97 datasets found

The YCB object and model set is a benchmark for manipulation research, consisting of 15 object categories and 3D models.

The dataset used in the paper is not explicitly described, but it is mentioned that it is a collection of expert demonstrations for imitation learning tasks.

The dataset consists of 50 simulation videos of a simulated Spot quadruped robot. The videos were recorded for a study on gait preference learning.

The dataset used in the paper is a dual-pendulum environment, which is a continuous action space task.

The dataset used in the paper is the AI2-THOR dataset, which is a 3D indoor environment dataset. The agent must navigate from a random starting position to a pre-specified...

PyBullet is a python module for physics simulation for games, robotics and machine learning.

The Habitat dataset is a large-scale indoor simulator dataset containing 145 semantically-annotated indoor scenes.

The dataset is used for training and testing the Equivariant Diffuser for Generating Interactions (EDGI) algorithm.

The dataset is used for training and testing the Equivariant Diffuser for Generating Interactions (EDGI) algorithm.

Robomimic environment consists of tasks such as lift, can, square, tool-hang, and transport.

D4RL benchmark suite consists of tasks such as locomotion, antmaze, adroit, and kitchen.

The HM3D dataset is a large-scale 3D environment dataset, consisting of 1000 large-scale 3D environments for embodied AI. The dataset is used to evaluate the performance of SLAM...

The dataset used in the paper is a set of demonstrations of a car driving in different directions and speeds.

The dataset used in the paper is a set of demonstrations of a bipedal robot performing different moving behaviors.

The dataset used in the paper is a set of demonstrations with mixed behaviors, where each demonstration is a sequence of states and actions.

PhotoBot is a framework for fully automated photo acquisition based on an interplay between high-level human language guidance and a robot photographer.

The dataset used for training the dm_control environment.

The DeepMind Control Suite is a collection of 20 robotic manipulation tasks, each with 5 different environments and 5 different robot parameters. The tasks are designed to test...

A system for applying sim2real approaches to “in the wild” scenes with realistic visuals, and to policies which rely on active perception using RGB cameras.

The Pendulum swing-up task, the agent tries to keep the pendulum upright and balanced under the constraint of keeping away from unsafe angles. In the Reacher task, the robotic...