Deep learning approaches to grasp synthesis: A review

R Newbury, M Gu, L Chumbley… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Gras** is the process of picking up an object by applying forces and torques at a set of
contacts. Recent advances in deep learning methods have allowed rapid progress in robotic …

A survey on learning-based robotic gras**

K Kleeberger, R Bormann, W Kraus, MF Huber - Current Robotics Reports, 2020 - Springer
Abstract Purpose of Review This review provides a comprehensive overview of machine
learning approaches for vision-based robotic gras** and manipulation. Current trends and …

6-dof graspnet: Variational grasp generation for object manipulation

A Mousavian, C Eppner, D Fox - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
Generating grasp poses is a crucial component for any robot object manipulation task. In this
work, we formulate the problem of grasp generation as sampling a set of grasps using a …

Acronym: A large-scale grasp dataset based on simulation

C Eppner, A Mousavian, D Fox - 2021 IEEE International …, 2021 - ieeexplore.ieee.org
We introduce ACRONYM, a dataset for robot grasp planning based on physics simulation.
The dataset contains 17.7 M parallel-jaw grasps, spanning 8872 objects from 262 different …

Hand-object contact consistency reasoning for human grasps generation

H Jiang, S Liu, J Wang, X Wang - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
While predicting robot grasps with parallel jaw grippers have been well studied and widely
applied in robot manipulation tasks, the study on natural human grasp generation with a …

Grasp'd: Differentiable contact-rich grasp synthesis for multi-fingered hands

D Turpin, L Wang, E Heiden, YC Chen… - … on Computer Vision, 2022 - Springer
The study of hand-object interaction requires generating viable grasp poses for high-
dimensional multi-finger models, often relying on analytic grasp synthesis which tends to …

Learning continuous 3d reconstructions for geometrically aware gras**

M Van der Merwe, Q Lu… - … on Robotics and …, 2020 - ieeexplore.ieee.org
Deep learning has enabled remarkable improvements in grasp synthesis for previously
unseen objects from partial object views. However, existing approaches lack the ability to …

Robotics dexterous gras**: The methods based on point cloud and deep learning

H Duan, P Wang, Y Huang, G Xu, W Wei… - Frontiers in …, 2021 - frontiersin.org
Dexterous manipulation, especially dexterous gras**, is a primitive and crucial ability of
robots that allows the implementation of performing human-like behaviors. Deploying the …

Planning multi-fingered grasps as probabilistic inference in a learned deep network

Q Lu, K Chenna, B Sundaralingam… - Robotics Research: The …, 2020 - Springer
We propose a novel approach to multi-fingered grasp planning leveraging learned deep
neural network models. We train a convolutional neural network to predict grasp success as …

Multifingered grasp planning via inference in deep neural networks: Outperforming sampling by learning differentiable models

Q Lu, M Van der Merwe… - IEEE Robotics & …, 2020 - ieeexplore.ieee.org
We propose a novel approach to multifingered grasp planning that leverages learned deep
neural network (DNN) models. We trained a voxel-based 3D convolutional neural network …