Loading...
Loading...
Self-driving perception, LiDAR/camera fusion, trajectory prediction, drone perception, robot manipulation
2,016 datasets
Four intensive field observation periods between 1986 and 1992 collected this dual-channel polarization sensitive lidar data. The Langley Research Center instrument was designed to monitor cloud properties between 3 km and 18 km altitude to improve general circulation models. NASA produced this data to investigate the life cycles and radiative properties of cirrus and marine stratocumulus cloud systems.
MIPS 915 MHz Doppler Wind Profiler data provides 15-minute averaged 3-D wind profiles, radial velocity, and backscatter intensity measurements. The dataset was collected by the University of Alabama in Huntsville's mobile atmospheric profiling system during the CAMEX-4 campaign. It is hosted by NASA's GHRC DAAC.
LASE_AFWEX data are Lidar Atmospheric Sensing Experiment water vapor and aerosol data measurements taken during ARM-FIRE Water Vapor Experiment. The LASE ARM-FIRE Water Vapor Experiment (AFWEX) field experiment was conducted from November 27 - December 15, 2000 at the ARM Southern Great Plains Cloud and Radiation Testbed (CART) Site site in Lamont, Oklahoma. LASE airborne lidar produces measurements of aerosols and water vapor vertical profiles from the aircraft altitude (6-8 km) down to the surface.
CALIPSO Lidar Level 3 Cloud Occurrence Data, Standard V1-00 reports global distributions of clouds on a uniform spatial grid derived from CALIOP instrument data. The product was generated with a temporal average of one month, but its generation and distribution ended in December 2016 due to laser degradation. CALIPSO is a joint NASA and CNES satellite mission launched in 2006, part of the A-Train constellation for studying clouds and aerosols.
1-meter resolution raster layers represent the canopy height model and digital terrain model for the Sabah Biodiversity Experiment in Malaysia. The Environmental Information Data Centre created these models from airborne LiDAR point cloud data collected in 2020. Data were collected to assess the effectiveness of restoration interventions for logged tropical forests.
Washington Island, Wisconsin, and the shores of Green Bay are covered by approximately 219 square miles of topobathy lidar data. The National Oceanic and Atmospheric Administration collected this data using a CZMIL Super Nova system between July 19 and August 16, 2022. It consists of 2,630 LAS tiles and includes classified points for ground, water surface, and bathymetric bottom.
A physically-grounded humanoid locomotion dataset created by Luckyt1, leveraging large-scale human motion data. The dataset was curated to overcome physical artifacts through physics-constrained retargeting, resulting in a high-quality resource for robotics research.
3,000 labeled synthetic samples for classifying coordinated drone swarm behavior and inferring tactical intent from aggregate radar observables. The dataset was created by electricsheepafrica and last updated on April 14, 2026. It is parameterized from published Sub-Saharan Africa literature and is not based on real observations.
High-altitude drone images are provided for the task of vehicle detection. The description suggests the images contain small vehicles and are captured under conditions involving clouds and fog. The dataset is hosted on Kaggle, but details regarding its size, authorship, and update history are unknown.
Code authored by Shunsuke Koseki generates 3D bipedal walking gaits and performs perturbation experiments. The simulation software is available under a CC-BY-4.0 license. The repository was last updated on May 18, 2026.
Projects proposed, in progress, or completed as part of the annual Iran Humanitarian Response Plans (HRPs) or other Humanitarian Programme Cycle plans. The data is provided by OCHA Humanitarian Programme Cycle Tools (HPC Tools) and was last updated on March 16, 2026. The original data is available on the HPC Tools platform.
Level curves with a 1-meter equidistance derived from a LiDAR survey conducted in 2024. The dataset includes attributes for a unique ID, curve subtype, and elevation value in meters. It is provided by the Government and Municipalities of Québec and was last updated in March 2026.
PhysicalAI-Autonomous-Vehicle-Cosmos-Drive-Dreams is a dataset for autonomous vehicle research, hosted by author fuzirui on Hugging Face. The dataset was last updated on April 12, 2026. The description mentions downloadable components including high-definition maps, lidar data, and synthetic data.
Physics-informed aerodynamic parameters for UAV prediction and optimization. The dataset is hosted on Kaggle, but the author, organization, and specific data volume are unknown. The last update date and license information are also not provided.
Tokyo, Japan is the geographic scope of this sample subset of a large-scale autonomous driving dataset. The data comprises over 100 hours of driving data, is stored in nuScenes format, and was authored by turing-motors. The dataset page was last updated on 2026-03-27.
DroneVLA DFR Episodes is the first open language-conditioned action dataset for drone first response. The dataset was published on Kaggle, but details about its author, organization, and specific size are not provided. Its last update date and licensing information are also unknown.
Six high-resolution photomosaic TIFF images document benthic communities across six 10m x 10m reef plots at Cheeca Rocks Coral Reef in Islamorada, Florida. The dataset was produced by NOAA's Coral Reef Conservation Program as part of the National Coral Reef Monitoring Program on July 11, 2016. Each mosaic is a composite of 1500-3000 individual underwater images, stitched together using Agisoft Photoscan to create a landscape view of the reef.
Madagascar highlands data from a study analyzing the effect of age and fertilization on Eucalyptus robusta biomass. The collection includes destructive biomass measurements for 64 trees, forest inventory data for 2598 trees across 22 plots, and UAV-derived canopy data from two flights over six plots. Data was collected between 2017 and 2021 as part of the EU-DIABE project for a doctoral thesis.
Airborne LiDAR elevation data collected on September 18, 1999, following Hurricane Floyd's landfall in North Carolina. The data covers the coastline from South Carolina into Virginia, measuring ground elevation from the low water line to the base of sand dunes. The dataset was produced by the NOAA Office for Coastal Management as part of the ALACE project.
PrivateMap-Bench is a benchmark dataset for evaluating privacy leakage and utility loss in indoor Simultaneous Localization and Mapping (SLAM) map sharing. It contains sanitized SLAM artifacts, processed results, and executable code for reproducing the NeurIPS 2026 processed-artifact benchmark. The benchmark evaluates floor-plan, room-graph, trajectory, and routine leakage, as well as map compactness and navigation utility across 15 TurtleBot4 runs from three indoor layout variants.