Filters








490 Hits in 6.6 sec

Self-supervised 6D Object Pose Estimation for Robot Manipulation [article]

Xinke Deng, Yu Xiang, Arsalan Mousavian, Clemens Eppner, Timothy Bretl, Dieter Fox
2020 arXiv   pre-print
In this work, we introduce a robot system for self-supervised 6D object pose estimation.  ...  Starting from modules trained in simulation, our system is able to label real world images with accurate 6D object poses for self-supervised learning.  ...  CONCLUSION We introduce a novel self-supervised 6D object pose estimation system for robot manipulation.  ... 
arXiv:1909.10159v2 fatcat:2pjdmi5ai5czlhwti2dkcc2fny

A Survey on Learning-Based Robotic Grasping

Kilian Kleeberger, Richard Bormann, Werner Kraus, Marco F. Huber
2020 Current Robotics Reports  
Summary Both approaches to robotic grasping and manipulation with and without object-specific knowledge are discussed.  ...  Purpose of Review This review provides a comprehensive overview of machine learning approaches for vision-based robotic grasping and manipulation.  ...  Utilizing the strength of supervised learning for 6D object pose estimation requires large amounts of labeled data for training.  ... 
doi:10.1007/s43154-020-00021-6 fatcat:wsqxh7b6o5cvbf3i4fa2b66eqy

OSSID: Online Self-Supervised Instance Detection by (and for) Pose Estimation [article]

Qiao Gu, Brian Okorn, David Held
2022 arXiv   pre-print
Real-time object pose estimation is necessary for many robot manipulation algorithms.  ...  However, state-of-the-art methods for object pose estimation are trained for a specific set of objects; these methods thus need to be retrained to estimate the pose of each new object, often requiring  ...  INTRODUCTION Object instance detection and pose estimation are crucial to many robot manipulation tasks.  ... 
arXiv:2201.07309v1 fatcat:q6oirxsqezcxjhdyegjsknapsy

Multi-view Self-supervised Deep Learning for 6D Pose Estimation in the Amazon Picking Challenge [article]

Andy Zeng, Kuan-Ting Yu, Shuran Song, Daniel Suo, Ed Walker Jr., Alberto Rodriguez, Jianxiong Xiao
2017 arXiv   pre-print
We demonstrate that our system can reliably estimate the 6D pose of objects under a variety of scenarios. All code, data, and benchmarks are available at http://apc.cs.princeton.edu/  ...  object pose.  ...  Benchmark for 6D pose estimation.  ... 
arXiv:1609.09475v3 fatcat:tpv5alfmpjf6fbtfrlktlor72u

Generating Annotated Training Data for 6D Object Pose Estimation in Operational Environments with Minimal User Interaction [article]

Paul Koch, Marian Schlüter, Serge Thill
2022 arXiv   pre-print
Recently developed deep neural networks achieved state-of-the-art results in the subject of 6D object pose estimation for robot manipulation.  ...  Here, we present a proof of concept for a novel approach of autonomously generating annotated training data for 6D object pose estimation.  ...  [12] recently proposed a self-supervised 6D model for robot manipulation that avoids high annotation costs by learning how to estimate the 6D pose of an object in simulation.  ... 
arXiv:2103.09696v3 fatcat:jfwnupwojnbbpmktlz5adijnwi

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
Finally, we transfer the a-priori knowledge from the relative pose between object and human hand with the estimate of the current object pose in the scene into necessary grasping instructions for the robot  ...  To this end, most approaches either compute the full 6D pose for the object of interest or learn to predict a set of grasping points.  ...  Fox, of the reconstructed MANO hand model with the hand point “Self-supervised 6d object pose estimation for robot manipulation,” in  ... 
arXiv:2112.02849v1 fatcat:kpwrzj6r4re6rodinzlrer25si

CPS++: Improving Class-level 6D Pose and Shape Estimation From Monocular Images With Self-Supervised Learning [article]

Fabian Manhardt and Gu Wang and Benjamin Busam and Manuel Nickel and Sven Meier and Luca Minciullo and Xiangyang Ji and Nassir Navab
2020 arXiv   pre-print
Contemporary monocular 6D pose estimation methods can only cope with a handful of object instances.  ...  This is especially true for class-level 6D pose estimation, as one is required to create a highly detailed reconstruction for all objects and then annotate each object and scene using these models.  ...  In the field of 6D pose, Deng et al. (2020b) propose a self-labeling pipeline for RGB-D based 6D object pose estimation with an interactive robotic manipulator.  ... 
arXiv:2003.05848v3 fatcat:bvkodwdpnbe5jlcranexwwwv6i

KOVIS: Keypoint-based Visual Servoing with Zero-Shot Sim-to-Real Transfer for Robotics Manipulation [article]

En Yen Puang and Keng Peng Tee and Wei Jing
2020 arXiv   pre-print
We present KOVIS, a novel learning-based, calibration-free visual servoing method for fine robotic manipulation tasks with eye-in-hand stereo camera system.  ...  The two networks are trained end-to-end in the simulated environment by self-supervised learning without manual data labeling.  ...  ACKNOWLEDGEMENT This research is supported by the Agency for Science, Technology and Research (A*STAR), Singapore, under its AME Programmatic Funding Scheme (Project #A18A2b0046).  ... 
arXiv:2007.13960v1 fatcat:nfyc54hmgvcgxl7bvxeablc2mm

