Loading...
Loading...
Self-driving perception, LiDAR/camera fusion, trajectory prediction, drone perception, robot manipulation
2,005 datasets
From 17 April to 30 April 2019, NASA conducted a five-flight airborne campaign using the High Altitude Lidar Observatory (HALO) instrument aboard a DC-8 aircraft. The dataset contains aerosol and water vapor profiles and images, collected to validate the European Space Agency's Aeolus satellite mission and demonstrate the performance of airborne wind, water vapor, and aerosol lidar instruments. Flights, totaling 46 hours, were based out of Palmdale, CA and Kona, HI, covering the Eastern Pacific and Southwest U.S.
NASA's Aeolus CalVal-MetNav_DC8 dataset contains GPS-derived meteorological and navigational data from a 2019 airborne campaign. Five DC-8 flights, totaling 46 flight hours, collected data over the Eastern Pacific and Southwest U.S. to validate satellite and airborne lidar wind, water vapor, and aerosol measurements.
An inter-laboratory study evaluated the reproducibility of multi-dimensional spinal loading protocols using lumbar surrogate models. The results demonstrated strong agreement between two distinct biomechanical testing systems, with inter-laboratory range of motion differences of 0.53°–0.55° and peak load differences of 0.92–1.64 Nm. This work by Emma C. Coltoff lays a foundation for future multidimensional testing of complex spine biomechanics.
A dataset of 124 experimental trials on Crown-of-Thorns starfish locomotion and orientation behavior. The data includes individual identification, reproductive phase, seawater conditions, trial results, coral species count, coral mass, and starfish sex. It was authored by Masumi Kamata and last updated on 2026-05-05.
FSU-QA is a multimodal question-answering dataset for autonomous driving scenes. It contains 850 annotated scenes, with associated metadata and a fine-tuned Qwen3-VL-8B model. The dataset was created by Gong-Grant and last updated on Hugging Face in June 2026.
R. P. Karthik published a dataset summarizing UAV-based mango leaf disease data on figshare in May 2026. The dataset is 5.5 KB in size and is available in XLS format under a CC-BY-4.0 license. The row count and column-level details are unknown.
A 3D topographic point cloud representation of territory captured via aerial LiDAR in 2015. The technology recorded up to 400,000 3D points per second, providing detailed ground and surface elevation data. It was sourced from XEOS Imaging Inc. for the Government and Municipalities of Québec.
Table S11 provides a summary of Generalized Linear Mixed Model (GLMM) analysis results for Crown-of-Thorns Starfish (COTS) locomotion, based on a full dataset of 248 observations. The table includes statistical metrics such as effect estimates, standard errors, confidence intervals, Z-values, p-values, and the Akaike Information Criterion (AIC). It was authored by Masumi Kamata and last updated on 2026-04-25.
Pre-Delta-X: L1 UAVSAR Single Look Complex and Interferograms, MRD, LA, USA, 2016 is a Level 1 dataset containing single look complex stack products and co-registered interferograms. The data were collected by NASA's UAVSAR L-band radar on a Gulfstream-III aircraft over the Atchafalaya Basin in Louisiana during October 2016. A single flight line was sampled six times at roughly 30-minute intervals to observe changing water levels.
UAV photogrammetry data collected in the Tasiapik Valley, Umiujaq, Nunavik, Québec, Canada. The dataset includes ground control points, flight parameters, processing parameters for Pix4Dmapper, orthomosaics, raw point clouds, ground point clouds, DTMs, and DSMs. It was created by Madeleine St-Cyr and harvested from Borealis Dataverse, with data collected in 2023, 2024, and 2025.
Terrestrial LiDAR data covers a lithalsas field in the Tasiapik Valley near Umiujaq, Nunavik, Québec. It was produced as part of a Master's research project at Université Laval to study thaw subsidence of ice-rich permafrost. The dataset was authored by Madeleine St-Cyr and last updated on June 20, 2026.
NASA's Cloud Physics LiDAR (CPL) IMPACTS dataset contains airborne lidar measurements from the ER-2 high-altitude research aircraft. The data, collected from January 15, 2020, to March 2, 2023, supports a three-year field campaign studying snowband formation and microphysics over the U.S. Atlantic Coast. It includes parameters like backscatter coefficient, depolarization ratio, layer heights, and ice water content to improve snowfall prediction models.
Historic Environment Scotland (HES) LiDAR data captured in 2016/17 for eight heritage sites and their immediate landscapes. The data was procured from Blom Aerofilms Ltd and processed to 0.25m resolution. It is delivered in *.laz and GeoTiff formats, including DTM and DSM data.
SAVANT is a model-agnostic reasoning framework that reformulates anomaly detection in autonomous driving as a layered semantic consistency verification. Approximately 10,000 real-world driving images were curated to address the challenge of detecting rare, out-of-distribution semantic anomalies. The dataset, created by Brusnicki, includes structured scene descriptions and multi-modal evaluations.
CALIPSO, a joint NASA-CNES satellite launched in 2006, provides calibrated infrared radiance data to study clouds and aerosols. Its Imaging Infrared Radiometer (IIR) collects half-orbit data registered to a 1 km grid centered on the satellite's lidar track. This Level 1B product is fundamental for analyzing the Earth's radiation budget and climate within the international A-Train constellation.
Ottavia Palazzo provides data for FoxP expression analysis and its role in locomotion. The data is available as a zipped folder with well-ordered files and includes a cloning protocol for pCFD6. The dataset is listed on paperswithcode with an Open Access (green) license.
Database dumps of API usages for several Java libraries and frameworks, including Guice, Guava, Easymock, Spring, and Hibernate. The dataset was created by Anand Ashok Sawant and is hosted on Papers with Code under an Open Access license. The last update date and exact scale are unknown.
This dataset maps 0.1429 million km of arterial roads across Iran, featuring AI-derived surface types, widths, and passability scores produced by HeiGIT. Using PlanetScope satellite imagery from 2020 and 2024, the data supplements OpenStreetMap (OSM) segments where surface information is missing for over 53% of the network.
7,000 keyframes of multi-modal data for off-road 3D traversability prediction, collected by autonomous ground vehicles. The dataset includes surround-view imagery from six cameras, 128-channel LiDAR scans, and voxel-level terrain annotations. It was created by harpreetsahota and last updated on 2026-05-29.
A merged dataset combines the RDD-2022 dataset from six countries with two supplementary aerial datasets, UAV-PDD2023 and RoadDamageVision from China and Spain. It is a derived dataset repackaged and relabeled by TamAko783 from three independently published sources. The dataset was last updated on June 4, 2026.