41 datasets found

The NuPlan dataset is a closed-loop motion planning benchmark for autonomous vehicles.

KITTI tracking dataset provides 21 training and 29 test sequences. The dataset provides 2D bounding box annotations for cars, pedestrians, and 6 other classes, but only the...

The dataset used in this paper is a set of vehicle models and obstacle avoidance formulations.

The dataset used in this paper is a collection of miles driven data from autonomous vehicles.

The dataset used in this paper is a collection of disengagement events data from autonomous vehicles.

A real-world dataset for LiDAR-based end-to-end navigation, consisting of 32km of driving data with 29km for training and 3km for testing.

The DeFIX dataset is generated by driving a rule-based CARLA autopilot to train an Imitation Learning agent.

TUM-MLS-2016: An annotated mobile lidar dataset of the TUM City Campus for semantic point cloud interpretation in urban areas.

Developing and testing robust autonomy: The university of sydney campus data set.

The Argoverse dataset is a large dataset of real-world outdoor driving scenes.

The dataset used in the paper is a set of demonstrations for an autonomous driving task, where the robot needs to maneuver through slower traffic.

The dataset contains human driving recordings in roads and parking lots.

Established an object-centric multi-view LiDAR dataset, dubbed NeRF-MVL, with carefully calibrated sensor poses and gathering multi-LiDAR sensor data from real autonomous vehicles.

The Waymo dataset is a LiDAR-based semantic segmentation dataset, which consists of 798 sequences for training and 202 for validation.

The Udacity dataset has images recorded while driving on highways and residential roads (with and without lane markings) in clear weather during daytime.

The KITTI odometry dataset is a collection of 22 sequences, containing point clouds, images, and GPS recordings of inner-city traffic, residential areas, highway scenes, and...

The KITTI-360 dataset is an extension of the KITTI dataset, containing 10 new sequences recorded in 2013, with a focus on 360-degree views.

The dataset used in this paper is a human demonstration dataset for autonomous vehicles, consisting of images from a center camera.

The WOMD dataset is a large-scale interactive motion forecasting dataset for autonomous driving, which includes 2 million agents and 6 motion trajectories for 8 seconds in the...

The Trajnet++ benchmark provides a fixed data split and unified pre-processing for these datasets.