Ulrich Hillenbrand

Surflet-pair-relation histograms: a statistical 3D-shape representation for rapid classification

A statistical representation of three-dimensional shapes is introduced, based on a novel four-dimensional feature. The feature parameterizes the intrinsic geometrical relation of an oriented surface-point pair. The set of all such features represents both local and global characteristics of the surface. We compress this set into a histogram. A database of histograms, one per object, is sampled in a training phase. During recognition, sensed surface data, as may be acquired by stereo vision, a laser range-scanner, etc., are processed and compared to the stored histograms. We evaluate the match quality by six different criteria that are commonly used in statistical settings. Experiments with artificial data containing varying levels of noise and occlusion of the objects show that Kullback-Leibler and likelihood matching yield robust recognition rates. We propose histograms of the geometric relation between two oriented surface points (surflets) as a compact yet distinctive representation of arbitrary three-dimensional shapes.

A Humanoid Two-Arm System for Dexterous Manipulation

This paper presents a humanoid two-arm system developed as a research platform for studying dexterous two-handed manipulation. The system is based on the modular DLR-Lightweight-Robot-III and the DLR-Hand-II. Two arms and hands are combined with a three degrees-of-freedom movable torso and a visual system to form a complete humanoid upper body. In this paper we present the design considerations and give an overview of the different sub-systems. Then, we describe the requirements on the software architecture. Moreover, the applied control methods for two-armed manipulation and the vision algorithms used for scene analysis are discussed

A humanoid upper body system for two-handed manipulation

This video presents a humanoid two-arm system developed as a research platform for studying dexterous two-handed manipulation. The system is based on the modular DLR-Lightweight-Robot-III and the DLR-Hand-II. Two arms and hands are combined with a three degrees-of-freedom movable torso and a visual system to form a complete humanoid upper body. The diversity of the system is demonstrated by showing the mechanical design, several control concepts, the application of rapid prototyping and hardware-in-the-loop (HIL) development as well as two-handed manipulation experiments and the integration of path planning capabilities.

Generalization of human grasping for multi-fingered robot hands

Multi-fingered robot grasping is a challenging problem that is difficult to tackle using hand-coded programs. In this paper we present an imitation learning approach for learning and generalizing grasping skills based on human demonstrations. To this end, we split the task of synthesizing a grasping motion into three parts: (1) learning efficient grasp representations from human demonstrations, (2) warping contact points onto new objects, and (3) optimizing and executing the reach-and-grasp movements. We learn low-dimensional latent grasp spaces for different grasp types, which form the basis for a novel extension to dynamic motor primitives. These latent-space dynamic motor primitives are used to synthesize entire reach-and-grasp movements. We evaluated our method on a real humanoid robot. The results of the experiment demonstrate the robustness and versatility of our approach.

Transferring functional grasps through contact warping and local replanning

We present a method for transferring grasps between objects of the same functional category. This transfer is intended to preserve the functionality of a grasp constructed for one of the objects, thus enabling the analogous action to be performed on a novel object for which no grasp has been specified. Manipulation knowledge is hence generalized from a single example to a class of objects with a significant amount of shape variability. The transfer is achieved through warping the surface geometry of the source object onto the target object, and along with it the contact points of a grasp. The warped contacts are locally replanned, if necessary, to ensure grasp stability, and a suitable grasp pose is computed. We present extensive results of experiments with a database of four-finger grasps, designed to systematically cover variations on grasping the mugs of the Princeton Shape Benchmark.

Consistent parameter clustering: Definition and analysis

Parameter clustering is a popular robust estimation technique based on location statistics in a parameter space where parameter samples are obtained from data samples. A problem with clustering methods is that they produce estimates not invariant to transformations of the parameter space. This article presents three contributions to the theoretical study of parameter clustering. First, it introduces a probabilistic formalization of parameter clustering. Second, it uses the formalism to define consistency in terms of a symmetry requirement and to derive criteria for a consistent choice of parameterization. And third, it applies the criteria to the practically relevant cases of motion and pose estimation of three-dimensional shapes. Bias and error statistics on random data sets demonstrate a significant advantage of using a consistent parameterization for rotation clustering. Moreover, clustering parameters of analytic shapes is discussed and a real application example of circle estimation given.

MRI-Based Skeletal Hand Movement Model

The kinematics of the human hand is optimal with respect to force distribution during pinch as well as power grasp, reducing the tissue strain when exerting forces through opposing fingers and optimising contact faces. Quantifying this optimality is of key importance when constructing biomimetic robotic hands, but understanding the exact human finger motion is also an important asset in, e.g. tracking finger movement during manipulation. The goal of the method presented here is to determine the precise orientations and positions of the axes of rotation of the finger joints by using suitable magnetic resonance imaging (MRI) images of a hand in various postures. The bones are segmented from the images, and their poses are estimated with respect to a reference posture. The axis orientations and positions are fitted numerically to match the measured bone motions. Eight joint types with varying degrees of freedom are investigated for each joint, and the joint type is selected by setting a limit on the rotational and translational mean discrepancy. The method results in hand models with differing accuracy and complexity, of which three examples, ranging from 22 to 33 DoF, are presented. The ranges of motion of the joints show some consensus and some disagreement with data from literature. One of the models is published as an implementation for the free OpenSim simulation environment. The mean discrepancies from a hand model built from MRI data are compared against a hand model built from optical motion capture data.

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 Hillenbrand (2007) [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.

Subthreshold dynamics of the neural membrane potential driven by stochastic synaptic input

In the cerebral cortex, neurons are subject to a continuous bombardment of synaptic inputs originating from the networks background activity. This leads to ongoing, mostly subthreshold membrane dynamics that depends on the statistics of the background activity and of the synapses made on a neuron. Subthreshold membrane polarization is, in turn, a potent modulator of neural responses. The present paper analyzes the subthreshold dynamics of the neural membrane potential driven by synaptic inputs of stationary statistics. Synaptic inputs are considered in linear interaction. The analysis identifies regimes of input statistics which give rise to stationary, fluctuating, oscillatory, and unstable dynamics. In particular, I show that (i) mere noise inputs can drive the membrane potential into sustained, quasiperiodic oscillations (noise-driven oscillations), in the absence of a stimulus-derived, intraneural, or network pacemaker; (ii) adding hyperpolarizing to depolarizing synaptic input can increase neural activity (hyperpolarization-induced activity), in the absence of hyperpolarization-activated currents.

On the relation between probabilistic inference and fuzzy sets in visual scene analysis

Strict probabilistic inference is a difficult and costly procedure, and generally unfeasible in practice for interesting cases. It requires knowledge, storage, and computational handling of usually very complicated probability-density functions of the data. Independence assumptions commonly made to alleviate these problems are often wrong and may lead to unsatisfactory results. By contrast, working with fuzzy sets in data space is simple, while the underlying assumptions have remained largely obscure. Here I derive from probabilistic principles a fuzzy-set-type formulation of visual scene interpretation. The argument is focused on making explicit the conditions for reasoning with fuzzy sets and how their membership function should be constructed. It turns out that the conditions may be fulfilled to a good approximation in some cases of visual scene analysis.