Sebastian Rockel

• Ph.D.
• Engineer at Jungheinrich AG

Real-world robotic systems have to deal with uncertain and dynamic environments in order to reliably perform tasks. State-of-the-art cognitive robotic systems use an abstract symbolic representation of the real-world, which is used for high level reasoning. Some aspects of the world — such as object dynamics — are inherently difficult to capture in...

For a robot serving in a complex environment such as in a restaurant, it is difficult to perform a task like tabletop object manipulation completely by itself, in that some information may be missing. An approach to deal with this is to use a tele-control system and method to control the robot or demonstrate. In this paper, a LeapMotion sensor base...

This paper reports on the aims, the approach, and the results of the European project RACE. The project aim was to enhance the behavior of an autonomous robot by having the robot learn from conceptualized experiences of previous performance, based on initial models of the domain and its own actions in it. This paper introduces the general system ar...

The approach presented shows possible ways of improving scene analysis to achieve more reliable and accurate object recognition in the context of mobile robotics. The centralized architecture combines different feature detectors with active modalities, such as change of perspective or influencing the scene. It opens possibilities for the use of 2D...

In this paper, an FIM (Fitness to Ideal Model) and a DLen (Description Length) based evaluation approach has been developed to measure the benefit of learning from experience to improve the robustness of the robot's behavior. The experience based mobile artificial cognitive system architecture is briefly described and adopted by a PR2 service robot...

In This work we ask whether an integrated system based on The concept of human imagination and realized as a hyperreal setup can improve system robustness and autonomy. In particular we focus on how non-nominal failures in a planning-based system can be detected before actual failure. To investigate, we integrated a system combining an accurate phy...

This work presents parallel plan execution, an intermediate layer for mobile robot systems using high-level planners such as Hierarchical Task Network planning to execute a series of actions. Sequential plans generated by high-level planners leave system resources unused while unnecessarily increasing execution time of generated plans. This increas...

Recording and exploiting past experiences to handle an unforeseen situation is an important asset of human beings. However, in current robot architectures, experience-based learning has mainly been realized at sub-symbolic levels. In this paper, we present how to handle exception for an experience-based artificial cognitive system which is able to...

One way to improve the robustness and flexibility of robot performance is to let the robot learn from its experiences. In this paper, we describe the architecture and knowledge-representation framework for a service robot being developed in the EU project RACE, and present examples illustrating how learning from experiences will be achieved. As a u...

In the field of robotics, typical, single-robot systems encounter limits when executing complex tasks. Todays systems often lack flexibility and inter-operability, especially when interaction between participants is necessary. Nevertheless, well developed systems for robotics and for the cognitive and distributive domain are available. What is miss...