基于视觉的机器人抓取相关论文和代码
The essential information to grasp the target object is the 6D gripper pose in the camera coordinate, which contains the 3D gripper position and the 3D gripper orientation to execute the grasp. Within the methods of vision-based robotic grasping, the estimation of 6D gripper poses varies aiming at different grasp manners, which can be categorized into 2D planar grasp and 6DoF grasp.
2D planar grasp means that the target object lies on a plane workspace and the grasp is constrained from one direction. The essential information is simplified from 6D into 3D, which are the 2D in-plane positions and 1D rotation angle. There exist methods of evaluating grasp contact points and methods of evaluating grasp oriented rectangles.
6DoF grasp means that the gripper can grasp the object from various angles in the 3D domain, and the essential 6D gripper pose could not be simplified. Based on whether the grasp is conducted on the complete shape or on the single-view point cloud, methods are categorized into methods based on the partial point cloud and methods based on the complete shape. Methods based on the partial point cloud contains methods of estimating candidate grasps and methods of transferring grasps from existing grasps database. Methods based on the complete shape contains methods of estimating 6D object pose and methods of shape completion. Most of current 6DoF grasp methods aim at known objects where the grasps could be precomputed manually or by simulation, and the problem is thus transformed into a 6D object pose estimation problem.
Besides, most of the robotic grasping approaches require the target object’s location in the input data first. This involves three different stages: object localization without classification, object detection and object instance segmentation. Object localization without classification only outputs the potential regions of the target objects without knowing their categories. Object detection provides bounding boxes of the target objects with their categories. Object instance segmentation further provides pixel or point-level regions of the target objects with their categories.
I summarize all above kinds of methods in this repository, and hope to present a big picture for friends work on vision-based robotic grasping. The table of content is listed as follows.
Thank Hatim Wen for modifying all links to the pdf files and writing a convenient program to download the papers.
python download.py to start your download process.NOTE:
Before you use, it's better read and change the codes.
Specifically, you should change the value of `name` in `download.py`(line 18) into the md file you split, e.g. '6DoF Grasp.md'.
[Foundations and Trends in Robotics] 2020-Semantics for Robotic Mapping, Perception and Interaction: A Survey, [paper]
[AIRE] 2020-Vision-based Robotic Grasp Detection From Object Localization, Object Pose Estimation To Grasp Estimation: A Review, [paper]
[arXiv] 2020-Affordances in Robotic Tasks - A Survey, [paper]
[arXiv] 2019-A Review of Robot Learning for Manipulation- Challenges, Representations, and Algorithms, [paper]
[arXiv] 2018-The Limits and Potentials of Deep Learning for Robotics, [paper]
[MTI] 2018-Review of Deep Learning Methods in Robotic Grasp Detection, [paper]
[ToR] 2016-Data-Driven Grasp Synthesis - A Survey, [paper]
[RAS] 2012-An overview of 3D object grasp synthesis algorithms - A Survey, [paper]
[BMVC] A buyer’s guide to conic fitting, [paper] [code]
[IJGIG] Algorithms for the reduction of the number of points required to represent a digitized line or its caricature, [paper] [code]
Survey papers:
[arXiv] 2020-RGB-D Salient Object Detection: A Survey, [paper] [project]
[arXiv] 2019-Salient object detection in the deep learning era: An in-depth survey, [paper]
[CVM] 2014-Salient object detection: A survey, [paper]
2020:
[ECCV] Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detection, [paper]
[ECCV] Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detection, [paper]
[ECCV] Cross-Modal Weighting Network for RGB-D Salient Object Detection, [paper]
[arXiv] Bilateral Attention Network for RGB-D Salient Object Detection, [paper]
[arXiv] Salient Object Detection Combining a Self-attention Module and a Feature Pyramid Network, [paper]
[arXiv] JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection, [paper]
[arXiv] UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders, [paper]
[arXiv] Cross-layer Feature Pyramid Network for Salient Object Detection, [paper]
[arXiv] Depth Potentiality-Aware Gated Attention Network for RGB-D Salient Object Detection, [paper]
[arXiv] Weakly-Supervised Salient Object Detection via Scribble Annotations, [paper]
[arXiv] Highly Efficient Salient Object Detection with 100K Parameters, [paper]
[arXiv] Global Context-Aware Progressive Aggregation Network for Salient Object Detection, [paper]
[arXiv] Adaptive Graph Convolutional Network with Attention Graph Clustering for Co-saliency Detection, [paper]
2019:
[ICCV] Employing deep part-object relationships for salient object detection, [[paper](http://openaccess.
暂无开放 Issues，或尚未同步最近议题。