SuctionNet-1Billion: A Large-Scale Benchmark for Suction Grasping

Cao, Hanwen; Fang, Hao-Shu; Liu, Wenhai; Lu, Cewu

doi:10.1109/lra.2021.3115406

Cited by 34 publications

(36 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They further proposed GQ-CNN to learn the grasp quality and used a sampling-based method to propose an optimal grasp in the inference phase, and also extended their study by proposing a fully convolutional GQ-CNN (Satish et al, 2019 ) to infer pixel-wise grasp quality, which achieved faster grasping. Recently, (Cao et al, 2021 ) used an auto-encoder–decoder to infer the grasp quality, which was labeled by a similar contact model to that used in GQ-CNN, to generate the suction pose. However, the accuracy of the contact model depends on the model complexity and parameter tuning.…”

Section: Related Workmentioning

confidence: 99%

Learning Suction Graspability Considering Grasp Quality and Robot Reachability for Bin-Picking

Jiang

Oaki²,

Ishihara³

et al. 2022

Front. Neurorobot.

View full text Add to dashboard Cite

Deep learning has been widely used for inferring robust grasps. Although human-labeled RGB-D datasets were initially used to learn grasp configurations, preparation of this kind of large dataset is expensive. To address this problem, images were generated by a physical simulator, and a physically inspired model (e.g., a contact model between a suction vacuum cup and object) was used as a grasp quality evaluation metric to annotate the synthesized images. However, this kind of contact model is complicated and requires parameter identification by experiments to ensure real world performance. In addition, previous studies have not considered manipulator reachability such as when a grasp configuration with high grasp quality is unable to reach the target due to collisions or the physical limitations of the robot. In this study, we propose an intuitive geometric analytic-based grasp quality evaluation metric. We further incorporate a reachability evaluation metric. We annotate the pixel-wise grasp quality and reachability by the proposed evaluation metric on synthesized images in a simulator to train an auto-encoder–decoder called suction graspability U-Net++ (SG-U-Net++). Experiment results show that our intuitive grasp quality evaluation metric is competitive with a physically-inspired metric. Learning the reachability helps to reduce motion planning computation time by removing obviously unreachable candidates. The system achieves an overall picking speed of 560 PPH (pieces per hour).

show abstract

Section: Related Workmentioning

confidence: 99%

Learning Suction Graspability Considering Grasp Quality and Robot Reachability for Bin-Picking

Jiang

Oaki²,

Ishihara³

et al. 2022

Front. Neurorobot.

View full text Add to dashboard Cite

show abstract

“…The advancement of affordable consumer-grade and precise 3D scanner hardware (SHINING 3D EinScan-SP) allows to generate custom 3D models for individual use-cases. For our work we chose a subset of 33 high-quality meshes from [3] being part of YCB object set [13], 4 from [15], scanned 36 objects by ourselves and remodeled 9 in CAD software when scanning was not possible. Obtaining accurate 3D models for all objects is challenging and time consuming.…”

Section: A Custom Object Dataset and Novel Object Testsetmentioning

confidence: 99%

“…Finding reliable grasps is therefore not limited to reason about the physical interaction between gripper and object, but also challenges the system to understand the arrangement of objects in the scene and identify an appropriate picking sequence. While many researches have provided excellent datasets on each individual part such as SynPick [1] for pose estimation and gripper-object interaction, REGRAD [2] for relationship reasoning, SuctionNet-1Billion [3] for vacuum grasping or Dex-Net 4.0 [4] for ambidextrous grasping, the problems were only addressed from one side or did not target automation. Because robotic picking is a multi-stage complex problem, solving the problem from one aspect will miss the details of other aspects.…”

Section: Introductionmentioning

confidence: 99%

“…Object Sets and Photorealism: Motivated by recent progress in the field of dexterous grasping based on RGBD data [16], we find it beneficial to categorize existing work into depth only or photo-realistic data. While depth only datasets [17], [4], [18], [19], [20], [21] are sufficient for training state-of-the-art grasp detection networks such as [17], [22], [4], they are not applicable to recent multi-modal sensor fusion approaches [16], [3], [23], [24]. Besides this limitation, order picking systems usually depend on an additional upstream object detection.…”

Section: Introductionmentioning

confidence: 99%

“…The spring model originates from [27], but instead of dynamically simulating the deformation of the suction cup over time as in [28], they simplify the problem by only considering the quasi-static projection of the cup on to the object's surface and evaluating the geometric deformation of each spring individually. SuctionNet1-Billion [3] simplifies [19] cup model and replaces the original binary scoring by a continuous sealability score. In contrast to [19] their resulting dataset SuctionNet-1Billion has real RGBD data and multiple objects per scene.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

MetaGraspNet: A Large-Scale Benchmark Dataset for Scene-Aware Ambidextrous Bin Picking via Physics-based Metaverse Synthesis

Gilles¹,

Chen²,

Winter³

et al. 2022

Preprint

View full text Add to dashboard Cite

Autonomous bin picking poses significant challenges to vision-driven robotic systems given the complexity of the problem, ranging from various sensor modalities, to highly entangled object layouts, to diverse item properties and gripper types. Existing methods often address the problem from one perspective. Diverse items and complex bin scenes require diverse picking strategies together with advanced reasoning. As such, to build robust and effective machine-learning algorithms for solving this complex task requires significant amounts of comprehensive and high quality data. Collecting such data in real world would be too expensive and time prohibitive and therefore intractable from a scalability perspective. To tackle this big, diverse data problem, we take inspiration from the recent rise in the concept of metaverses, and introduce MetaGraspNet, a large-scale photo-realistic bin picking dataset constructed via physics-based metaverse synthesis. The proposed dataset contains 217k RGBD images across 82 different article types, with full annotations for object detection, amodal perception, keypoint detection, manipulation order and ambidextrous grasp labels for a parallel-jaw and vacuum gripper. We also provide a real dataset consisting of over 2.3k fully annotated high-quality RGBD images, divided into 5 levels of difficulties and an unseen object set to evaluate different object and layout properties. Finally, we conduct extensive experiments showing that our proposed vacuum seal model and synthetic dataset achieves state-of-the-art performance and generalizes to real world use-cases.

show abstract