derived closed-form expressions for outage probability, incorporating hardware impairments, imperfect channel state information, and non-ideal successive interference cancellation.
A synthetic LiDAR scene flow benchmark collected using the CARLA simulator and formatted for compatibility with OpenSceneFlow. The dataset is provided by KTH and was last updated on June 20, 2026. It includes two pretrained model checkpoints to support further research.
The CAMEX-4 MIPS Microwave Profiling Radiometer dataset from the University of Alabama in Huntsville provides mobile atmospheric profiles. It includes vertical profiles of temperature, water vapor, and liquid water from the surface to 10 km altitude, measured approximately every 15 minutes. The data was collected by NASA during the CAMEX-4 field campaign.
Eight days of mission reports from the NASA DC-8 aircraft during the CPEX-AW field campaign. These documents detail daily objectives, flight times, and instrument performance for the joint NASA-ESA campaign to validate the ADM-Aeolus wind Lidar satellite. Data covers the period from August 20 to August 27, 2021.
Fourteen flights between August 15 and September 12, 2006 collected atmospheric profiles during the NASA African Monsoon Multidisciplinary Analyses campaign. The dataset contains Differential Absorption Lidar measurements of water vapor mixing ratio and aerosol scattering ratio from the NASA DC-8 aircraft, along with derived parameters like relative humidity and aerosol optical thickness.
CALIPSO satellite data provides global monthly-averaged stratospheric aerosol profiles derived from lidar backscatter measurements. The dataset includes parameters such as 532nm total attenuated backscatter, extinction, attenuated scattering ratios, and stratospheric aerosol optical depths, reported on a uniform spatial grid. It distinguishes between 'background only' aerosol conditions and 'all aerosol' layers, with clouds and polar stratospheric clouds removed.
Yukon drone lidar surveys provide 30 cm resolution bare-earth Digital Terrain Models over segments of the Eastern Denali fault. The Yukon Geological Survey and Kluane First Nation collected the data to evaluate geothermal energy potential near Burwash Landing. The data reveals dextral offsets between 5 and 75 meters and vertical separation up to 20 meters.
Colauntangle Post-cutoff dataset contains 300 synthesized tangled commits collected from open-source Java and C# projects. The benchmark is constructed by combining pairs of atomic commits using git cherry-pick, following the methodology of the original Flexeme benchmark. Each data point contains a tangled commit and its corresponding atomic commits, which serve as ground-truth decomposition answers.
Hui Wu's dataset provides an improved Analytic Hierarchy Process (AHP) evaluation metric weights table for sensor fusion screening. The 9.5 KB XLS file, last updated in May 2026, supports research into optimizing unmanned aerial vehicle (UAV) sensor combinations for monitoring highway geohazards in rural and urban areas.
Hui Wu published judgment matrices on figshare in May 2026. The dataset supports research on selecting optimal multi-sensor fusion schemes for unmanned aerial vehicle (UAV) monitoring of highway geohazards. It applies an improved AHP-TOPSIS method to evaluate sensor combinations for rural and urban highway areas.
7,000 keyframes of multi-modal data for off-road 3D traversability prediction, collected by autonomous ground vehicles across four outdoor environments in South Korea. The dataset provides surround-view imagery from 6 cameras, 128-channel LiDAR scans, and voxel-level traversability annotations. It was created by Voxel51 and last updated in June 2026.
The Ministry of Natural Resources and Forests produced vector layers of riparian ecotones starting in 2020. These layers delineate transition zones between aquatic and forest environments using a canopy height model and topographic humidity index derived from aerial LiDAR, integrated with southern Quebec's ecoforest map data. The methodology was developed in collaboration with Laval University's forest hydrology laboratory.
1.8+ million individual tree crown mortality records were generated from LiDAR data using the lidR algorithm. The data were created by Atticus Stovall for a study on tree height and mortality during extreme drought. The study area is the Sierra Nevada mountains in California, and the data cover the period from 2009 to 2016.
Four datasets created by Francisco Neves for UAV landing operations using a multimodal fiducial marker called ArTuga. The collection includes spatially aligned RGB images from LiDAR, visual, and thermal sensors, as well as an early-fused multimodal version. The datasets are hosted on paperswithcode under an Open Access (green) license.
Parameters of beam spot size on a detector in an array varying with the half receiving field of view. This data is associated with Figure 7 in the paper 'Design of the Quadrangular prism Beam Splitting Receiving System in MEMS-Based Scanning Lidar' authored by Xiaobao Lee. The dataset is hosted on Papers with Code under an Open Access license.
185.8 MB of semantically structured urban data integrated into a machine-readable knowledge graph. The Autonomous Vehicle Knowledge Graph (AVKG) is organized into five subgraphs covering road networks, incidents, activities, points of interest, and operators, stored in a GraphDB triple store. Author Huihai Wang published the dataset on figshare in April 2026 under a CC-BY-4.0 license.
Lidar dataset of the first week of measurements of the Hunga Tonga volcanic plume recorded above Reunion Island. The data was authored by Alexandre Baron of the Centre National de la Recherche Scientifique. The dataset is available under an Open Access (green) license.
776 publicly available autonomous vehicle collision reports from the California Department of Motor Vehicles, analyzed by Liu Yang. The dataset, last updated in April 2026, categorizes risk factors into vehicle information, collision details, and road/environmental characteristics. It employs statistical and Bayesian network analysis to explore causal chains and collision severity.