Graspit! A versatile simulator for robotic grasping

By Andrew T. Miller, Peter K. Allen. 2004

1,257 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Control and Systems Engineering, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Control and Systems Engineering

In Robotics & Control

Citations in the corpus

Supersizing self-supervision: Learning to grasp from 50K tries and 700 robot hours (2015, methodology): “Other approaches to predict grasping includes using simulators such as Graspit [17], [18].”
Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations (2017, methodology): “re unfortunately lacking. Model-based methods [24] [17] using trajectory optimization and model predictive control have been used to synthesize complex behaviors with high dimensional hands. Sampling [23] and motion capture [22] based approaches have also shown similar success. However, these method”
Multiple Interactions Made Easy (MIME): Large Scale Demonstrations Data for Imitation (2018, background): “[24] developed an interface to evaluate robotic grasps in a simulator.”
Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost (2018, background): “work is often focused on achieving stable grasps by explicitly reasoning about the stability of the grasp using geometric and analytic metrics [6], [7], [8].”
Deep learning for detecting robotic grasps (2013, methodology): “en full knowledge of 2D or 3D object shape using physics-based techniques such as form closure [19], force closure [35, 32]. Other works, such as Dogar and Srinivasa [7], Dogar et al. [8] and GraspIt [10, 28] use full physical simulation given 3D models to determine feasible grasps. Gallegos et al. ”
Data-Driven Grasp Synthesis—A Survey (2013, background): “[18] to generate a set of grasp candidates in force closure.”
Learning to push by grasping: Using multiple tasks for effective learning (2016, background): “Analytical frameworks such as [1], [2], [3] focus on defining (c) via mathematical framework.”
OpenRAVE: A Planning Architecture for Autonomous Robotics (2008, methodology): “Other software tools, notably the GraspIt! simulator [17], perform similar computations for grasp analysis.”
VisGraB: A benchmark for vision-based grasping (2012, methodology): “Our benchmark methodology is based on open xml formats and can hence be used with other grasp simulators, such as GraspIt [23] and OpenGRASP [22].”
Grasp'D: Differentiable Contact-rich Grasp Synthesis for Multi-fingered Hands (2022, methodology): “Notably, [21, 39, 46, 49, 56, 57] all use datasets synthesized with the GraspIt! [63] simulator, which is widely used for both multi-finger robotic and human grasp synthesis.”
Action Image Representation: Learning Scalable Deep Grasping Policies with Zero Real World Data (2020, methodology): “Early approaches to grasping used models of the environment coupled with grasp planning based on force closure metrics [1] or grasping-specific simulations [18] to compute optimal grasps.”
A low-cost and modular, 20-DOF anthropomorphic robotic hand: design, actuation and modeling (2013, methodology): “Therefore simulation as a promising tool to help evaluating the performance of robotic hands has been adopted to speed up the design process [14].”
Manipulators and Manipulation in high dimensional spaces (2016, background): “These metrics have been widely leveraged by data driven [14] and optimization based techniques [62] for static grasp synthesis.”
Learning Dexterous Grasping with Object-Centric Visual Affordances (2020, background): “ContactGrasp [7] leverages thermal image data to rank GraspIt [29] hand poses for a model-based optimization approach.”
HOnnotate: A Method for 3D Annotation of Hand and Object Poses (2019, background): “Generating physically correct grasps is possible [29], as shown in [18], but complex manipulation is difﬁcult to simulate.”
Analysis and Observations From the First Amazon Picking Challenge (2016, methodology): “The Rutgers U. Pracsys cited using the “GraspIt” software package [25] for generating grasping poses for the 3-ﬁnger Robotiq hand.”
Lessons from the Amazon Picking Challenge: Four Aspects of Building Robotic Systems (2016, background): “Grasping, for example, can be posed as a contact point planning problem [36], which is appealing as it abstracts the problem away from the hand and the environmental context.”