39 datasets found

A dataset for view synthesis, part segmentation, and articulated pose estimation of articulated objects.

The Behavior-1k dataset contains 1,000 everyday activities and realistic simulation.

NOIR is a general-purpose, intelligent brain-robot interface system that enables humans to command robots to perform everyday activities through brain signals.

The dataset used in the paper is an adapted version of the Atari baseline Breakout, and a simulated Robot pushing domain.

The dataset used in the paper is a robotic pushing domain with negative reward regions, and variants of the video game Breakout.

The dataset used in the paper for one-shot visual imitation via attributed waypoints and demonstration augmentation.

The dataset used in the paper for one-shot visual imitation via attributed waypoints and demonstration augmentation.

The dataset used in the paper for one-shot visual imitation via attributed waypoints and demonstration augmentation.

The dataset used in the paper for one-shot visual imitation via attributed waypoints and demonstration augmentation.

OLAF is a learning system that allows everyday users to teach a robot using verbal corrections when the robot makes mistakes.

The dataset used in the paper for learning preference-agnostic representations from trajectory similarity queries.

The RLBench dataset is used for robot learning benchmark and learning environment.

The dataset is used to train the Make-An-Agent model, a novel policy parameter generator that leverages the power of conditional diffusion models for behavior-to-policy generation.

The dataset is used to train the Make-An-Agent model, a novel policy parameter generator that leverages the power of conditional diffusion models for behavior-to-policy generation.

The dataset is used to train the Make-An-Agent model, a novel policy parameter generator that leverages the power of conditional diffusion models for behavior-to-policy generation.

Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning.

A synthetic dataset of a Franka Emika Panda robot arm manipulating objects in four visually distinct 3D environments.

The Open X-Embodiment Collaboration dataset is a collection of robotic learning datasets and RT-X models.

The Fleet-Tools benchmark is a dataset for robotic tool-use tasks.

Training general robotic policies from heterogeneous data for different tasks is a significant challenge. Existing robotic datasets vary in different modalities such as color,...