Filters








102 Hits in 7.2 sec

Vision-based Robotic Grasp Detection From Object Localization, Object Pose Estimation To Grasp Estimation: A Review [article]

Guoguang Du, Kai Wang, Shiguo Lian, Kaiyong Zhao
2020 arXiv   pre-print
Grasp estimation includes 2D planar grasp methods and 6DoF grasp methods, where the former is constrained to grasp from one direction.  ...  Some grasp estimation methods need not object localization and object pose estimation, and they conduct grasp estimation in an end-to-end manner.  ...  The grasp qualities are then measured using the Grasp Quality-CNN network, and the one with the highest quality will be selected as the final grasp.  ... 
arXiv:1905.06658v2 fatcat:6u3k2ltwifaanjpp2nkayyj2f4

Multi-Fingered Grasp Planning via Inference in Deep Neural Networks [article]

Qingkai Lu, Mark Van der Merwe, Balakumar Sundaralingam, Tucker Hermans
2020 arXiv   pre-print
Our work is the first to directly plan high quality multi-fingered grasps in configuration space using a deep neural network without the need of an external planner.  ...  We train a voxel-based 3D convolutional neural network to predict grasp success probability as a function of both visual information of an object and grasp configuration.  ...  Grasp Data Collection We conduct all training and experiments using the fourfingered, 16 DOF Allegro hand mounted on a Kuka LBR4 7 DOF arm.  ... 
arXiv:2001.09242v2 fatcat:kpoa5vzwynfwhj2lhv3utveeju

DemoGrasp: Few-Shot Learning for Robotic Grasping with Human Demonstration [article]

Pengyuan Wang, Fabian Manhardt, Luca Minciullo, Lorenzo Garattoni, Sven Meie, Nassir Navab, Benjamin Busam
2021 arXiv   pre-print
Subsequently, we complete missing parts of the reconstructed object shape and estimate the relative transformation between the reconstruction and the visible object in the scene.  ...  To overcome these shortcomings, we propose to teach a robot how to grasp an object with a simple and short human demonstration.  ...  Fox, “6-dof graspnet: Variational of DemoGrasp, we run the teaching phase for our simulated grasp generation for object manipulation,” in ICCV, 2019. grasp experiments with decreasing amount  ... 
arXiv:2112.02849v1 fatcat:kpwrzj6r4re6rodinzlrer25si

Learning to Grasp 3D Objects using Deep Residual U-Nets [article]

Yikun Li, Lambert Schomaker, S. Hamidreza Kasaei
2020 arXiv   pre-print
It devised to plan 6-DOF grasps for any desired object, be efficient to compute and use, and be robust against varying point cloud density and Gaussian noise.  ...  Grasp synthesis is one of the challenging tasks for any robot object manipulation task. In this paper, we present a new deep learning-based grasp synthesis approach for 3D objects.  ...  [3] used a synthetic dataset to train a Grasp Quality Convolutional Neural Network (GQ-CNN) model, which can predict the probability of success of grasps from depth images. Choi et al.  ... 
arXiv:2002.03892v2 fatcat:562l2wur7za75l3l6y7bv22k6y

Grasp Planning and Visual Servoing for an Outdoors Aerial Dual Manipulator

Pablo Ramon-Soria, Begoña Arrue Ulles, Anibal Ollero Baturone
2019 Engineering  
This paper covers three principal aspects for this task: object detection and pose estimation, grasp planning, and in-flight grasp execution.  ...  A three-dimensional (3D) model of the object is then used to estimate an arranged list of good grasps for the aerial manipulator.  ...  Acknowledgement This work was carried out in the framework of the AEROARMS (SI-1439/2015) EU-funded project and the national project ARMEXTENDED (DPI2017-89790-R).  ... 
doi:10.1016/j.eng.2019.11.003 fatcat:hx4fbi6zx5evbalceg3xbbf7gi

kPAM: KeyPoint Affordances for Category-Level Robotic Manipulation [article]

Lucas Manuelli, Wei Gao, Peter Florence, Russ Tedrake
2019 arXiv   pre-print
Using this formulation, we factor the manipulation policy into instance segmentation, 3D keypoint detection, optimization-based robot action planning and local dense-geometry-based action execution.  ...  Existing manipulation pipelines typically specify the desired configuration as a target 6-DOF pose and rely on explicitly estimating the pose of the manipulated objects.  ...  B.1 3D Reconstruction and Masking Here we give a brief overview of the approach used to generate the 3D reconstruction, more details can be found in [4].  ... 
arXiv:1903.06684v2 fatcat:gaghpp3ukjg7xad3u35yplur24

The State of Lifelong Learning in Service Robots:

S. Hamidreza Kasaei, Jorik Melsen, Floris van Beers, Christiaan Steenkist, Klemen Voncina
2021 Journal of Intelligent and Robotic Systems  
Nowadays, robots are able to recognize various objects, and quickly plan a collision-free trajectory to grasp a target object in predefined settings.  ...  Therefore, apart from batch learning, the robot should be able to continually learn about new object categories and grasp affordances from very few training examples on-site.  ...  ., [138] proposed an approach to plan 6-DoF grasps for any desired object in a cluttered scene from partial point cloud observations.  ... 
doi:10.1007/s10846-021-01458-3 fatcat:eeunivdvmrcg3piyx3r3pdsviq

The State of Lifelong Learning in Service Robots: Current Bottlenecks in Object Perception and Manipulation [article]

