Probabilistic Models of Object Geometry for Grasp Planning

Glover, Jared; Rus, Daniela; Roy, Nicholas

doi:10.15607/rss.2008.iv.036

Cited by 26 publications

(20 citation statements)

References 23 publications

(10 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It provides easy conversion between occupancy grids and pointclouds, which makes it easy to use various algorithms in the Point Cloud Library (PCL) [20]. Glover et al [21] proposed to learn probablistic generative models of a class of objects from 2-D image, and the learned models can be used to infer the hidden parts to complete the object contour before manipulation. We take a different approach by using priors inspired from the sensor characteristics to infer the object shape in 3-D for the purpose of further pretouch sensing and grasping.…”

Section: Framework and Environment Representationmentioning

confidence: 99%

A unified framework for grasping and shape acquisition via pretouch sensing

Jiang

Smith

2013

2013 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Abstract-This paper presents a unified framework to enable automatic exploration with a pretouch sensor to reduce object shape uncertainty before grasping. The robot starts with only the incomplete object shape data it acquires from a Kinect depth sensor-it has no model of the object. Combining the Kinect pointcloud with prior probability distributions for occlusion and transparency, it makes inferences about portions of the object that the Kinect was not able to observe. Operating on the inferred shape of the object, an iterative grasp replanning and exploration algorithm decides when further exploration is required, and where to explore in the scene using the pretouch sensor. The information gathered by the exploration action is added directly to the robot's environment representation and is considered automatically in the next grasp planning iteration.The pretouch sensor used is the first "seashell effect" pretouch sensor fully integrated into a robot (the PR2); the sensor replaces the PR2's touch sensor pads, and uses the PR2's existing hardware interfaces to eliminate all external wires for power and signal. This new non-contact sensor enables the robot to gather local object shape information without disturbing it.The new sensor and framework was validated on the PR2 robot for its usefulness in sensor-driven grasping of un-modeled objects.

show abstract

Section: Framework and Environment Representationmentioning

confidence: 99%

A unified framework for grasping and shape acquisition via pretouch sensing

Jiang

Smith

2013

2013 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

show abstract

“…Huebner et al [20] transformed 3D models to box-based approximation before generating grasp hypotheses. Glover et al [21] built generative probabilistic models for known objects when they are occluded or deformed to complete the object geometry. Some other work has focused on learning grasps from examples, such as [22], [23].…”

Section: Related Workmentioning

confidence: 99%

Learning hardware agnostic grasps for a universal jamming gripper

Jiang

Amend

Lipson

et al. 2012

2012 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

“…All of the techniques in this paper in principle extend to 3-D, but following the observation of Bone and Du (2001) that "grasp planning is much simpler in 2D, and 2D grasps are applicable to many 3D objects", we concentrate on the 2-D representations required to grasp objects (Shimoga 1996;Mirtich and Canny 1994) with a planar manipulator capable of supporting the weight of the object. This paper extends the methods presented in Glover et al (2006) to include extensions of the shape completion algorithm and a complete description of the model learning and shape inference algorithms. In addition to the preliminary experiments on a small set of shapes reported in Glover et al (2006), we present results on the larger MPEG-7 shape dataset (Latecki et al 2000).…”

Section: Introductionmentioning

confidence: 99%

“…This paper extends the methods presented in Glover et al (2006) to include extensions of the shape completion algorithm and a complete description of the model learning and shape inference algorithms. In addition to the preliminary experiments on a small set of shapes reported in Glover et al (2006), we present results on the larger MPEG-7 shape dataset (Latecki et al 2000).…”

Section: Introductionmentioning

confidence: 99%

Probabilistic Models of Object Geometry with Application to Grasping

Glover

Rus

Roy

2009

The International Journal of Robotics Research

Self Cite

View full text Add to dashboard Cite

Abstract-Robot manipulators typically rely on complete knowledge of object geometry in order to plan motions and compute grasps. But when an object is not fully in view it can be difficult to form an accurate estimate of the object's shape and pose, particularly when the object deforms.In this paper we describe a generative model of object geometry based on Mardia and Dryden's "Probabilistic Procrustean Shape" which captures both non-rigid deformations and object variability in a class. We extend their shape model to the setting where point correspondences are unknown using Scott and Nowak's COPAP framework. We use this model to recognize objects in a cluttered image and to infer their complete 2-D boundaries with a novel algorithm called OSIRIS. We show examples of learned models from image data and demonstrate how the models can be used by a manipulation planner to grasp objects in cluttered visual scenes.

show abstract

Probabilistic Models of Object Geometry for Grasp Planning

Abstract: Abstract

Cited by 26 publications

References 23 publications

A unified framework for grasping and shape acquisition via pretouch sensing

A unified framework for grasping and shape acquisition via pretouch sensing

Learning hardware agnostic grasps for a universal jamming gripper

Probabilistic Models of Object Geometry with Application to Grasping

Contact Info

Product

Resources

About