First construction robots had been designed in the beginning seventies in order to increase the quality in prefabrication of modular homes in Japan and the late 70ies planning started for use of robots in construction sites. In the 80ies the first construction robots appeared on sites and in the 90i…

Data processing of today (like communication networks, multiagent systems, swarm intelligence, ubiquitous, wearable and mobile computing) is often distributed and comprises various components that run partially independent of each other, but may access and update the same information structures, com…

The increasing number of launched satellites per year, calls for solutions to keep free operational space for telecommunication systems in geo-synchronized orbit, as well as to avoid the endangering of space systems in LEO and of the public living in the habited parts on Earth. A feasible way to ha…

In this talk I present some reinforcement learning architectures and algorithms designed to solve robot control problems with continuous state and action spaces, where the use of function approximators to represent the value functions is a must. I start by defining an architecture for supervised rei…

An environment where virtual worlds coexist with real worlds, Mixed Reality, has been extensively studied in the last decade. Mixed reality is not restricted to a mixing of visual images or sounds, but include other phenomena (e.g., electric, mechanical, hydraulic, aerodynamic, thermodynamic). The e…

In robotics, Qualitative Spatial Reasoning (QSR) is typically known in the context of robot navigation and task planning. Here, I will present an approach that uses methods derived from QSR for spatial information retrieval from structured and unstructured documents. This approach applies a low-leve…

Marine waters and especially coastal zones are subject to intensive utilization, such as transport, tourism, fisheries and energy generation. The assessment and monitoring of anthropogenic as well as natural threats and changes to the marine environment is crucial to understand their dynamics and to…

The behavior of species (i.,e. classes of similar natural agents) is optimized on different time-scales, ranging from long-term optimization of morphology and structure on the level of generations of agents (evolution) to short-term optimization of an agents behavior during its lifetime (learning). …

Neural networks are useful in evolving the control systems of agents. They provide a straightforward mapping between sensors and motors, enabling them to represent directly the policy (control) or the value function to be learned. It has been shown using standard benchmark problems that combinations…

Am Bremer Institut für Produktion und Logistik an der Universität Bremen (BIBA) wurde ein neues Verfahren zur vollständigen Automatisierung des Paketumschlages entwickelt und erprobt. Durch eine systematisch-grundlagenorientierte Untersuchung wurden bestehende Defizite in der Roboter- und Greifertec…