Christian Scheering

Uncalibrated hand-eye coordination with a redundant camera system

We describe a method for 3D visual manipulator control using a redundant camera system without explicit external or internal calibration. Under the assumption of a simple linear camera model a fusion equation is derived for which only three parameters have to be estimated regardless of the number of cameras. In simulations as well as in real experiments the feasibility of our approach for a 3D positioning task of a six degree of freedom (DOF) Puma 200 to a target is demonstrated. It is shown that using redundant views increases positioning accuracy and fault tolerance. The achieved accuracy is sufficient to perform an additional insertion task.

A neuro-fuzzy solution for integrated visual and force control

In this paper the use of a B-spline neuro-fuzzy model for different tasks such as vision-based fine positioning using uncalibrated cameras and force control is presented. It is shown that neuro-fuzzy controllers can be used not only for low-dimensional problems like force control but also for high-dimensional problems like vision-based sensorimotor control and for fusing input from different sensors. Controllers of this type can be modularly combined to solve a given assembly problem.

A Situated Artificial Communicator for Assembly Tasks

SummaryIn this article we describe a Situated Artificial Communicator for assembly tasks. The main components of the system we are developing are a speech understanding module and a two-arm-robot module. The robot system can be instructed using spontaneous speech. The speech understanding module is based on Combinatory Categorial Grammar, which makes incremental and interactive speech understanding possible. The robot module is provided with multiple sensors and it masters complex assembly operations like peg-in-hole or screwing a nut into a bolt. The architecture and the underlying cognitive principles enable interactive processing that depends on the actual situation and allows the system to take advantage of redundant items of information. Due to these principles our Situated Artificial Communicator is highly robust.ZusammenfassungIn diesem Beitrag stellen wir einen Situierten Künstlichen Kommunikator vor, im vorliegenden Fall ein Robotersystem für Konstruktionsaufgaben. Das Robotersystem kann durch spontansprachliche Anweisungen gesteuert werden. Die Hauptkomponenten des Systems sind eine Sprachverstehenskomponente und eine Zwei-Arm-Roboterkomponente. Die Sprachverstehenskomponente basiert auf der Combinatory Categorial Grammar und ermöglicht eine inkrementelle und interaktive Sprachverarbeitung. Die Roboterkomponente verfügt über eine Vielzahl von Sensoren und beherrscht Montageoperationen wie Stecken und Schrauben. Durch die gewählte Architektur und die zugrundegelegten kognitiven Verarbeitungsprinzipien können Teilkomponenten des Systems der aktuellen Situation entsprechend interagieren und Informationsredundanz nutzen. Das System erhält dadurch eine hohe Robustheit.

Ein situierter Künstlicher Kommunikator für Konstruktionsaufgaben

SummaryIn this article we describe a Situated Artificial Communicator for assembly tasks. The main components of the system we are developing are a speech understanding module and a two-arm-robot module. The robot system can be instructed using spontaneous speech. The speech understanding module is based on Combinatory Categorial Grammar, which makes incremental and interactive speech understanding possible. The robot module is provided with multiple sensors and it masters complex assembly operations like peg-in-hole or screwing a nut into a bolt. The architecture and the underlying cognitive principles enable interactive processing that depends on the actual situation and allows the system to take advantage of redundant items of information. Due to these principles our Situated Artificial Communicator is highly robust.ZusammenfassungIn diesem Beitrag stellen wir einen Situierten Künstlichen Kommunikator vor, im vorliegenden Fall ein Robotersystem für Konstruktionsaufgaben. Das Robotersystem kann durch spontansprachliche Anweisungen gesteuert werden. Die Hauptkomponenten des Systems sind eine Sprachverstehenskomponente und eine Zwei-Arm-Roboterkomponente. Die Sprachverstehenskomponente basiert auf der Combinatory Categorial Grammar und ermöglicht eine inkrementelle und interaktive Sprachverarbeitung. Die Roboterkomponente verfügt über eine Vielzahl von Sensoren und beherrscht Montageoperationen wie Stecken und Schrauben. Durch die gewählte Architektur und die zugrundegelegten kognitiven Verarbeitungsprinzipien können Teilkomponenten des Systems der aktuellen Situation entsprechend interagieren und Informationsredundanz nutzen. Das System erhält dadurch eine hohe Robustheit.

Using Distributed Sensing and Sensor Fusion for Uncalibrated Visual Manipulator Guidance

We describe a method for 3D visual manipulator control using a redundant camera system without explicit external or internal calibration. Under the assumption of a simple linear camera model, a fusion equation is derived for which only three parameters have to be estimated, regardless of the number of cameras. Distributed sensor-units provide the necessary measurements, which are fused together in a Kalman filter. In simulations, as well as in real experiments, the feasibility of our approach for a 3D positioning task of a six degree of freedom (DOF) Puma 200 to a target is demonstrated. It is shown that using redundant views increases positioning accuracy and fault tolerance. The achieved accuracy is sufficient to perform an insertion task.

Fast colour image segmentation using a pre-clustered chromaticity-plane

We present an efficient method for segmenting colour-images, which may be utilised in several robotic vision tasks. It categorises pixels according to their perceptual colour by exploiting the chromaticity contained in the signal of a standard colour camera as an index into a pre-clustered chromaticity plane. A technique called perceptual colour grouping is introduced to prevent oversegmentation. Experimental data demonstrate the performance of the proposed approach; computation time is reduced by a factor of 8...30 over previously known methods.

Distributed multiple view fusion for two-arm distance estimation

We propose an approach for estimating the distance of two moving robot arms based on fusion of multiple vision data. The images are fused by simple concatenation of all images followed by a projection of the high-dimensional visual input data into an appropriate low-dimensional subspace. We extended the well known principal component analysis to the so-called output relevant features and present a distributed online computation algorithm performing the projection in parallel. We show that complex sensor data can be efficiently compressed if the robot motions are constrained to a local scenario. The second component of our model is an adaptive B-spline neuro-fuzzy controller whose input space is the constructed subspace and whose output is the estimated distance. Our experimental setup is a two-arm robot system with four uncalibrated cameras. Experiments with a complex circular motion show that the method works even if no robust geometric features can be extracted from the sensor pattern.