S. Hamidreza Kasaei, Jorik Melsen, Floris van Beers, Christiaan Steenkist, Klemen Voncina
2021 arXiv   pre-print
Nowadays, robots are able to recognize various objects, and quickly plan a collision-free trajectory to grasp a target object in predefined settings.  ...  Therefore, apart from batch learning, the robot should be able to continually learn about new object categories and grasp affordances from very few training examples on-site.  ...  ., [122] proposed an approach to plan 6-DoF grasps for any desired object in a cluttered scene from partial point cloud observations.  ... 
arXiv:2003.08151v3 fatcat:ks4t3qfq3bhszgbb6lzrwwq3iq

Depth Image–Based Deep Learning of Grasp Planning for Textureless Planar-Faced Objects in Vision-Guided Robotic Bin-Picking

Ping Jiang, Yoshiyuki Ishihara, Nobukatsu Sugiyama, Junji Oaki, Seiji Tokura, Atsushi Sugahara, Akihito Ogawa
2020 Sensors  
Our method uses a deep convolutional neural network (DCNN) model that is trained on 15,000 annotated depth images synthetically generated in a physics simulator to directly predict grasp points without  ...  Further, we propose a surface feature descriptor to extract surface features (center position and normal) and refine the predicted grasp point position, removing the need for texture features for vision-guided  ...  [32, 33] proposed Grasp-Quality CNN (GQ-CNN) to predict grasp robustness and to rank most grasp points.  ... 
doi:10.3390/s20030706 pmid:32012874 pmcid:PMC7038393 fatcat:kw4amlhmxbbvfo7um2calp54oa

In vivo human-like robotic phenotyping of leaf traits in maize and sorghum in greenhouse

Abbas Atefi, Yufeng Ge, Santosh Pitla, James Schnable
2019 Computers and Electronics in Agriculture  
An Image processing technique and deep learning method were used to identify grasping points on leaves and stems, respectively. The systems were tested in a greenhouse using maize and sorghum plants.  ...  The robotic systems comprised of a four degree of freedom (DOF) robotic manipulator and a Time-of-Flight (TOF) camera.  ...  The path planning technique can be used to find the optimal grasping path without hitting the plant to minimize the time for stem grasping process.  ... 
doi:10.1016/j.compag.2019.104854 fatcat:ku47tqb4srg2risrs4ukqq7rqi

Latest Datasets and Technologies Presented in the Workshop on Grasping and Manipulation Datasets [article]

Matteo Bianchi, Jeannette Bohg, Yu Sun
2016 arXiv   pre-print
The workshop clearly displayed the importance of quality datasets in robotics and robotic grasping and manipulation field.  ...  This summary servers as a review of recent developments in data collection in grasping and manipulation.  ...  the instruments 6-DOF motion using NaturalPoint OptiTrack MoCap.  ... 
arXiv:1609.02531v1 fatcat:eh55sor6mfc6pekm3r75bpwxcm

GKNet: grasp keypoint network for grasp candidates detection [article]

Ruinian Xu, Fu-Jen Chu, Patricio A. Vela
2021 arXiv   pre-print
Follow-up experiments on a manipulator evaluate GKNet using 4 types of grasping experiments reflecting different nuisance sources: static grasping, dynamic grasping, grasping at varied camera angles, and  ...  The two dominant approaches design either grasp-quality scoring or anchor-based grasp recognition networks.  ...  Likewise, identifying a means to translate the 2D grasp representation to a full 3D grasp pose would remove the need for a top-down grasp and permit richer manipulation from more varied viewpoints.  ... 
arXiv:2106.08497v3 fatcat:453hdniyanbyborxg66inxxrc4

Robotic grasp detection based on image processing and random forest

Jiahao Zhang, Miao Li, Ying Feng, Chenguang Yang
2019 Multimedia tools and applications  
Firstly, an improved graph segmentation approach is used to do objects detection and it can separate objects from the background directly and fast.  ...  The model is mainly used to score every element in our candidate grasps set and the one gets the highest score will be converted to the final grasp configuration for robots.  ...  Their work is to use the depth image to predict the grasp quality and grasp pose of every pixel.  ... 
doi:10.1007/s11042-019-08302-9 fatcat:ddelth45gfdfbdtm6gbdqjr75u

A Survey on 3D Hand Skeleton and Pose Estimation by Convolutional Neural Network

Van-Hung Le, Hung-Cuong Nguyen
2020 Advances in Science, Technology and Engineering Systems  
The estimation process followed two directions: (a) using the 2D CNNs to predict 2D hand pose, and (b) using the 3D synthetic dataset (3D annotations/ ground truth) to regress 3D hand pose or using the  ...  The study discussed several areas of 3D hand pose estimation: (i)the number of valuable studies about 3D hand pose estimation, (ii) estimates of 3D hand pose when using 3D CNNs and 2D CNNs, (iii) challenges  ...  The title is "Using the Lie algebra, Lie group to improve the skeleton hand presentation".  ... 
doi:10.25046/aj050418 fatcat:tzpjnmpwtjbh7m6ld3nucyvxia

Beta version of advanced autonomous functionalities for ground robots and crawlers

PILOTING Project
2021 Zenodo  
and maintenance for ground robots and crawlers.  ...  The main purpose of this document is to present the beta version of the algorithms developed with respect to dexterous manipulation, advanced perception and intelligent navigation for autonomous inspection  ...  Grasp planning Once the valve pose is known, a fixed grasp can be computed. Note that one can decide among multiple grasping strategies.  ... 
doi:10.5281/zenodo.5045351 fatcat:y76igle64fd6niwund4mua6koa
« Previous Showing results 1 — 15 out of 102 results