SLAM-Supported Self-Training for 6D Object Pose Estimation [article]

Ziqi Lu, Yihao Zhang, Kevin Doherty, Odin Severinsen, Ethan Yang, John Leonard
2022 arXiv   pre-print
To address the problem, we present a SLAM-supported self-training procedure to autonomously improve robot object pose estimation ability during navigation.  ...  Recent progress in learning-based object pose estimation paves the way for developing richer object-level world representations.  ...  ACKNOWLEDGMENT The authors acknowledge Jonathan Tremblay and other NVIDIA developers for providing consultation on training DOPE networks and generating synthetic data.  ... 
arXiv:2203.04424v2 fatcat:kwuvnb7jr5ai5ib2fahqoizbe4

Perspective from International Robotics Competicion
国際ロボット競技から見る将来展望

Kei Okada
2017 Journal of the Robotics Society of Japan  
.: Multi-view Self-supervised Deep Learning for 6D Pose Estimation in the Amazon Picking Challenge, ArXiv e-prints, 2016. [ 6 ] Amazon Picking Challenge no.14-15, 2016.  ...  .: Amazon Picking Challenge Object Scans, http://rll.berkeley.edu/amazon picking challenge/ [ 8 ] Colin Rennie et al.: A Dataset for Improved RGBD-based Object Detection and Pose Estimation for Warehouse  ... 
doi:10.7210/jrsj.35.9 fatcat:tx7mjno4p5gwlh64mo2gwtoho4

Visual Reconstruction and Localization based Robust Robotic 6-DoF Grasping in the Wild

Ji Liang, Jiguang Zhang, Bingbing Pan, Shibiao Xu, Guangheng Zhao, Ge Yu, Xiaopeng Zhang
2021 IEEE Access  
Then, constrained by the above initial localization, a 3D point cloud reconstruction based 6-DoF pose estimation method is proposed for the manipulator further fine locating grasping target.  ...  Finally, our framework realizes full function of visual 6DoF robotic grasping, which includes two different visual servoing and grasp planning strategies for different objects grasping.  ...  Moreover, collecting and generating huge training data on real robots through self-supervised trial is too expensive for practical applications.  ... 
doi:10.1109/access.2021.3079245 fatcat:oyisfxi22zdfzi3ljrl7chorfa

Uncertainty-Aware Self-Supervised Learning of Spatial Perception Tasks [article]

Mirko Nava, Antonio Paolillo, Jérôme Guzzi, Luca Maria Gambardella, Alessandro Giusti
2021 arXiv   pre-print
We propose a general self-supervised approach to learn neural models that solve spatial perception tasks, such as estimating the pose of an object relative to the robot, from onboard sensor readings.  ...  We demonstrate the general approach in three different concrete scenarios: a simulated robot arm that visually estimates the pose of an object of interest; a small differential drive robot using 7 infrared  ...  Object of Interest Pose Estimation with a Robotic Arm For the scenario described in Sect.  ... 
arXiv:2103.12007v1 fatcat:3sxgdtw46vbxfkzo4eorzl4vsu

Nothing But Geometric Constraints: A Model-Free Method for Articulated Object Pose Estimation [article]

Qihao Liu, Weichao Qiu, Weiyao Wang, Gregory D. Hager, Alan L. Yuille
2020 arXiv   pre-print
task of category-independent articulated object pose estimation.  ...  Furthermore, we build a synthetic dataset with different kinds of robots and multi-joint articulated objects for the research of vision-based robot control and robotic vision.  ...  Articulated Object Pose Estimation Articulated object pose estimation is the prerequisite for robot manipulating daily objects with functional parts.  ... 
arXiv:2012.00088v1 fatcat:tev3bedvjnem3m3oxud2fmjmuu

DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion

Chen Wang, Danfei Xu, Yuke Zhu, Roberto Martin-Martin, Cewu Lu, Li Fei-Fei, Silvio Savarese
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
In this work, we present DenseFusion, a generic framework for estimating 6D pose of a set of known objects from RGB-D images.  ...  We also deploy our proposed method to a real robot to grasp and manipulate objects based on the estimated pose. Our code and video are available at https://sites.google.com/view/densefusion/.  ...  We also want to thank Toyota Research Institute for the Human Support Robot which we used to perform our real robot experiments.  ... 
doi:10.1109/cvpr.2019.00346 dblp:conf/cvpr/WangXZML0S19 fatcat:2zgeffs6qjbn5bkvovl6arpkxm

S3K: Self-Supervised Semantic Keypoints for Robotic Manipulation via Multi-View Consistency [article]

Mel Vecerik, Jean-Baptiste Regli, Oleg Sushkov, David Barker, Rugile Pevceviciute, Thomas Rothörl, Christopher Schuster, Raia Hadsell, Lourdes Agapito, Jonathan Scholz
2020 arXiv   pre-print
with minimal supervision.  ...  However, both approaches often struggle to capture the fine-detail required for precision tasks on specific objects, e.g. grasping and mating a plug and socket.  ...  Other related methods utilize keypoints internally to obtain 6D pose estimates, but do not require explicit supervision on the keypoints [6, 20, 21] .  ... 
arXiv:2009.14711v2 fatcat:timaaid4zfb2pbfmpimytdbdk4
« Previous Showing results 1 — 15 out of 490 results