Estimating 6D Object Poses with Temporal Motion Reasoning for Robot Grasping in Cluttered Scenes

Huang, Rui; Mu, Fengjun; Wen-jiang, LI; Liu, Huaping; Cheng, Hong

doi:10.1109/lra.2022.3147334

Cited by 5 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In real-world grasping, however, these shape-based methods are inaccurate to classify the objects into com-plete 3D shapes, even less to de ne the grasping prim-itives. In recent years, grasp detection methods based on 6D pose estimation [8][9][10][11][12][13][14] have been proposed for gras-ping regression. Other methods aim at obtaining grasp data directly from the sensors of the robot arm without estimating the object's pose [15,16,17].…”

Section: Introductionmentioning

confidence: 99%

Detection-driven 3D masking for efficient object grasping

Li,

Cherouat,

Snoussi

et al. 2023

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Robotic arms are currently in the spotlight of the industry of future, but their e ciency faces huge challenges. The e cient grasping of the robotic arm, replacing human work, requires visual support. In this paper, we rst propose to augment end-to-end deep learning gasping with a object detection model in order to improve the e ciency of grasp pose prediction. The accurate positon of the object is di cult to obtain in the depth image due to the absent of the label in point cloud in an open environment. In our work, the detection information is fused with the depth image to obtain accurate 3D mask of the point cloud, guiding the classical GraspNet to generate more accurate grippers. The detection-driven 3D mask method allows also to design a priority scheme increasing the adaptability of grasping scenarios. The proposed grasping method is validated on multiple benchmark datasets achieving state-of-the-art performances.

show abstract