Towards Open-Set Scene Graph Generation with Unknown Objects
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Access"
DOI: 10.1109/access.2022.3145465
Abstract: Scene graph generation (SGG) aims to detect objects and their relationships in an image, thereby enabling a detailed understanding of a complex scene for various real-world applications. In SGG applications such as robot vision, it… read more here.
Keywords: scene graph; graph generation; unknown objects; open set ... See more keywords
CM-UNet: ConvMixer UNet for Segmentation of Unknown Objects in Cluttered Scenes
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Access"
DOI: 10.1109/access.2022.3224588
Abstract: Object segmentation in cluttered environments is a fundamental pre-processing step for many perception-related tasks such as vision-based robotic grasping. Most of the existing object segmentation methods are incapable of precisely segmenting unknown objects, particularly in… read more here.
Keywords: cluttered scenes; unet convmixer; segmentation; segmentation unknown ... See more keywords
Robotic Grasping of Unknown Objects Using Novel Multilevel Convolutional Neural Networks: From Parallel Gripper to Dexterous Hand
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Transactions on Automation Science and Engineering"
DOI: 10.1109/tase.2020.3017022
Abstract: To achieve high-accuracy grasping of unknown objects, we present novel multilevel convolutional neural networks (CNNs) for robotic grasping with a parallel gripper or multifingered dexterous hand. The multilevel CNNs include four levels with different structures… read more here.
Keywords: unknown objects; multilevel convolutional; grasping unknown; parallel gripper ... See more keywords
Deeply Supervised Subspace Learning for Cross-Modal Material Perception of Known and Unknown Objects
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Industrial Informatics"
DOI: 10.1109/tii.2022.3195171
Abstract: In order to help robots understand and perceive an object's properties during noncontact robot-object interaction, this article proposes a deeply supervised subspace learning method. In contrast to previous work, it takes the advantages of low… read more here.
Keywords: deeply supervised; unknown objects; cross modal; supervised subspace ... See more keywords
Model-Based Grasping of Unknown Objects from a Random Pile
Sign Up to like & getrecommendations! Published in 2019 at "Robotics"
DOI: 10.3390/robotics8030079
Abstract: Grasping an unknown object in a pile is no easy task for a robot—it is often difficult to distinguish different objects; objects occlude one another; object proximity limits the number of feasible grasps available; and… read more here.
Keywords: model based; based grasping; unknown objects; grasping unknown ... See more keywords