GlassLoc: Plenoptic Grasp Pose Detection in Transparent Clutter

Zhou, Zebing; Pan, Tianyang; Wu, S. M.; Chang, Haonan; Jenkins, Odest Chadwicke

doi:10.1109/iros40897.2019.8967685

Cited by 18 publications

(9 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Grasp candidates are then generated at regular orientations orthogonal to the curvature axis. Zhou et al ( 2019 ) samples the grasping candidates based on the depth descriptor Depth Likelihood Volume (Zhou Z. et al, 2018 ).…”

Section: Grasping Candidate Generationmentioning

confidence: 99%

“…Gualtieri et al ( 2017 ) and Zhang and Demiris ( 2020 ) propose robot systems to assist disabled people grab objects and dress cloths. Llopart et al ( 2017 ), Zhou et al ( 2019 ), Yang et al ( 2020 ) and Zeng et al ( 2020 ) aim to learn grasping capability to accomplish opening doors, grabbing glasses, picking objects from human's hands and throwing arbitrary objects. More interestingly, Parhar et al ( 2018 ), Guo N. et al ( 2020 ), and Kang et al ( 2020 ) utilizes robot grasp ability to help completing crops harvesting in the farm.…”

Section: Applicationsmentioning

confidence: 99%

See 1 more Smart Citation

Robotics Dexterous Grasping: The Methods Based on Point Cloud and Deep Learning

et al. 2021

View full text Add to dashboard Cite

Dexterous manipulation, especially dexterous grasping, is a primitive and crucial ability of robots that allows the implementation of performing human-like behaviors. Deploying the ability on robots enables them to assist and substitute human to accomplish more complex tasks in daily life and industrial production. A comprehensive review of the methods based on point cloud and deep learning for robotics dexterous grasping from three perspectives is given in this paper. As a new category schemes of the mainstream methods, the proposed generation-evaluation framework is the core concept of the classification. The other two classifications based on learning modes and applications are also briefly described afterwards. This review aims to afford a guideline for robotics dexterous grasping researchers and developers.

show abstract

Section: Grasping Candidate Generationmentioning

confidence: 99%

Section: Applicationsmentioning

confidence: 99%

Robotics Dexterous Grasping: The Methods Based on Point Cloud and Deep Learning

et al. 2021

View full text Add to dashboard Cite

show abstract

“…For example, transparent object pose can be estimated through a monocular color camera [43,44], but the translation estimation along the z-axis tends to be inaccurate due to lack of 3D depth information. Stereo camera [45,46], light field camera [47], single pixel camera [48], and microscope-camera system [49] can be used for object pose estimation, but these works are very different from this paper and are not discussed further.…”

Section: Related Workmentioning

confidence: 91%

6DoF Pose Estimation of Transparent Object from a Single RGB-D Image

Chen

Yao

et al. 2020

Sensors

View full text Add to dashboard Cite

6DoF object pose estimation is a foundation for many important applications, such as robotic grasping, automatic driving, and so on. However, it is very challenging to estimate 6DoF pose of transparent object which is commonly seen in our daily life, because the optical characteristics of transparent material lead to significant depth error which results in false estimation. To solve this problem, a two-stage approach is proposed to estimate 6DoF pose of transparent object from a single RGB-D image. In the first stage, the influence of the depth error is eliminated by transparent segmentation, surface normal recovering, and RANSAC plane estimation. In the second stage, an extended point-cloud representation is presented to accurately and efficiently estimate object pose. As far as we know, it is the first deep learning based approach which focuses on 6DoF pose estimation of transparent objects from a single RGB-D image. Experimental results show that the proposed approach can effectively estimate 6DoF pose of transparent object, and it out-performs the state-of-the-art baselines by a large margin.

show abstract

“…In the computer vision community, significant advances have been made in object detection and segmentation [1]- [6], hand detection [7], [8], hand pose estimation [9]- [12] and its state recognition [13], and human behavior recognition [14]- [20], which are potential sources of useful information in human-robot interaction scenarios. For example, grasping [21]- [25], pickingand-placing [26], stable human pose estimation [27], and stable object detection/discovery [28]- [37] are several topics of interest in HRI scenarios. Recent approaches are pushing the boundaries of HRI by continuously adopting advanced methods of individual vision modules to understand human behaviours, especially in cooperative [38] and safe [39] HRI.…”

Section: Introductionmentioning

confidence: 99%

Message Passing Framework for Vision Prediction Stability in Human Robot Interaction

Jang

Demiris

2022

2022 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

In Human Robot Interaction (HRI) scenarios, robot systems would benefit from an understanding of the user's state, actions and their effects on the environments to enable better interactions. While there are specialised vision algorithms for different perceptual channels, such as objects, scenes, human pose, and human actions, it is worth considering how their interaction can help improve each other's output. In computer vision, individual prediction modules for these perceptual channels frequently produce noisy outputs due to the limited datasets used for training and the compartmentalisation of the perceptual channels, often resulting in noisy or unstable prediction outcomes. To stabilise vision prediction results in HRI, this paper presents a novel message passing framework that uses the memory of individual modules to correct each other's outputs. The proposed framework is designed utilising common-sense rules of physics (such as the law of gravity) to reduce noise while introducing a pipeline that helps to effectively improve the output of each other's modules. The proposed framework aims to analyse primitive human activities such as grasping an object in a video captured from the perspective of a robot. Experimental results show that the proposed framework significantly reduces the output noise of individual modules compared to the case of running independently. This pipeline can be used to measure human reactions when interacting with a robot in various HRI scenarios.

show abstract

GlassLoc: Plenoptic Grasp Pose Detection in Transparent Clutter

Cited by 18 publications

References 30 publications

Robotics Dexterous Grasping: The Methods Based on Point Cloud and Deep Learning

Robotics Dexterous Grasping: The Methods Based on Point Cloud and Deep Learning

6DoF Pose Estimation of Transparent Object from a Single RGB-D Image

Message Passing Framework for Vision Prediction Stability in Human Robot Interaction

Contact Info

Product

Resources

About