Loading...
Loading...
Self-driving perception, LiDAR/camera fusion, trajectory prediction, drone perception, robot manipulation
2,023 datasets
NASA ER-2 aircraft lidar data from the 1992 ASTEX campaign measured cloud altitudes and layer structure over the eastern North Atlantic Ocean. The Cloud Lidar System instrument recorded geophysical location, time, and heights for up to five cloud layers across four spectral channels. This dataset was collected by NASA's LARC_ASDC organization during the intensive field observation period from June 1 to June 28, 1992.
uav_fireman_test is a dataset published on Kaggle. Its title suggests it contains data related to testing Unmanned Aerial Vehicles (UAVs) in firefighting scenarios. The dataset's specific content, size, and origin require verification after download.
Kaggle hosts a dataset titled Drone-Weapon-Detection-Showcase. The dataset likely contains imagery for detecting weapons using drone-based sensors. Its specific contents, size, and origin require verification after download.
VisDrone-dataset is a collection of drone-captured images hosted on Kaggle. The dataset likely contains visual data for computer vision tasks. Its specific content, size, and creation details are not provided in the available metadata.
A 5.5 KB Excel file details a hierarchical Model Predictive Control architecture for robotic arms. The data likely contains simulation results for path planning and obstacle avoidance in unpredictable environments. It was authored by Jiexin Wang and last updated on March 19, 2026.
VisDrone is a dataset published on Kaggle. The title suggests it contains video or image data captured by drones, likely for computer vision tasks. Its specific content, scale, and origin require verification after download.
Multiview video data of human activity, both scripted and unscripted, collected with roughly 100 actors over several weeks. The current release consists of about 328 hours (516GB, 4259 clips) of video data from 29 cameras, plus 4.6 hours of UAV data and annotations for roughly 184 hours. The dataset was created by Kitware, with further updates planned.
2.3 million text chunks sourced from the writings of four major world religions. The dataset likely contains segmented passages from Christian, Jewish, Hindu, and Islamic texts, facilitating comparative analysis. Its origin, collection method, and specific textual sources are not detailed in the provided metadata.
Kaggle hosts a dataset on self-driving cars. The dataset's specific content, size, and origin are not detailed in the provided metadata. Its actual structure and features require verification after download.
Self-driving cars01 is a dataset hosted on Kaggle, likely containing information related to autonomous vehicles. The platform tags suggest it includes tabular data for robotics and self-driving car applications. Its specific contents, size, and origin require verification after download.
VisualDroneDataset is a collection of drone-captured images published on Kaggle. The dataset likely contains visual data intended for computer vision tasks such as object detection or scene understanding. Its specific contents, scale, and creation details are not provided in the available metadata.
Time-series atmospheric profiles from the Phoenix Mars Lander, with durations between 5 and 90 minutes. The data contains raw laser scattering profiles at 532nm and 1064nm wavelengths, with each profile representing an accumulation over 1.28 to 20.24 seconds. It was produced by the National Aeronautics and Space Administration and last updated in March 2026.
NOAA and USGS provide a 0.5-meter bare-earth raster digital elevation model (DEM) derived from Quality Level 1 lidar data collected between 2020 and 2023. The dataset consists of 16,760 individual 500-meter x 500-meter GeoTIFF tiles covering approximately 1,428 square miles across the islands of Kahoolawe, Lanai, Maui, Molokai, and Oahu. Data acquisition followed the National Geospatial Program Lidar Base Specification Version 2.1 with an aggregate nominal pulse spacing of 0.35 meters.
Morro Bay, California, is covered by a 1-meter resolution digital elevation model derived from topobathymetric lidar data. The dataset covers approximately 4,215 acres and consists of 96 tiles, collected by NV5 Geospatial for NOAA's Office of Coastal Management in June 2022. The data includes classified point clouds with categories for ground, water surface, bathymetric bottom, water column, and submerged objects like oyster reefs.
177 acres of high-density lidar data were collected over the Grand Bay National Estuarine Research Reserve using a drone-mounted Velodyne Puck VLP-16 system. Quantum Spatial and PrecisionHawk conducted flights from May 9-11, 2017, achieving an average first return density over 105 points per square meter. The deliverables include lidar point clouds in LAS/LAZ format with UTM zone 16 NAD83(2011) horizontal and NAVD88 vertical datums.
Morro Bay, California, 2022 topobathymetric lidar data covering approximately 4,215 acres along the south central Pacific Coast. The dataset, collected by NV5 Geospatial for NOAA OCM and the NEP, includes classified LAS point clouds and 1-meter resolution bare earth Digital Elevation Models (DEMs). Data were acquired on June 14, 2022, and are delivered in 500 m x 500 m tiles clipped to the project boundary.
Chesapeake Bay, Maryland, is covered by two lidar datasets (MD1902 and MD1903) collected by NV5 Geospatial in November 2019. The data includes classified point clouds and derived 1-meter resolution digital elevation models (DEMs) covering approximately 260 and 273 square kilometers respectively. The National Oceanic and Atmospheric Administration (NOAA) processed the lidar data into GeoTIFF format.
2023 NOAA NGS Lidar data for Long Island Sound, NY, collected in four blocks across 69 missions flown between March and October 2023. The dataset includes topobathymetric point clouds in LAS 1.4 format with 18 distinct classification codes and 4 channel bits for sensor identification. Data features lidar intensity values, number of returns, return number, time, and scan angle, compiled into 500 m x 500 m tiles.
3,075,010 acres of coastal terrain and seafloor were surveyed using multiple airborne lidar systems from November 2019 to August 2020. The National Oceanic and Atmospheric Administration (NOAA) collected this point cloud data, which includes intensity values, return numbers, scan angles, and time stamps. Data is formatted in LAS 1.4 with ASPRS-standard classifications.
311 square miles of topobathymetric lidar data covering Tampa Bay, Florida, collected by Leading Edge Geomatics for NOAA. The data were acquired from November 22 to December 20, 2019, and are delivered in two blocks totaling 1,788 tiles. The point cloud data is in LAS 1.4 format with classifications for ground, water surface, bathymetric bottom, and other features.