SOTAVerified

Robotic Grasping

This task is composed of using Deep Learning to identify how best to grasp objects using robotic arms in different scenarios. This is a very complex task as it might involve dynamic environments and objects unknown to the network.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 76–100 of 246 papers

TitleStatusHype
WALL-E: Embodied Robotic WAiter Load Lifting with Large Language Model—0
Instance segmentation based 6D pose estimation of industrial objects using point clouds for robotic bin-picking—0
DMFC-GraspNet: Differentiable Multi-Fingered Robotic Grasp Generation in Cluttered Scenes—0
SCENEREPLICA: Benchmarking Real-World Robot Manipulation by Creating Replicable ScenesCode1
NBMOD: Find It and Grasp It in Noisy BackgroundCode1
Learning Any-View 6DoF Robotic Grasping in Cluttered Scenes via Neural Surface Rendering—0
Self-Supervised Instance Segmentation by Grasping—0
Asynchronous Events-based Panoptic Segmentation using Graph Mixer Neural NetworkCode0
Fast GraspNeXt: A Fast Self-Attention Neural Network Architecture for Multi-task Learning in Computer Vision Tasks for Robotic Grasping on the Edge—0
Implicit representation priors meet Riemannian geometry for Bayesian robotic grasping—0
ShapeShift: Superquadric-based Object Pose Estimation for Robotic Grasping—0
Natural Language Robot Programming: NLP integrated with autonomous robotic grasping—0
DoUnseen: Tuning-Free Class-Adaptive Object Detection of Unseen Objects for Robotic GraspingCode1
Bimodal SegNet: Instance Segmentation Fusing Events and RGB Frames for Robotic GraspingCode0
Learning Accurate Template Matching with Differentiable Coarse-to-Fine Correspondence RefinementCode1
Amodal Intra-class Instance Segmentation: Synthetic Datasets and BenchmarkCode1
Simulation-based Bayesian inference for robotic grasping—0
Depth-based 6DoF Object Pose Estimation using Swin TransformerCode1
Perceiving Unseen 3D Objects by Poking the Objects—0
Deep Reinforcement Learning for Robotic Pushing and Picking in Cluttered Environment—0
Digital Twin Tracking Dataset (DTTD): A New RGB+Depth 3D Dataset for Longer-Range Object Tracking ApplicationsCode1
Self-Supervised Unseen Object Instance Segmentation via Long-Term Robot InteractionCode1
Towards Precise Model-free Robotic Grasping with Sim-to-Real Transfer Learning—0
Learning 6-DoF Fine-grained Grasp Detection Based on Part Affordance Grounding—0
Learning to Generate All Feasible Actions—0
Show:102550
← PrevPage 4 of 10Next →
All datasetsGraspNet-1BillionCornell Grasp DatasetJacquard dataset

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1FlexLoG-CDmAP56.02—Unverified
2GtG2.0mAP53.42—Unverified
3Scale-Balanced-Grasp-CDmAP48.97—Unverified
4graspness-CDmAP48.75—Unverified
5HGGD-CDmAP47.54—Unverified
6HGGDmAP44.24—Unverified
7graspnet-baseline-CDmAP35.45—Unverified
8graspnet-baselinemAP21.41—Unverified
#ModelMetricClaimedVerifiedStatus
1grasp_det_seg_cnn (rgb only, IW split)5 fold cross validation98.2—Unverified
2GR-ConvNet5 fold cross validation97.7—Unverified
3ResNet50 multi-grasp predictor5 fold cross validation96—Unverified
4Multi-Modal Grasp Predictor5 fold cross validation89.21—Unverified
5AlexNet, MultiGrasp5 fold cross validation88—Unverified
6GGCNN5 fold cross validation73—Unverified
7Fast Search5 fold cross validation60.5—Unverified
#ModelMetricClaimedVerifiedStatus
1Efficient-GraspingAccuracy (%)95.6—Unverified
2GR-ConvNetAccuracy (%)94.6—Unverified
3grasp_det_seg_cnn (rgb only)Accuracy (%)92.95—Unverified