The talk will deal with a fundamental problem in robotics and artificial intelligence: How to bridge the gap between semantics and perception. The semantic domain can be described as a set of symbols and meanings in the ontology which describe things. Symbolic representation is the way how things in…

The goal is to develop a manipulating anthropomorphic walker at DFKI. Experiences from some projects at DFKI, e.g. iStruct, AILA etc. should flow into the development. With regard to boundary conditions, first evaluations and concepts will presented.

In biologically motivated models for object segmentation and recognition, the ability to do stereo vision is often overlooked. Here I will present a model inspired by the ventral stream of the human visual cortex, which integrates disparity information of local features into a pattern recognition hi…

Robot localisation and mapping in its current state is dominated by the application of optical sensors in conjunction with probabilistic methods for sensor fusion. While attractive in structured environments, especially indoors, this approach does not always yield the desired results in unstructured…

This talk gives an overview about the current status and the planned work of the CAPIO project. Alternative concepts for the dual-arm exoskeleton - that also cover the human upper torso, and the human hands - are explained together with a design methodology that aims at improving the kinematics arch…

Communication methods in modern robotic systems are connecting multiple sensors, actuators, micro-controllers and embedded PCs. A lot of development time is used to set up communication between and within those systems. Modern robot control middlewares like e.g. ROS, Orocos and others improving this…

The CUSLAM project aims at the development of a vision-based localization and mapping algorithm (SLAM) specially tailored for underwater vehicles which operate in confined spatial structures. Traditional localization methods for underwater vehicles expect open terrain and constant line of sight to a…

The main goal of INVERITAS is the prototypic realization of a broad-spectrum rendezvous and docking (RvD) system All fundamental technologies necessary to engineer a satellite that can dock to other satellites in orbit will be developed. Lunar landing scenarios will also be simulated. Primary tasks…

The goal of the project CSurvey is the development of a semi-autonomous inspection unit which can be mounted on underwater vehicles and which provides the ability to detect anomalies at underwater structures as well as ship hulls. The CSurvey head is an integrated System which has its own intelligen…

The inspection of marine vessels is currently performed manually. Inspectors use sensors (e.g. cameras, devices for non-destructive testing) to detect damaged areas, cracks, and corrosion in large cargo holds, tanks, and other parts of a ship. Due to the size and complex geometry of most ships, ship…