GP-GPIS-OPT: Grasp planning with shape uncertainty using Gaussian process implicit surfaces and Sequential Convex Programming

@article{Mahler2015GPGPISOPTGP,
  title={GP-GPIS-OPT: Grasp planning with shape uncertainty using Gaussian process implicit surfaces and Sequential Convex Programming},
  author={Jeffrey Mahler and S. Patil and Ben Kehoe and J. V. D. Berg and M. Ciocarlie and P. Abbeel and Ken Goldberg},
  journal={2015 IEEE International Conference on Robotics and Automation (ICRA)},
  year={2015},
  pages={4919-4926}
}
Computing grasps for an object is challenging when the object geometry is not known precisely. In this paper, we explore the use of Gaussian process implicit surfaces (GPISs) to represent shape uncertainty from RGBD point cloud observations of objects. We study the use of GPIS representations to select grasps on previously unknown objects, measuring grasp quality by the probability of force closure. Our main contribution is GP-GPIS-OPT, an algorithm for computing grasps for parallel-jaw… Expand
Robust Grasp Planning Over Uncertain Shape Completions
TLDR
Experimental results show statistically significant improvements both in terms of grasp quality metrics and grasp success rate, demonstrating that planning shape-uncertainty-aware grasps brings significant advantages over solely planning on a single shape estimate, especially when dealing with complex or unknown objects. Expand
Multi-Arm Bandit Models for 2 D Sample Based Grasp Planning with Uncertainty
For applications such as warehouse order fulfillment, robot grasps must be robust to uncertainty arising from sensing, shape, mechanics, and control. One way to achieve this is to evaluate theExpand
Building 3D Object Models during Manipulation by Reconstruction-Aware Trajectory Optimization
TLDR
This letter exploits Gaussian process implicit surfaces extracted from RGB-D sensor data to grasp an unknown object and proposes a reconstruction-aware trajectory optimization that makes use of the extracted GPIS model plan a motion to improve the ability to estimate the object's 3D geometry, while performing a pick-and-place action. Expand
Simultaneous Tactile Exploration and Grasp Refinement for Unknown Objects
TLDR
This letter proposes a grasp exploration approach using a probabilistic representation of shape, based on Gaussian Process Implicit Surfaces, which enables initial partial vision data to be augmented with additional data from successive tactile glances to refine grasp configurations. Expand
Budgeted Multi-Armed Bandit Models for Sample-Based Grasp Planning in the Presence of Uncertainty
Sampling perturbations in shape, state, and control can facilitate grasp planning in the presence of uncertainty arising from noise, occlusions, and surface properties such as transparency andExpand
Precision grasping based on probabilistic models of unknown objects
TLDR
This work proposes a two-stage grasp generation method, which is specifically designed for generating precision grasps, and achieves 78% success rate and shows robustness to the placement orientation. Expand
Multi-armed bandit models for 2D grasp planning with uncertainty
TLDR
This work forms robust grasp planning as a MAB problem and evaluates convergence times towards an optimal grasp candidate using 100 object shapes from the Brown Vision 2D Lab Dataset with 1000 grasp candidates per object. Expand
Automatic Grasp Pose Generation for Parallel Jaw Grippers
TLDR
A novel approach for the automatic offline grasp pose synthesis on known rigid objects for parallel jaw grippers using several criteria such as gripper stroke, surface friction, and a collision check to determine suitable 6D grasp poses on an object. Expand
Object shape estimation and modeling, based on sparse Gaussian process implicit surfaces, combining visual data and tactile exploration
TLDR
The presented approach is shown to provide computational efficiency, and also efficient use of the robot’s exploratory actions, and the proposed method yields adequate surface representations to distinguish objects. Expand
A Probabilistic Framework for Uncertainty-Aware High-Accuracy Precision Grasping of Unknown Objects
TLDR
This paper proposes an object model called probabilistic signed distance function (p-SDF) to represent unknown object surface and proposes a model to evaluate the likelihood of grasp success for antipodal grasps and uses the object representation as a bridge to unify grasp synthesis and grasp execution. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 54 REFERENCES
Toward cloud-based grasping with uncertainty in shape: Estimating lower bounds on achieving force closure with zero-slip push grasps
TLDR
This paper considers the most common robot gripper: a pair of thin parallel jaws, and a class of objects that can be modeled as extruded polygons, and model a conservative class of push-grasps that can enhance object alignment. Expand
Gaussian process implicit surfaces for shape estimation and grasping
TLDR
This work considers Gaussian process implicit surface potentials as object shape representations and validates the shape estimation using Gaussian processes in a simulation on randomly sampled shapes and the grasp controller on a real robot with 7 doF arm and 7DoF hand. Expand
On quality functions for grasp synthesis, fixture planning, and coordinated manipulation
TLDR
Preliminary experiments with a three-fingered robotic hand demonstrate that the proposed functions can be used to optimize the grasp quality during manipulation/manufacturing, and keep the optimal grasp configuration once it is reached. Expand
Budgeted Multi-Armed Bandit Models for Sample-Based Grasp Planning in the Presence of Uncertainty
Sampling perturbations in shape, state, and control can facilitate grasp planning in the presence of uncertainty arising from noise, occlusions, and surface properties such as transparency andExpand
Bayesian Grasp Planning
TLDR
A Bayesian framework for grasp planning is presented that takes into account uncertainty in object shape or pose, as well as robot motion error, allowing us to select grasps that are robust to incorrect object recognition aswell as motion error due to imperfect robot calibration. Expand
Estimating part tolerance bounds based on adaptive Cloud-based grasp planning with slip
TLDR
A procedure for finding the effect of increasing tolerance in vertices on grasp quality, which allows part tolerances to be bounded to ensure minimum grasp quality levels, is developed and found that including slip improves grasp quality estimates. Expand
Computation of Independent Contact Regions for Grasping 3-D Objects
TLDR
This paper presents an efficient algorithm to compute ICRs with any number of frictionless or frictional contacts on the surface of any 3-D object with robustness to finger positioning errors during an object grasping. Expand
Pose error robust grasping from contact wrench space metrics
  • Jonathan Weisz, P. Allen
  • Engineering, Computer Science
  • 2012 IEEE International Conference on Robotics and Automation
  • 2012
TLDR
This work examines a large number of grasps from the Columbia Grasp Database for the Barrett hand and finds that in most cases the grasp with the most robust force closure with respect to pose error for a particular object is not the grasped with the highest epsilon quality. Expand
Collaborative grasp planning with multiple object representations
TLDR
This work presents a framework that combines two approaches to grasp planning based on perceived sensor data of an object, aiming to find consensus on how the object should be grasped by using the information from each object representation according to their confidence levels. Expand
Output-Sensitive Computation of Force-Closure Grasps of a Semi-Algebraic Object
TLDR
A colored projection scheme is used from the three-dimensional wrench space to two-dimensional screens, which allows to reduce the problem of identifying combinations of arcs and concave vertices of a curved planar part that admit frictionless force-closure grasps, to colored intersection searching problems in the screens. Expand
...
1
2
3
4
5
...