Teaching

General Classes

Class / Event Lecturer Abstract
Cognitive Systems

Thomas Barkowsky, Frank Dylla,
Christian Freksa

A two-semester course on natural and artificial cognitive systems. The first semester provides an introduction to basic concepts, terminology, and methods used in the interdisciplinary study of cognitive systems; it covers foundations of perception, memory and reasoning, learning and action, and verbal and non-verbal communication.

The course consists of lectures and practical implementation tasks. The goal of the course is to provide a basic understanding of concepts and methods of cognitive science. The course will be both in English and in German such that

  • german students will experience a smooth introduction to English courses and that
  • international students will be able to participate in this course.
Spatial Cognition

Thomas Barkowsky

This seminar provides an introduction to the interdisciplinary research field of spatial cognition from an informatics point of view. Spatial cognition deals with the acquisition, organization, utilization, and communication of information about spatial environments. As such, it is fundamental to intelligent human behavior and forms the basis of many other, even abstract cognitive capabilities. In the seminar, we also will learn about specific topics in spatial cognition like spatial knowledge representation, spatial memory, wayfinding and navigation, or spatial communication.

Cognitive Modeling

 

Holger Schultheis
Thomas Barkowsky,
Christian Freksa

A two-semester course on natural and artificial cognitive systems. The first semester provides an introduction to basic concepts, terminology, and methods used in the interdisciplinary study of cognitive systems; it covers foundations of perception, memory and reasoning, learning and action, and linguistic and non-linguistic communication.

The second semester investigates methods from psychology, neuroscience, and informatics in more detail; cognitive architectures and modeling approaches are studied; we perform case studies in cognitive modeling and discuss challenges for the field of cognitive science. The course consists of lectures, reading, modeling, and writing assignments, and discussion groups. The goal of the course is to provide a firm grasp on concepts and methods of cognitive science.

SFB/TR 8 / IQN colloquium
Spatial Cognition
Christian Freksa,
Kerstin Schill, 
John Bateman,
Wolfram Burgard, 
Bernhard Nebel

This colloquium is part of the International Quality Network of the Universities of Bremen, Freiburg, and Hamburg in cooperation with 23 international partner universities and the Transregional Collaborative Research Center Spatial Cognition: Reasoning, Action, Interaction of the Universities Bremen and Freiburg. Scientists of the participating institutions and guests report on their research in the area of spatial cognition. Usually research groups from other locations are connected through an interactive teleconferencing network.

Graduate seminar
Cognitive Systems
Christian Freksa
Carl Schultz 
 

Ph.D. and master/diploma students discuss their current research. For the preparation of the session the candidates distribute a research paper one or two weeks ahead of time to the seminar participants. In the seminar session, the most important aspects of the paper are summarized by the author to initiate an in-depth discussion of the work in progress.

Student Projects    

CogQDA:

Cognitive Qualitative Descriptions and Applications

Zoe Falomir

website

The seminar provides an introduction to Qualitative Descriptions and Reasoning from a Cognitive point of view. It is divided into 2 learning modules and 1 working module. The topic of each module is introduced as follows:

Module I: If you were a robot, you would see the world pixelized through your camera. How would you explain to a human being what do you see? What concepts could you use for the human to understand you?

Module II: Psychological studies proved that people with good spatial cognition skills, are successful in STEM (Science Technology Engineering and Math). Other studies say that we humans can train these spatial skills. Therefore:

  • How do we measure our spatial cognition skills? How do we improve them? Can we build systems that help us to improve them?
  • Can a robot have spatial cognition skills? What logical thinking must the robot have?

Module III: From all the contents, what is the most interesting topic for you? Which one would you like to explore/learn/research more? How? Theoretically or practically? Let's explore it together. What have you learned? What can you teach us?

     

 

 

List of all lectures

Cognitive Systems - SoSe 2015

 

Course 03-BB-711.01

Cognitive Systems

Thomas Barkowsky, Frank Dylla, Christian Freksa

Summer 2015

lecture: Mon 08:30 - 10:00 Cartesium Rotunde

tutorials:
Wed 08:30 - 10:00 Cartesium Rotunde
Wed 10:15 - 11:45 Cartesium Rotunde

4 SWS (ECTS: 6)

course language: English / German

 

   

The technical discussions ("Fachgespräche") will be held on Monday, 20 July 2015 (and on Monday, 28 September 2015, for repeaters). To participate in a technical discussion, please register by 04 July 2015 (or by 12 September 2015, for repeaters) by sending an email to cosy@informatik.uni-bremen.de. When registering, the email should list the names of all participants of the group (one mail per group is sufficient). Please note that the successful participation in the tutorials is a precondition for registering for a technical discussion.

 

 

 

Tutorials (22 April; 06 May; 20 May; 03 June; 17 June; 01 July; 15 July)

Tutorial 1 (Thomas Barkowsky): Wed 08:30-10:00
Tutorial 2 (Thomas Barkowsky): Wed 10:15-11:45
 

 

Assignments / Credits

To receive credit for this course you have to work on six written / programming exercises (see return dates below). Please send your solutions to cosy-exercises@informatik.uni-bremen.de with the subject of the mail starting with "CoSy / Tutorial <n>" (numbers of tutorials see above). The mail should contain a written documentation as .pdf, .rtf, or .doc file as well as the source code of your implementation. This work is to be done in groups of 3-4 students. In the six exercises you have to reach an average grade of at least 60%. In the tutorial, each group has to present their solutions in an appropriate way (slide presentation, handout).

At the end of the semester we will have a technical discussion of 30 minutes with every group to check whether the marks achieved in each working group are homogeneously applicable to all candidates of the group and to decide on individual marks.

