Member Login

JCal Pro Mini-calendar

October 2019 November 2019 December 2019
Mo Tu We Th Fr Sa Su
Week 44 1 2 3
Week 45 4 5 6 7 8 9 10
Week 46 11 12 13 14 15 16 17
Week 47 18 19 20 21 22 23 24
Week 48 25 26 27 28 29 30

Current Time

The time is 19:05:52.
ALUMNI Dr. Sascha Jockel Print E-mail
Sascha Jockel

Contact Details

Formerly:

Department of Informatics
Hamburg University
Vogt-Kölln-Straße 30
22527 Hamburg, Germany

   
   
   
   
Former Supervisor: Prof. Jianwei Zhang

Short Biography

Dr. Sascha Jockel finished his PhD (2010) in the CINACS project while working for the group Technical Aspects of Multimodal Systems (TAMS), Department Informatics, University of Hamburg. He received his diploma degree in computer science from the University of Hamburg, Germany, in 2006.

Note: In October 2009 I joined the Diagnostic X-Ray (DXR) Development team of the Philips Medical Systems DMC GmbH. DXR develops, manufactures, sells and maintains highly complex medical devices for conventional and digital X-ray imaging.

Research Interests

  • Robotics and Sensors
  • Intelligent systems
  • Multimodal processing and interacting systems
  • Image processing
  • Natural and artificial cognition
  • Medical informatics

Hobbies

Abstract of my Dissertation

This work develops a connectionist memory model for a service robot that satisfi es a number of desiderata: associativity, vagueness, approximation, robustness, distribution and parallelism. A biologically inspired and mathematically sound theory of a highly distributed and sparse memory serves as the basis for this work. The so-called sparse distributed memory (SDM), developed by P. Kanerva, corresponds roughly to a random-access memory (RAM) of a conventional computer but permits the processing of considerably larger address spaces. Complex structures are represented as binary feature vectors. The model is able to produce expectations of world states and complement partial sensory patterns of an environment based on memorised experience. Caused by objects of the world, previously learnt experiences will activate pattern sequences in the memory and claim the system's attention. In this work, the sparse distributed memory concept is mainly considered a biologically inspired and content-addressable memory structure. It is used to implement an autobiographical long-term memory for a mobile service-robot to store and retrieve episodic sensor and actuator patterns.

Within the scope of this work the sparse distributed memory concept is applied to several domains of mobile service robotics, and its feasibility for the respective areas of robotics is analysed. The studied areas range from pattern matching, mobile manipulation, navigation, telemanipulation to crossmodal integration. The robot utilises properties of sparse distributed memory to detect intended actions of human teleoperators and to predict the residual motion trajectory of initiated arm or robot motions. Several examples show the model's fast and online learning capability for precoded and interactively provided motion sequences of a 6 DoF robot arm. An appropriate encoding of sensor-based information into a binary feature space is discussed and alternative coding schemes are elucidated.

A transfer of the developed system to robotic subfi elds such as vision-based navigation is discussed. The model's performance is compared across both of these domains, manipulation and navigation. A hierarchical extension enables the memory model to link low-level sensory percepts to higher-level semantic task descriptions. This link is used to perform a classi fication of demonstrated telemanipulation tasks based on the robot's experience in the past. Tests are presented where di fferent sensory patterns are combined into an integrated percept of the world. Those crossmodal percepts are used to dissolve ambiguities that may arise from unimodal perception.

