A self-supervised learning-based 6-DOF grasp planning method for manipulator

  title={A self-supervised learning-based 6-DOF grasp planning method for manipulator},
  author={Gang Peng and Zhenyu Ren and Hongya Wang and Xinde Li},
To realize a robust robotic grasping system for unknown objects in an unstructured environment, large amounts of grasp data and 3D model data for the object are required, the sizes of which directly affect the rate of successful grasps. To reduce the time cost of data acquisition and labeling and increase the rate of successful grasps, we developed a self-supervised learning mechanism to control grasp tasks performed by manipulators. First, a manipulator automatically collects the point cloud… 
1 Citations
Dex-NeRF: Using a Neural Radiance Field to Grasp Transparent Objects
This work proposes using neural radiance fields (NeRF) to detect, localize, and infer the geometry of transparent objects with sufficient accuracy to find and grasp them securely, and shows that NeRF and Dex-Net are able to reliably compute robust grasps on transparent objects.


PointNetGPD: Detecting Grasp Configurations from Point Sets
Experiments on object grasping and clutter removal show that the proposed PointNetGPD model generalizes well to novel objects and outperforms state-of-the-art methods.
Self-supervised 6D Object Pose Estimation for Robot Manipulation
This work introduces a robot system for self-supervised 6D object pose estimation and improves object segmentation and 6D pose estimation performance, and consequently enables the system to grasp objects more reliably.
Learning ambidextrous robot grasping policies
Dex-Net 4.0 is presented, a substantial extension to previous versions of Dex-Net that learns policies for a given set of grippers by training on synthetic datasets using domain randomization with analytic models of physics and geometry.
Constructing Force- Closure Grasps
  • V.-D. Nguyen
  • Engineering, Computer Science
    Int. J. Robotics Res.
  • 1988
This paper presents fast and simple algorithms for directly constructing force-closure grasps based on the shape of the grasped object, and shows that most nonmarginal equilibriumGrasps are force- closuregrasps.
Self-Supervised Sim-to-Real Adaptation for Visual Robotic Manipulation
  • Rae Jeong, Y. Aytar, +5 authors F. Nori
  • Computer Science
    2020 IEEE International Conference on Robotics and Automation (ICRA)
  • 2020
This work learns a latent state representation implicitly with deep reinforcement learning in simulation, and then adapt it to the real domain using unlabeled real robot data, and proposes a novel such objective, the Contrastive Forward Dynamics loss, which combines dynamics model learning with time-contrastive techniques.
Benchmarking in Manipulation Research: Using the Yale-CMU-Berkeley Object and Model Set
The Yale-Carnegie Mellon University-Berkeley object and model set is presented, intended to be used to facilitate benchmarking in robotic manipulation research and to enable the community of manipulation researchers to more easily compare approaches and continually evolve standardized benchmarking tests and metrics as the field matures.
PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes
This work introduces PoseCNN, a new Convolutional Neural Network for 6D object pose estimation, which is highly robust to occlusions, can handle symmetric objects, and provide accurate pose estimation using only color images as input.
BundleFusion: real-time globally consistent 3D reconstruction using on-the-fly surface re-integration
This work systematically addresses issues with a novel, real-time, end-to-end reconstruction framework, which outperforms state-of-the-art online systems with quality on par to offline methods, but with unprecedented speed and scan completeness.
Deep Learning on Point Sets for 3 D Classification and Segmentation
Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or collections of images. This, however,
Deep hierar chical feature learning on point sets in a metric spac
  • Neural Information Processing Syst ems
  • 2017