1,069 Hits in 5.4 sec

ACRONYM: A Large-Scale Grasp Dataset Based on Simulation [article]

Clemens Eppner, Arsalan Mousavian, Dieter Fox
2020 arXiv   pre-print
We introduce ACRONYM, a dataset for robot grasp planning based on physics simulation.  ...  We show the value of this large and diverse dataset by using it to train two state-of-the-art learning-based grasp planning algorithms.  ...  CONCLUSION In this paper, we introduced a new large-scale grasp dataset based on physics simulation called ACRONYM.  ... 
arXiv:2011.09584v1 fatcat:ifkmxwosbfgihh5vutcdylgvei

DA$^{2}$ Dataset: Toward Dexterity-Aware Dual-Arm Grasping

Guangyao Zhai, Yu Zheng, Ziwei Xu, Xin Kong, Yong Liu, Benjamin Busam, Yi Ren, Nassir Navab, Zhengyou Zhang
2022 IEEE Robotics and Automation Letters  
In this paper, we introduce DA^2, the first large-scale dual-arm dexterity-aware dataset for the generation of optimal bimanual grasping pairs for arbitrary large objects.  ...  In addition, we propose an end-to-end dual-arm grasp evaluation model trained on the rendered scenes from this dataset.  ...  CONCLUSION This paper introduced the first large-scale dexterity-aware grasping dataset toward dual-arm grasping.  ... 
doi:10.1109/lra.2022.3189959 fatcat:pkl4htcm4rdunmnv364mswct6u

TransGrasp: Grasp Pose Estimation of a Category of Objects by Transferring Grasps from Only One Labeled Instance [article]

Hongtao Wen, Jianhang Yan, Wanli Peng, Yi Sun
2022 arXiv   pre-print
Specifically, we perform grasp pose transfer across a category of objects based on their shape correspondences and propose a grasp pose refinement module to further fine-tune grasp pose of grippers so  ...  However, most of existing methods require exact 3D object models available beforehand or a large amount of grasp annotations for training.  ...  For convenience, we randomly select one instance for each category from the existing large-scale grasp dataset ACRONYM [7] with pose annotations.  ... 
arXiv:2207.07861v3 fatcat:pl6sjgujd5b6tbtad36lqruddm

Robotic Grasping from Classical to Modern: A Survey [article]

Hanbo Zhang, Jian Tang, Shiguang Sun, Xuguang Lan
2022 arXiv   pre-print
After that, we provide a discussion on the recent state-of-the-art data-driven grasping approaches rising in recent years.  ...  Robotic Grasping has always been an active topic in robotics since grasping is one of the fundamental but most challenging skills of robots.  ...  A summary of robotic grasp datasets is shown in Table 5 . One also could refer to [100] for a comprehensive summary of large-scale robotic manipulation datasets.  ... 
arXiv:2202.03631v1 fatcat:xkwyelt5tfd5jnkhjkgxqlkevq

Goal-Auxiliary Actor-Critic for 6D Robotic Grasping with Point Clouds [article]

Lirui Wang, Yu Xiang, Wei Yang, Arsalan Mousavian, Dieter Fox
2021 arXiv   pre-print
Previous solutions based on 6D grasp synthesis with robot motion planning usually operate in an open-loop setting, which are sensitive to grasp synthesis errors.  ...  6D robotic grasping beyond top-down bin-picking scenarios is a challenging task.  ...  Alternatively, end-to-end policy learning methods [16, 4, 17] make use of large-scale data to learn closed-loop vision-based grasping.  ... 
arXiv:2010.00824v4 fatcat:w3ut3hdv4jdnfndeaynba2t424

Deep Learning Approaches to Grasp Synthesis: A Review [article]

