An experimental study of four variants of pose clustering from dense range data

Abstract

Parameter clustering is a robust estimation technique based on location statistics in a parameter space where parameter samples are computed from data samples. This article investigates parameter clustering as a global estimator of object pose or rigid motion from dense range data without knowing correspondences between data points. Four variants of the algorithm are quantitatively compared regarding estimation accuracy and robustness: sampling poses from data points or from points with surface normals derived from them, each combined with clustering poses in the canonical or consistent parameter space, as defined in [1]. An extensive test data set is employed: synthetic data generated from a public database of three-dimensional object models through various levels of corruption of their geometric representation; real range data from a public database of models and cluttered scenes. It turns out that sampling raw data points and clustering in the consistent parameter space yields the estimator most robust to data corruption. For data of sufficient quality, however, sampling points with normals is more efficient; this is most evident when detecting objects in cluttered scenes. Moreover, the consistent parameter space is always preferable to the canonical parameter space for clustering.

Geometric backtracking for combined task and motion planning in robotic systems

“…Given known geometric models of possible objects in the actual scene, an interpretation of that scene in terms of object classes and poses is computed [48,49].…”

Sequential trajectory re-planning with tactile information gain for dexterous grasping under object-pose uncertainty

“…We assume a known point cloud model of the object shape, and uncertainty in the object pose. In this trial the robot observes the object as a point cloud and applies a model fitting process described in [4]. The model fitting process is stochastic and so the resulting pose of the object is uncertain.…”

“…This gives an incomplete point cloud of the object surface. Using a model fitting procedure similar to the sampling from surflet pairs method presented in [4], a probability density (or belief state) over the object pose is estimated, represented as a particle set. Given this distribution, a reach-to-grasp trajectory is planned.…”

Generalization of human grasping for multi-fingered robot hands

“…Three different types of mugs were used during the experiments. After placing a mug on a table in front of the robot, all information about the pose of the mug was estimated using a Kinect camera and the techniques explained in [12]. Subsequently, using the contact warping techniques from Sec.…”

“…The alignment step involves sampling and aligning many surflet pairs, i.e., pairs of surface points and their local normals, from source and target shapes. The estimation of relative clusters of the pose parameters is obtained from the surflet-pair alignments [11], [12].…”