mlsanityData to 7 Oct 2026

Self-supervised 6-DoF Robot Grasping by Demonstration via Augmented Reality Teleoperation System

arXiv 2404.03067 ↗First posted 3 Apr 2024cs.RO cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Most existing 6-DoF robot grasping solutions depend on strong supervision on grasp pose to ensure satisfactory performance, which could be laborious and impractical when the robot works in some restricted area. To this end, we propose a self-supervised 6-DoF grasp pose detection framework via an Augmented Reality (AR) teleoperation system that can efficiently learn human demonstrations and provide 6-DoF grasp poses without grasp pose annotations. Specifically, the system collects the human demonstration from the AR environment and contrastively learns the grasping strategy from the demonstration. For the real-world experiment, the proposed system leads to satisfactory grasping abilities and learning to grasp unknown objects within three demonstrations.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 52 references that are in the map. First posted on arXiv 3 Apr 2024.

Builds on

24 of 52 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  4. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 584
  5. 2020ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulationcited by 249
  6. 2022AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domainscited by 205
  7. 2023AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation Systemcited by 136
  8. 2019DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm Systemcited by 105
  9. 2015Benchmarking in Manipulation Research: The YCB Object and Model Set and Benchmarking Protocolscited by 98
  10. 2021Volumetric Grasping Network: Real-time 6 DOF Grasp Detection in Cluttercited by 94
  11. 2022You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstrationcited by 79
  12. 2022Robotic Telekinesis: Learning a Robotic Hand Imitator by Watching Humans on Youtubecited by 79
12 more
  1. 2022Deep Learning Approaches to Grasp Synthesis: A Reviewcited by 69
  2. 2016Unsupervised Perceptual Rewards for Imitation Learningcited by 64
  3. 2022Holo-Dex: Teaching Dexterity with Immersive Mixed Realitycited by 52
  4. 2019S4G: Amodal Single-view Single-Shot SE(3) Grasp Detection in Cluttered Scenescited by 51
  5. 2021CaTGrasp: Learning Category-Level Task-Relevant Grasping in Clutter from Simulationcited by 49
  6. 2020PointNet++ Grasping: Learning An End-to-end Spatial Grasp Generation Algorithm from Sparse Point Cloudscited by 39
  7. 2021RGB Matters: Learning 7-DoF Grasp Poses on Monocular RGBD Imagescited by 38
  8. 2020Grasp Proposal Networks: An End-to-End Solution for Visual Learning of Robotic Graspscited by 22
  9. 2021Vision-driven Compliant Manipulation for Reliable, High-Precision Assembly Taskscited by 18
  10. 2021Simultaneous Semantic and Collision Learning for 6-DoF Grasp Pose Estimationcited by 14
  11. 2020Human-Robot Interaction in a Shared Augmented Reality Workspacecited by 10
  12. 2022Learning Sensorimotor Primitives of Sequential Manipulation Tasks from Visual Demonstrationscited by 6

Built on by

Not cited yet.