For further information confer:
Jockel, S. (2010). Crossmodal Learning and Prediction of Autobiographical Episodic Experiences using a Sparse Distributed Memory. Dissertation, University of Hamburg, Germany, October 2010. [PDF] or http://www.saschajockel.de

Publications

Jockel, S. (2010). Crossmodal Learning and Prediction of Autobiographical Episodic Experiences using a Sparse Distributed Memory. Dissertation, University of Hamburg, Germany, October 2010. [PDF]

Jockel, S., Mendes, M., Zhang, J., Paulo Coimbra, A. & Crisóstomo, M. (2009). Robot Navigation and Manipulation based on a Predictive Associative Memory. Proceedings of the 2009 IEEE 8th International Conference on Development and Learning (ICDL), Shanghai, China, June 4-7, 2009. [PDF]

Klimentjew, D., Stroh, A., Jockel, S. & Zhang, J. (2000). Real-Time 3D Environment Perception: An Application for Small Humanoid Robots. Proceedings of the 2008 IEEE International Conference on Robotics and Biomimetics (ROBIO), Bangkok, Thailand, February 21-26, 2009, pp. 354-359. ISBN: 978-1-4244-2679-9.

Jockel, S., Lindner, F. & Zhang, J. (2008). Sparse Distributed Memory for Experience-Based Robot Manipulation. Proceedings of the 2008 IEEE International Conference on Robotics and Biomimetics (ROBIO), Bangkok, Thailand, February 21-26, 2009, pp. 1298-1303. ISBN: 978-1-4244-2679-9. [PDF]

Jockel, S., Weser, M., Westhoff, D. & Zhang, J. (2008). Towards an Episodic Memory for Cognitive Robots. In Proceedings of the 6th International Cognitive Robotics Workshop at the 18th European Conference on Artificial Intelligence (ECAI), Patras, Greece, IOS Press, 21-22 July 2008, pp. 68-74. ISBN: 978-960-6843-09-9. [PDF]

Weser, M., Jockel, S. & Zhang, J. (2008). Fuzzy Multisensor Fusion for Autonomous Proactive Robot Perception. In Proceedings of IEEE International Conference on Fuzzy Systems (FUZZ 2008) at IEEE World Congress on Computational Intelligence (WCCI), Hong Kong, China, 1-6 June 2008, pp. 2262-2267. ISBN: 978-1-4244-1819-0. [PDF]

Jockel, S., Westhoff, D. & Zhang, J. (2007). EPIROME -- A Novel Framework to Investigate High-Level Episodic Robot Memory. Proceedings of IEEE International Conference on Robotics and Biomimetics (ROBIO), Sanya, China, 15 - 18 December 2007, IEEE Press, pp. 1075-1080. [IEEE Xplore article]. Digital Object Identifier: 10.1109/ROBIO.2007.4522313.

Jockel, S., Baier-Löwenstein, T. & Zhang, J. (2007). Three-Dimensional Monocular Scene Reconstruction for Service-Robots -- An Application. Proceedings of VISAPP 2007 - Second International Conference on Computer Vision Theory and Applications, Vol. Special Sessions, Barcelona, Spain, 08 - 11 March 2007, INSTICC Press, pp. 41 - 46. [PDF]

Events Attended

Project Management Course
Hamburg University

2009
24th Image Processing Workshop
HAW, Hamburg, Germany

2008
3rd CINACS International Summer School 2008
Topic: Cross-modal Communication
Hamburg, Germany

2008
6th Int. Cognitive Robotics Workshop(CogRob)
of the European Conference on Artificial Intelligence (ECAI)
Patras, Greece

2008
9th Int. Multisensory Research Forum (IMRF)
Hamburg, Germany

2008
2nd CINACS International Summer School 2007
Topic: Cross-modal Communication
Beijing, China

2007
IEEE Int. Conf. on Robotics and Biomimetics (ROBIO)
Sanya, China

2007
China-EU-India Triangular School
Topic: Complexity in neural and socio-economic networks
Beijing, China

2007
2nd Int. Conf. on Computer Vision Theory and Applications (VISAPP)
Barcelona, Spain

2007
1st CINACS International Summer School 2006
Topic: Cross-modal Communication
Beijing, China

2006
9th IEEE Int. Conf. on Control, Automation, Robotics and Vision (ICARCV)
Singapore

2006
Visualisation for Image Based Diagnostics and Therapy Planning Tutorial
Conference on Image Processing for Medical Purposes
Hamburg, Germany

2006
10th Conference on Information Processing in Hospitals and Medical Care Networks
Hamburg, Germany

2005