• Home
  • Sebastian Rockel
Sebastian Rockel

Sebastian Rockel
  • Ph.D.
  • Engineer at Jungheinrich AG

About

12
Publications
1,499
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
120
Citations
Introduction
I am research associate at the University of Hamburg. I worked on the EU FP7 project "RACE" and I am now working for the EU FP7 project "Robot-Era".
Current institution
Jungheinrich AG
Current position
  • Engineer
Additional affiliations
September 2011 - present
Hamburg University
Position
  • PhD Student and Research Associate
Description
  • Working in the EU project RACE (www.project-race.eu), teaching Intelligent robotics project and supervising Master and Bachelor student. Furthermore developing ROS software for our PR2 robot Trixi:)
September 2011 - present
Hamburg University
Position
  • Intelligent Robotics Student Project Supervisor
Description
  • The goal of this two semester Master students course is to learn how to program a mobile robot for navigating, manipulating and perception. Therefore ROS as the standard open-source middle-ware will be used to program in simulation and on the PR2 robot.
Education
January 2012 - November 2015
Hamburg University
Field of study
  • Artificial Intelligence
April 2009 - July 2011
Hamburg University
Field of study
  • Computer Science (Informatik)
October 2002 - June 2005
Georg Simon Ohm University of Applied Sciences Nuremberg
Field of study
  • Computer Science (Informatik)

Publications

Publications (12)
Conference Paper
Full-text available
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...
Conference Paper
Full-text available
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...
Article
Full-text available
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...
Article
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...
Conference Paper
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...
Conference Paper
Full-text available
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...
Conference Paper
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...
Conference Paper
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...
Conference Paper
Full-text available
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...
Conference Paper
Full-text available
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...

Network

Cited By