Learning of 2D grasping strategies from box-based 3D object approximations

Geidenstam, Sebastian; Huebner, Kai; Banksell, Daniel; Kragić, Danica

doi:10.15607/rss.2009.v.002

Cited by 17 publications

(13 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their approach relied on having known models for the objects based on which grasps for the objects could be analyzed in the grasping simulation software GraspIt!. Srinivasa et al [19] pre-computed grasps for objects and then executed them based on registration of the objects in the environment, and Geidenstam et al [4] used box-based decompositions of simulated 3-D point clouds to learn 2-D grasping strategies for objects. The use of known 3-D models precludes these techniques from being used for grasp selection in unstructured environments.…”

Section: Introduction and Related Workmentioning

confidence: 99%

Contact-reactive grasping of objects with partial shape information

Hsiao

Chitta

Ciocarlie

et al. 2010

2010 IEEE/RSJ International Conference on Intelligent Robots and Systems

181

129

View full text Add to dashboard Cite

Robotic grasping in unstructured environments requires the ability to select grasps for unknown objects and execute them while dealing with uncertainty due to sensor noise or calibration errors. In this work, we propose a simple but robust approach to grasp selection for unknown objects, and a reactive adjustment approach to deal with uncertainty in object location and shape. The grasp selection method uses 3D sensor data directly to determine a ranked set of grasps for objects in a scene, using heuristics based on both the overall shape of the object and its local features. The reactive grasping approach uses tactile feedback from fingertip sensors to execute a compliant robust grasp. We present experimental results to validate our approach by grasping a wide range of unknown objects. Our results show that reactive grasping can correct for a fair amount of uncertainty in the measured position or shape of the objects, and that our grasp selection approach is successful in grasping objects with a variety of shapes.

show abstract

Section: Introduction and Related Workmentioning

confidence: 99%

Contact-reactive grasping of objects with partial shape information

Hsiao

Chitta

Ciocarlie

et al. 2010

2010 IEEE/RSJ International Conference on Intelligent Robots and Systems

181

129

View full text Add to dashboard Cite

show abstract

“…grasping information is synthesised on the resulting bounding boxes. An extension of this work is presented in [16] where neural networks are used to combine 3D and 2D grasping strategies. The grasp planner presented in [17] is operating on a topological object segmentation which is computed based on the Reeb Graph formalism.…”

Section: Related Workmentioning

confidence: 99%

Planning High-Quality Grasps Using Mean Curvature Object Skeletons

Vahrenkamp

Koch

Wächter

et al. 2018

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

In this work, we present a grasp planner which integrates two sources of information to generate robust grasps for a robotic hand. First, the topological information of the object model is incorporated by building the mean curvature skeleton and segmenting the object accordingly in order to identify object regions which are suitable for applying a grasp. Second, the local surface structure is investigated to construct feasible and robust grasping poses by aligning the hand according to the local object shape. We show how this information can be used to derive different grasping strategies, which also allows to distinguish between precision and power grasps. We applied the approach to a wide variety of object models of the KIT and the YCB real-world object model databases and evaluated the approach with several robotic hands. The results show that the skeleton-based grasp planner is capable to autonomously generate high-quality grasps in an efficient manner. In addition, we evaluate how robust the planned grasps are against hand positioning errors as they occur in real-world applications due to perception and actuation inaccuracies. The evaluation shows that the majority of the generated grasps are of high quality since they can be successfully applied even when the hand is not exactly positioned.

show abstract

“…Algorithm 1 was presented in [17]. The idea is to decompose the object in MVBBs minimizing the volume of the boxes which fit partial point clouds.…”

Section: Bounding Box Decompositionmentioning

confidence: 99%

Advanced Grasping with the Pisa/IIT SoftHand

Bonilla

Santina

Rocchi

et al. 2018

Communications in Computer and Information Science

View full text Add to dashboard Cite

This chapter presents the hardware, software and overall strategy used by the team UNIPI-IIT-QB to participate to the Robotic Grasping and Manipulation Competition. It relies on the PISA/IIT Soft-Hand, which is underactuated soft robotic hand that can adapt to the grasped object shape and is compliant with the environment. It was used for the hand-in-hand and for the simulation tracks, where the team reached first and third places respectively.

show abstract

Learning of 2D grasping strategies from box-based 3D object approximations

Cited by 17 publications

References 18 publications

Contact-reactive grasping of objects with partial shape information

Contact-reactive grasping of objects with partial shape information

Planning High-Quality Grasps Using Mean Curvature Object Skeletons

Advanced Grasping with the Pisa/IIT SoftHand

Contact Info

Product

Resources

About