Robert Haschke

Platform portable anthropomorphic grasping with the bielefeld 20-DOF shadow and 9-DOF TUM hand

We present a strategy for grasping of real world objects with two anthropomorphic hands, the three-fingered 9- DOF hydraulic TUM and the very dextrous 20-DOF pneumatic Bielefeld Shadow Hand. Our approach to grasping is based on a reach-pre-grasp-grasp scheme loosely motivated by human grasping. We comparatively describe the two robot setups, the control schemes, and the grasp type determination. We show that the grasp strategy can robustly cope with inaccurate control and object variation. We demonstrate that it can be ported among platforms with minor modifications. Grasping success is evaluated by comparative experiments performing a benchmark test on 21 everyday objects.

On-line planning of time-optimal, jerk-limited trajectories

Service robots which directly interact with humans in highly unstructured, unpredictable and dynamic environments must be able to flexibly adapt their motion in reaction to unforeseen events or obstacles and they must provide a new feasible trajectory in real-time. Hence, algorithms come into focus which replan the motion path and its time evolution from arbitrary initial conditions within milliseconds. We present a real-time algorithm to generate synchronised and time-optimal third-order manipulator trajectories complying maximal motion limits on velocity, acceleration and jerk. Experimental results carried out on a Mitsubishi PA10-7C arm are presented.

Task-oriented quality measures for dextrous grasping

We propose a new and efficient approach to compute task oriented quality measures for dextrous grasps. Tasks can be specified as a single wrench to be applied, as a rough direction in form of a wrench cone, or as a complex wrench polytope. Based on the linear matrix inequality formalism to treat the friction cone constraints we formulate respective convex optimization problems, whose solutions give the maximal applicable wrench in the task direction together with the needed contact forces. Numerical experiments show that application to complex grasps with many contacts is possible.

Situated robot learning for multi-modal instruction and imitation of grasping

Abstract A key prerequisite to make user instruction of work tasks by interactive demonstration effective and convenient is situated multi-modal interaction aiming at an enhancement of robot learning beyond simple low-level skill acquisition. We report the status of the Bielefeld GRAVIS-robot system that combines visual attention and gestural instruction with an intelligent interface for speech recognition and linguistic interpretation to allow multi-modal task-oriented instructions. With respect to this platform, we discuss the essential role of learning for robust functioning of the robot and sketch the concept of an integrated architecture for situated learning on the system level. It has the long-term goal to demonstrate speech-supported imitation learning of robot actions. We describe the current state of its realization to enable imitation of human hand postures for flexible grasping and give quantitative results for grasping a broad range of everyday objects.

A Probabilistic Approach to Tactile Shape Reconstruction

In this paper, we present a probabilistic spatial approach to build compact 3-D representations of unknown objects probed by tactile sensors. Our approach exploits the high frame rates provided by modern tactile sensors and utilizes Kalman filters to build a probabilistic model of the contact point cloud that is efficiently stored in a kd-tree. The quality of generated shape representations is compared with a naive averaging approach, and we show that our method provides superior accuracy. We also evaluate the feasibility of object classification combining the generated object representations, together with the iterative closest point algorithm.

Flexible and stretchable fabric-based tactile sensor

We introduce a novel, fabric-based, flexible, and stretchable tactile sensor, which is capable of seamlessly covering natural shapes. As humans and robots have curved body parts that move with respect to each other, the practical usage of traditional rigid tactile sensor arrays is limited. Rather, a flexible tactile skin is required. Our design allows for several tactile cells to be embedded in a single sensor patch. It can have an arbitrary perimeter and can cover free-form surfaces. In this article we discuss the construction of the sensor and evaluate its performance. Our flexible tactile sensor remains operational on top of soft padding such as a gel cushion, enabling the construction of a human-like soft tactile skin. The sensor allows pressure measurements to be read from a subtle less than 1?kPa up to high pressures of more than 500?kPa, which easily covers the common range for everyday human manual interactions. Due to a layered construction, the sensor is very robust and can withstand normal forces multiple magnitudes higher than what could be achieved by a human without sustaining damage.As an exciting application for the sensor, we describe the construction of a wearable tactile dataglove with 54 tactile cells and embedded data acquisition electronics. We also discuss the necessary implementation details to maintain long term sensor performance in the presence of moisture. A flexible and stretchable durable fabric-based tactile sensor capable of capturing typical human interaction forces was developed.We present elaborate measurement results of the sensor.A process of creating multiple sensor areas in a single fabric patch was developed.The measures against performance degradation due to moisture are presented.Using the developed technology, a tactile dataglove with 54 pressure sensitive regions was built.

The curious robot - Structuring interactive robot learning

If robots are to succeed in novel tasks, they must be able to learn from humans. To improve such human-robot interaction, a system is presented that provides dialog structure and engages the human in an exploratory teaching scenario. Thereby, we specifically target untrained users, who are supported by mixed-initiative interaction using verbal and non-verbal modalities. We present the principles of dialog structuring based on an object learning and manipulation scenario. System development is following an interactive evaluation approach and we will present both an extensible, event-based interaction architecture to realize mixed-initiative and evaluation results based on a video-study of the system. We show that users benefit from the provided dialog structure to result in predictable and successful human-robot interaction.

A control framework for tactile servoing

The advent of sensor arrays providing tactile feedback with high spatial and temporal resolution asks for new control strategies to exploit this important and valuable sensory channel for grasping and manipulation tasks. In this paper, we introduce a control framework to realize a whole set of tactile servoing tasks, i.e. control tasks that intend to realize a specific tactile interaction pattern. This includes such simple tasks like tracking a touched object, maintaining both contact location and contact force, as well as more elaborate tasks like tracking an object’s pose or tactile object exploration. Exploiting methods known from image processing, we introduce robust feature extraction methods to estimate the 2D contact position, the contact force, and the orientation of an object edge being in contact to the sensor. The flexible control framework allows us to adapt the PID-type controller to a large range of different tasks by specification of a projection matrix toggling certain control components on and off. We demonstrate and evaluate the capabilities of the proposed control framework in a series of experiments employing a 16×16 tactile sensor array attached to a Kuka LWR as a large fingertip.

Real-time 3D segmentation of cluttered scenes for robot grasping

We present a real-time algorithm that segments unstructured and highly cluttered scenes. The algorithm robustly separates objects of unknown shape in congested scenes of stacked and partially occluded objects. The model-free approach finds smooth surface patches, using a depth image from a Kinect camera, which are subsequently combined to form highly probable object hypotheses. The real-time capabilities and the quality of the algorithm are evaluated on a benchmark database. Advantages compared to existing approaches as well as weaknesses are discussed. We also report on an autonomous grasping experiment with the Shadow Robot Hand which employs the estimated shape and pose of objects given by our algorithm in a task in which it cleans a table.

A modular high-speed tactile sensor for human manipulation research

Tactile sensing is an important field of research in the domains of human-computer and human-robot interaction. To provide appropriate tactile sensing capabilities, this work presents the development of a new modular tactile sensor system focusing especially on high frame rates (up to 1.9 kHz) and good spatial resolution (5 mm). Larger sensor areas are composed from identical sensor modules providing a 16×16 matrix of tactels. We compare different tactel layouts and different force-sensitive materials to achieve optimal sensitivity especially to low forces in order to facilitate detection of first touch. An example application demonstrates the capability of the developed sensor to detect tiny variations in applied force.