285 datasets found

Groups: Robotics Organizations: No Organization

Filter Results

  • Vision-and-Language Navigation

    The Vision-and-Language Navigation (VLN) task gives a global natural sentence I = {w0,..., wl} as an instruction, where wi is a word token while the l is the length of the...

  • Mujoco tasks

    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.

  • Robot Gait Preference Learning Dataset

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

  • Pybullet Multigoal

    A dataset for robotic manipulation tasks, including ChestPush, ChestPickAndPlace, and BlockStack.

  • Mini-Grid

    A dataset for multi-step sparse reward tasks, including gridworld tasks and robotic manipulation tasks.

  • ARS: Augmented Reality Semi-automatic-labeling

    Two novel datasets are created using the ARS pipeline, one on electromechanical components (industrial scenario) and one on fruits (daily-living scenario).

  • QCAT dataset

    The proposed semi-supervised method for terrain classification of legged robots using force sensor and IMU sensor recorded historical motion data.

  • Generalization in Deep Reinforcement Learning for Robotic Navigation by Rewar...

    A novel reward function for reinforcement learning and a Soft Actor-Critic algorithm to train a DRL policy in the context of local navigation for autonomous mobile robots in...

  • PhyPartNet

    PhyPartNet is a large-scale 3D-linguistic dataset for robotic grasping, featuring 195K object instances with varying physical properties and human preferences.

  • Falling-Shoe

    A synthetic dataset of shoes for training and testing the proposed method.

  • Centered-Shoe

    A unified object-centric implicit representation that can be used for RGB and depth novel view rendering, 3D reconstruction, and proposing stable grasps.

  • Dual Pendulum Environment

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

  • iCubWorld Transformations

    iCubWorld Transformations (iCWT): a dataset for object recognition and manipulation

  • Robotic Ant Maze

    The dataset used in this paper is a collection of high-dimensional RGB images of environments, where each image represents a trajectory of observations generated during the...

  • Redundant Arm

    The dataset used in this paper is a collection of high-dimensional RGB images of environments, where each image represents a trajectory of observations generated during the...

  • HardMaze

    The dataset used in this paper is a collection of high-dimensional RGB images of environments, where each image represents a trajectory of observations generated during the...

  • CollectBall

    The dataset used in this paper is a collection of high-dimensional RGB images of environments, where each image represents a trajectory of observations generated during the...

  • Billiard, Maze, Ant, Kuka

    The dataset used in this paper is a collection of high-dimensional RGB images of environments, where each image represents a trajectory of observations generated during the...

  • Mingling robots

    The dataset of a real-life collective motion scenario of a mingling robots swarm.

  • Cross-Scale Dataset

    The cross-scale dataset is built from the Scott Reef 25 dataset (2009) provided by Australian Centre for Field Robotics (ACFR). The dataset contains 1000 data tuples to split...