Loading...
Loading...
Self-driving perception, LiDAR/camera fusion, trajectory prediction, drone perception, robot manipulation
2,023 datasets
NuScenes is a dataset for autonomous driving research, published on Kaggle. The dataset's specific scale, such as the number of scenes or annotations, is not detailed in the available metadata. Its original creators and temporal coverage are also unspecified in this listing.
TRACE-A_AircraftRemoteSensing_DC8_DIAL_Data is Differential Absorption Lidar (DIAL) data collected onboard a NASA DC-8 aircraft during the Transport and Atmospheric Chemistry near the Equator - Atlantic (TRACE-A) campaign. The mission was conducted from September 21 to October 24, 1992, as part of NASA's Global Tropospheric Experiment, with the objective of determining the source of high ozone concentrations over the Atlantic Ocean. The DC-8 was equipped with 19 instruments, including the DIAL which measured ozone, aerosols, and ozone column, alongside other instruments measuring gases like CO2, CH4, and N2O.
1989 to 1993 data from the CEDAR database contains lidar measurements of photocounts, relative neutral number density, and sodium or iron density. The dataset was collected by University of Illinois and Colorado State University lidar systems at locations including Arecibo, Hawaii, Urbana, and Fort Collins. It is maintained by the National Center for Atmospheric Research (NCAR) High Altitude Observatory (HAO).
Lidar In-Space Technology Experiment (LITE) L1 data contain vertical profile measurements collected by a three-wavelength lidar aboard the space shuttle Discovery during the STS-64 mission in September 1994. NASA's LARC_ASDC processed the high-rate telemetry to create geolocated profiles of clouds, aerosols, and atmospheric properties. The dataset covers the mission period from September 9 to September 20, 1994.
Lidar Atmospheric Sensing Experiment (LASE) data from the 1998 Convection and Moisture Experiment (CAMEX-3) campaign. The dataset contains airborne DIAL system measurements of water vapor and aerosol profiles. It was collected by NASA's LARC_ASDC organization during the study of Hurricanes Bonnie, Danielle, Earl, and Georges.
Co-aligned hyperspectral and LiDAR data covers four sites of European beech forest in Germany's RhÓ§n Biosphere Reserve. Data was collected via UAV in September 2020 to assess canopy damage from a 2018/2019 extreme drought event. Hyperspectral images have approximately 5cm pixel resolution.
DAAD-X is a video-based explanations dataset derived from the DAAD dataset for driver intention prediction. It contains explanations for each maneuver instance, intended to advance research into explainable autonomous driving and ADAS systems. The dataset was created by Skyrmion and was last updated on March 19, 2026.
Dinov3_denseuav is a dataset hosted on Kaggle. The platform tags indicate it contains UAV imagery for computer vision tasks, likely object detection. The dataset's specific content, size, and origin are not detailed in the provided metadata.
BlueTopo is a definitive nationwide model of seafloor and lakebed depths for navigationally significant U.S. waters, compiled by NOAA's Office of Coast Survey. It integrates bathymetric data from NOAA and U.S. Army Corps of Engineers surveys, lidar, and external submissions, with gaps filled using the Global Multi-Resolution Topography model. The dataset includes metadata with quality metrics to guide appropriate use.
2017-18 data collected by a fleet of manually driven Ford Fusion vehicles on a 66 km route in Michigan. The dataset captures seasonal variations in weather, lighting, construction, and traffic across urban, freeway, airport, and suburban scenarios. It was created by Ford Motor Company and includes raw sensor data, calibration, pose trajectories, and 3D maps in ROS bag format.
Comprising ablation study results measuring mIoU (%) for the Potsdam, Vaihingen, UAVid, and MSIDBG remote sensing image datasets. The data is provided in an XLS file with a size of 5.5 KB. It was authored by Xin Wang and last updated in March 2026.
Featuring segmentation results from multiple models applied to the UAVid dataset. The data is stored in an XLS file sized 9.5 KB. It was authored by Xin Wang and last updated in March 2026.
Featuring results from nonparametric tests comparing UAV unit time to road traffic unit time at various time points. The data is provided in an XLS file of 5.5 KB, authored by Xingbo Long and last updated in March 2026. The specific row count and column structure are not detailed in the input.
This dataset compares road traffic unit time measurements from Tencent Map and drone surveillance at nine different time points over 30 consecutive days. It includes results of normality tests for the data. The dataset is provided in an XLS file with a size of 5.5 KB.
LET Dataset is a collection of real-world multi-task data from the Kuavo 4 Pro full-size humanoid robot, covering multiple scenarios and operation types. It was created by LejuRobotics and last updated on March 13, -2026. The dataset is designed to support scalable robot learning in real environments.
Four intensive field observation periods collected lidar data on cirrus and marine stratocumulus clouds between 1986 and 1992. The dataset contains raw lidar return signals from coordinated satellite, airborne, and surface observations, processed by the University of Utah and archived by NASA's LARC ASDC. The primary goal was to improve cloud and radiation parameterizations used in general circulation models.
University of Utah lidar data from the First ISCCP Regional Experiment (FIRE) Cirrus Phase II field campaign. The dataset contains raw, background-subtracted lidar return signals for studying cirrus cloud properties and life cycles. Observations were conducted during an intensive field period from November 13 to December 7, 1991.
November 13 to December 7, 1991 data from the Second FIRE Cirrus intensive field observation in Coffeyville, Kansas. The dataset contains images of cirrus clouds captured by a High Spectral Resolution Lidar, showing backscatter and depolarization ratio. It was collected by the LARC_ASDC organization to study cloud properties and interactions for improving climate models.
October 1986 data from the NASA ER-2 Cloud Lidar System during the First ISCCP Regional Experiment (FIRE) Cirrus campaign. It contains calculated cloud top height and ground height measurements. The data was collected by NASA's Langley Research Center Atmospheric Science Data Center (LARC_ASDC).
Four intensive field campaigns between 1986 and 1992 collected coordinated airborne, satellite, and surface observations to study cirrus and marine stratocumulus cloud systems. The Cloud Lidar System aboard the NASA ER-2 airplane recorded cloud altitudes, layer boundaries, and geophysical location. Data was produced by the LARC_ASDC organization.