-
Constrained Grasp Diffusion Fields
Constrained 6-DoF Grasp Generation on Complex Shapes for Improved Dual-Arm Manipulation -
D-Cubed: Latent Diffusion Trajectory Optimisation for Dexterous Deformable Ma...
A task-agnostic play dataset of robot hand trajectories Dplay is collected per robot platform, allowing its reuse across multiple tasks. -
Multi-step Pick and Place
The Multi-step Pick and Place dataset is a collection of images and labels used for training a visual representation that can bridge the sim2real visual gap. -
Stack Object
The Stack Object dataset is a collection of images and labels used for training a visual representation that can bridge the sim2real visual gap. -
Lang4Sim2Real
The Lang4Sim2Real dataset is a collection of image-language pairs used for training a visual representation that can bridge the sim2real visual gap. -
EuRoC MAV Dataset
A dataset for visual odometry, containing 11 sequences with provided ground-truth poses. -
Oxford Radar RobotCar dataset
The Oxford Radar RobotCar dataset is a radar extension to the Oxford RobotCar dataset, containing radar observations of a vehicle in various scenarios. -
TidySim: A 3D object rearrangement simulator
The dataset is a collection of 75 user-generated scenes for a tidying task, where users are asked to arrange objects in a tidy manner. -
NAO robot database
The NAO robot database published in [1] which includes images taken in various game situations and under different illumination conditions. -
RIO-10 dataset
The RIO-10 dataset contains 10 real indoor environments with varying lighting conditions, camera positions, and object arrangements. -
D3Fields: Dynamic 3D Descriptor Fields for Zero-Shot Generalizable Robotic Ma...
D3Fields — dynamic 3D descriptor fields for zero-shot generalizable robotic manipulation tasks -
Dex-NeRF: Using a Neural Radiance Field to Grasp Transparent Objects
Synthetic datasets of transparent objects for training NeRF models. -
Distilled Feature Fields Enable Open-Ended Manipulation
The dataset used in the paper is a collection of RGB images of a tabletop scene, along with their corresponding camera poses and 3D geometry. -
Cornell Grasp Detection Data Set
The Cornell Grasp Detection Data Set consists of 1035 images of 280 different objects, with several images taken of each object by different orientations or poses. -
Amazon Picking Challenge 2016 Dataset
The dataset used in the Amazon Picking Challenge 2016, a vision-based robotic picking system developed by Team Applied Robotics. -
Shadow Hand Dataset
A dataset of 1140 grasp trajectories for a robotic hand interacting with a turntable. -
MPL Hand Dataset
A dataset of 132 sensor readings over 100 steps into the future for a robotic hand interacting with an unknown and uncertain external world. -
Robot Trajectories Dataset
The dataset consists of 80,000 robot trajectories collected via human teleoperation, with 2,800 demonstrations labeled by crowd-sourced language annotators.
