The OpenGRASP benchmarking suite: An environment for the comparative analysis of grasping and dexterous manipulation

By Stefan Ulbrich, Daniel Kappler, Tamim Asfour, Nikolaus Vahrenkamp, A. Bierbaum, Markus Przybylski, Rüdiger Dillmann. 2011

55 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

RLBench: The Robot Learning Benchmark & Learning Environment (2019, methodology): “For grasping, both OpenGrasp [36] and VisGraB [37] are popular simulation-based benchmarks, whilst the YCB dataset [38] focuses on real-world objects.”
Data-Driven Grasp Synthesis—A Survey (2013, neutral): “There have also been robotic challenges organized such as the DARPA Arm project [143] or RoboCup@Home [144] and a framework for benchmarking has been proposed by Ulbrich et al. [145].”
VisGraB: A benchmark for vision-based grasping (2012, methodology): “By enabling the comparison between di erent grasping methods, we aim to provide a better insight into the di erent methodologies and their outcomes.”
Benchmarking in Manipulation Research: The YCB Object and Model Set and Benchmarking Protocols (2015, methodology): “13 The OpenGRASP benchmarking suite [20] 2011 Mesh with texture, stereo images Grasping Uses KIT database No http://opengrasp.”
Cartman: The Low-Cost Cartesian Manipulator that Won the Amazon Robotics Challenge (2017, background): “There is a long history of research into grasping and dexterous manipulation [1], and recent progress has largely been driven by technological developments such as stronger, more precise and more readily available collaborative robotic arms [2] and simple compliant and universal grippers [3], [4], [”
CommonRoad: Composable benchmarks for motion planning on roads (2017, background): “Detailed benchmarks have been developed in particular for robotic grasping [7], [8] and for robotic manipulators with a focus on indoor human environments [9].”
Learning of grasp selection based on shape-templates (2013, background): “(Miller and Allen 2004), Open-Rave (Diankov and Kuffner 2008) or OpenGRASP (Leon et al. 2010; Ulbrich et al. 2011) that can execute grasps given perfect knowledge of the object and its environment.”
Benchmarking in Manipulation Research: Using the Yale-CMU-Berkeley Object and Model Set (2015, methodology): “The OpenGRASP benchmarking suite [20] presents a simulation framework for robotic manipulation.”
The ACRV picking benchmark: A robotic shelf picking benchmark to foster reproducible research (2016, background): “Despite a long history of research into dexterous manipulation [1], much of the observable recent progress has been driven by technological developments such as quality low-cost arms – e.”
The YCB object and Model set: Towards common benchmarks for manipulation research (2015, methodology): “The OpenGRASP benchmarking suite [19] presents a simulation framework for robotic manipulation.”
Benchmarking Simulated Robotic Manipulation Through a Real World Dataset (2019, background): “and those available have been developed to assess the performance of planners and grasping [14]–[16].”
Rearrangement: A Challenge for Embodied AI (2020, background): “…vision, and machine learning have proposed various standardized evaluation methods, including protocols for evaluating robotic grasping [52, 72, 49], navigation [1, 4], manipulation tasks focusing on standardized real-world object sets [13], and competition-style setups, such as RoboCup…”