Rhys Newbury, Morris Gu, Lachlan Chumbley, Arsalan Mousavian, Clemens Eppner, Jürgen Leitner, Jeannette Bohg, Antonio Morales, Tamim Asfour, Danica Kragic, Dieter Fox, Akansel Cosgun
2022 arXiv   pre-print
Our review found four common methodologies for robotic grasping: sampling-based approaches, direct regression, reinforcement learning, and exemplar approaches.  ...  Grasping is the process of picking an object by applying forces and torques at a set of contacts. Recent advances in deep-learning methods have allowed rapid progress in robotic object grasping.  ...  The majority of the reviewed works were trained on simulated datasets which offer large-scale data collection.  ... 
arXiv:2207.02556v1 fatcat:xw77crimuzhu5dvxpoiizjhpx4

Predicting Stable Configurations for Semantic Placement of Novel Objects [article]

Chris Paxton, Chris Xie, Tucker Hermans, Dieter Fox
2021 arXiv   pre-print
Our experiments through a set of simulated ablations demonstrate that using a relational classifier alone is not sufficient for reliable planning.  ...  We train our models purely in simulation, with no fine-tuning needed for use in the real world.  ...  Dataset Creation We generated a large-scale dataset in simulation of RGB-D images with associated segmentation masks and relational predicates.  ... 
arXiv:2108.12062v1 fatcat:l53iivf37veyxe4i2tfhcwueca

The Global Gridded Crop Model Intercomparison phase 1 simulation dataset

Christoph Müller, Joshua Elliott, David Kelly, Almut Arneth, Juraj Balkovic, Philippe Ciais, Delphine Deryng, Christian Folberth, Steven Hoek, Roberto C. Izaurralde, Curtis D. Jones, Nikolay Khabarov (+13 others)
2019 Scientific Data  
The Global Gridded Crop Model Intercomparison (GGCMI) phase 1 dataset of the Agricultural Model Intercomparison and Improvement Project (AgMIP) provides an unprecedentedly large dataset of crop model simulations  ...  The dataset consists of annual data fields at a spatial resolution of 0.5 arc-degree longitude and latitude.  ...  The PRYSBI2 model (Process-based Regional-scale crop Yield Simulator with Bayesian Inference version 2.1) is a semi-process-based large-area crop model for major crops: maize, soybeans, wheat, and rice  ... 
doi:10.1038/s41597-019-0023-8 pmid:31068583 pmcid:PMC6506552 fatcat:ud3fyydpcnh2npxlwju6ksd7ni

Strong regional influence of climatic forcing datasets on global crop model ensembles

Alex C. Ruane, Meridel Phillips, Christoph Müller, Joshua Elliott, Jonas Jägermeyr, Almut Arneth, Juraj Balkovic, Delphine Deryng, Christian Folberth, Toshichika Iizumi, Roberto C. Izaurralde, Nikolay Khabarov (+11 others)
2021 Agricultural and Forest Meteorology  
Bias-adjusted CFDs most often were among the highest model-observation correlations, although all CFDs produced the highest correlation in at least one top-producing country.  ...  Agricultural Model Intercomparison and Improvement Project (AgMIP) Global Gridded Crop Model Intercomparison (GGCMI) Phase I, which aligned 14 global gridded crop models (GGCMs) and 11 climatic forcing datasets  ...  The selection of large-scale precipitation datasets (WFDEIgpcc vs. GPCCcru) did not have a substantial overall effect on performance.  ... 
doi:10.1016/j.agrformet.2020.108313 fatcat:s67onagp6jdz3isiab4ej5mhx4

Hierarchical Policies for Cluttered-Scene Grasping with Latent Plans [article]

Lirui Wang, Xiangyun Meng, Yu Xiang, Dieter Fox
2022 arXiv   pre-print
Our hierarchical framework learns collision-free target-driven grasping based on partial point cloud observations.  ...  6D grasping in cluttered scenes is a longstanding problem in robotic manipulation.  ...  To train a policy on a cluttered-scene grasping dataset with potentially many solutions (e.g. different ways to grasp a bowl), we condition the policy on a specific plan [14] such that the low-level  ... 
arXiv:2107.01518v3 fatcat:77kuz66ydbdedktanbzes5ccbq

