Browsing by Author "Calandra, Roberto"

Now showing 1 - 2 of 2
  • Item
    Open Access
    Learning Gentle Grasping Using Vision, Sound, and Touch
    (Technische Universität Dresden, 2025-03-11) Nakahara, Ken; Calandra, Roberto
    This dataset contains 1,500 robotic grasps collected for the paper of Learning Gentle Grasping Using Vision, Sound, and Touch. Additionally, we provide a description of this dataset and Python scripts to visualize the data and process raw data into a training dataset for a PyTorch model. The robotics system used consists of a multi-fingered robotic hand (16-DoF, Allegro Hand v4.0), 7-DoF robotic arms (xArm7), DIGIT tactile sensors, an RGB-D camera (Intel RealSense D435i), and a commodity microphone. The target object is a toy that emits sound when grasped strongly.
  • Item
    Open Access
    The Feeling of Success: Does Touch Sensing Help Predict Grasp Outcomes?
    (Technische Universität Dresden, 2025-02-16) Calandra, Roberto; Owens, Andrew; Upadhyaya, Manu; Yuan, Wenzhen; Lin, Justin; Adelson, Edward H.; Levine, Sergey
    This dataset contains 9269 robotic grasps collected from 106 objects, and their corresponding outcome. The hardware used consists of a 7-DoF Sawyer arm, a Weiss WSG-50 parallel gripper, one Microsoft Kinect 2, and two GelSight sensors, one for each finger.