Homography Estimation Between Omnidirectional Cameras Without Point Correspondences [chapter]

Robert Frohlich, Levente Tamás, Zoltan Kato
2015 Studies in Systems, Decision and Control  
The intent is to cover the theory, applications, and perspectives on the state of the art and future developments relevant to systems, decision making, control, complex processes and related areas, as  ...  Control" (SSDC) covers both new developments and advances, as well as the state of the art, in the various areas of broadly perceived systems, decision making and control-quickly, up to date and with a  ...  The approach is validated on several public datasets.  ... 
doi:10.1007/978-3-319-26327-4_6 fatcat:jzfi55x2bzgnxmalsregytzmmq

Untangling Dense Knots by Learning Task-Relevant Keypoints [article]

Jennifer Grannen, Priya Sundaresan, Brijen Thananjeyan, Jeffrey Ichnowski, Ashwin Balakrishna, Minho Hwang, Vainavi Viswanath, Michael Laskey, Joseph E. Gonzalez, Ken Goldberg
2020 arXiv   pre-print
We instantiate this into an algorithm, HULK: Hierarchical Untangling from Learned Keypoints, which combines learning-based perception with a geometric planner into a policy that guides a bilateral robot  ...  We compare two variants of HULK to three baselines and observe that HULK achieves 43.3% higher success rates on a physical system compared to the next best baseline.  ...  either does not include the relevant under-crossing or captures too large of a crop.  ... 
arXiv:2011.04999v1 fatcat:kqclqjw7nfdqxiaaerladnuywi

Development, Production and Evaluation of Aerosol Climate Data Records from European Satellite Observations (Aerosol_cci)

Thomas Popp, Gerrit de Leeuw, Christine Bingen, Christoph Brühl, Virginie Capelle, Alain Chedin, Lieven Clarisse, Oleg Dubovik, Roy Grainger, Jan Griesfeller, Andreas Heckel, Stefan Kinne (+20 others)
2016 Remote Sensing  
Producing a global and comprehensive description of atmospheric aerosols requires integration of ground-based, airborne, satellite and model datasets.  ...  Our thanks go to the AERONET and MAN networks for providing the valuable validation datasets in a consistent, quality-assured and easily accessed form.  ...  Supporting work for the development of GOMOS datasets was performed in the framework of a Marie Curie Career Integration Grant within the 7th European Community Framework Programme under grant agreement  ... 
doi:10.3390/rs8050421 fatcat:n7hkxgqexredbnxtrqmjnkmsga

The Sun's role in decadal climate predictability in the North Atlantic

Annika Drews, Wenjuan Huo, Katja Matthes, Kunihiko Kodera, Tim Kruschke
2022 Atmospheric Chemistry and Physics  
We utilize two 10-member ensemble simulations with a state-of-the-art chemistry–climate model, to date a unique dataset in chemistry–climate modeling.  ...  Despite several studies on decadal-scale solar influence on climate, a systematic analysis of the Sun's contribution to decadal surface climate predictability is still missing.  ...  We would like to thank a number of colleagues for continuous discussions about the solar influence on cli-  ... 
doi:10.5194/acp-22-7893-2022 fatcat:rf2igbr7ozeydk66et6f4thhay

Language Grounding with 3D Objects [article]

Jesse Thomason, Mohit Shridhar, Yonatan Bisk, Chris Paxton, Luke Zettlemoyer
2021 arXiv   pre-print
We find that adding view estimation to language grounding models improves accuracy on both SNARE and when identifying objects referred to in language on a robot platform, but note that a large gap remains  ...  If a human requests an object based on any of its basic properties, such as color, shape, or texture, robots should perform the necessary exploration to accomplish the task.  ...  The annotations are collected to complement the ACRONYM 3 [43] grasping dataset and include language that targets both visual and tactile attributes of objects.  ... 
arXiv:2107.12514v2 fatcat:hth2wl7xtnaojdhksfalh37gfe
« Previous Showing results 1 — 15 out of 1,069 results