We much encourage collaboration and collaborative work will be especially required when completing your exercises. However, collaboration is to be sharply distinguished from cheating. No forms of cheating (including plagiarism) will be tolerated, so don't! If you do, rest assured that we will find out about it. Should you be caught cheating, this may result in your automatic failure in the course.

Return dates for the exercises:
No. 1: 03 May; No. 2: 17 May; No. 3: 31 May; No. 4: 14 June; No. 5: 28 June; No. 6: 12 July

 

Literature

Anderson, J. R. (2009). Cognitive psychology and its implications (7th ed.). New York: Worth Publishers.

Palmer, S. E. (1999). Vision science - Photons to phenomenology. Cambridge, MA: MIT Press.

 

Cognitive Modeling - WS 2016/17

Course 03-MB-711.02

Holger Schultheis

Winter 2016/17
Mondays 8 - 12 Cartesium Room 0.01
4 SWS (ECTS: 6)

Further detail on the course is available through Stud.IP.

Spatial Cognition - WS 2015/16

Course 03-ME-711.03

Thomas Barkowsky

Winter 2015/16
Thursdays 16:00 - 18:00h, Cartesium 0.01
2 SWS (ECTS: 4)

Syllabus

A Introduction

1) 15 Oct 2015:

  • Introduction to Spatial Cognition
  • Distribution of topics for the presentations

B Spatial Representations

2) 22 Oct 2015:

3) 29 Okt 2015:
  • Analogical Representations (Sloman (1971, 1975))

C Mental Models

4) 05 Nov 2015:

5) 12 Nov 2015:

D Mental Images

6) 19 Nov 2015:

7) 26 Nov 2015:

8) 03 Dec 2015:

E Diagrams

9) 10 Dec 2015:

10) 17 Dec 2015:

F Cognitive Architectures

11) 14 Jan 2016:

12) 21 Jan 2016:

13) 28 Jan 2016:

G Wrap-Up

14) 04 Feb 2016:

  • Final Discussion

 

References

  • Byrne, R. M. J. & Johnson-Laird, P. N. (1989). Spatial reasoning. Journal of Memory and Language, 28:564– 575.
  • Chandrasekaran, B., Banerjee, B., Kurup, U., & Lele, O. (2011). Augmenting cognitive architectures to support diagrammatic imagination. Topics in Cognitive Science, 3.
  • Forbus, K., Usher, J., Lovett, A., Lockwood, K., & Wetzel, J. (2011). CogSketch: Sketch understanding for cognitive science research and for education. Topics in Cognitive Science, 3:648-666.
  • Funt, B. V. (1980). Problem-solving with diagrammatic representations. Artificial Intelligence, 13.
  • Glasgow, J., & Papadias, D. (1992). Computational imagery. Cognitive Science, 16.
  • Gunzelmann, G. & Lyon, D. R. (2007). Mechanisms for human spatial competence. In T. Barkowsky, M. Knauff, G. Ligozat, and D. R. Montello, editors, Spatial Cognition V - Reasoning, Action, Interaction, pages 288– 307. Springer, Berlin.
  • Kosslyn, S. M. (2005). Mental images and the brain. Cognitive Neuropsychology, 22(3-4):333–347.
  • Kosslyn, S. M., Shephard, J. M., & Thompson, W. L. (2007). Spatial processing during mental imagery: a neurofunctional theory. In F. Mast and L. Jancke (Eds), Spatial Processing in Navigation, Imagery, and Perception. New York: Springer. pp 1-16.
  • Palmer, S. (1978). Fundamental aspects of cognitive representation. In E. Rosch & B. Lloyd (Eds.) Cognition and Categorization, Hillsdale, NJ: LEA.
  • Ragni, M. & Knauff, M. (2013). A theory and a computational model of spatial reasoning with preferred mental models. Psychological Review, 120(3):561–588.
  • Schultheis, H., & Barkowsky, T. (2011). Casimir: An architecture for mental spatial knowledge processing. Topics in Cognitive Science, 3.
  • Sima, J. F. (2011). The nature of mental images – An integrative computational theory. In L. Carlson, C. Hölscher, and T. Shipley, editors, Proceedings of the 33rd Annual Conference of the Cognitive Science Society, pages 2878–2883. Cognitive Science Society, Austin, TX.
  • Sima, J. F. & Freksa, C. (2012). Towards computational cognitive modeling of mental imagery. Künstliche Intelligenz, 26(3):261–267.
  • Sloman, A. (1971). Interactions between philosophy and artificial intelligence. Artificial Intelligence, 2.
  • Sloman, A. (1975). Afterthoughts on analogical representations. In B. L. Nash-Webber & R. Schank (Eds.), Proc. theoretical issues in natural language processing. Cambridge, MA: Association for Computer Linguistics.

Course Credit

Here are a few notes on grading and other formal aspects of the course. To receive credits for the course you will need to actively and continually participate throughout the semester; this includes:

  • to read all papers,
  • to prepare 2 questions regarding each topic (based on the reading material for this topic)
  • to present at least one topic
  • to write a term paper on the topic you presented during the course. Here is a template for the term paper.

Questions for each topic have to be submitted by email to barkowsky@informatik.uni-bremen.de by the Wednesdays preceding the day when the corresponding topic is presented and discussed. Questions will be graded according to quality. For example, questions only asking for key terms (explained) in the reading material of the topic (e.g., "What is Spatial Cognition?") will receive no credit. Questions should rather address conceptual issues arising from the text such as, for instance, regarding seeming contradictions or feasibility issues. Presentations should be well-prepared, well-informed, and above all serve to help your classmates learn about and understand the facts and issues connected with your topic and it should enable them to enter into a qualified discussion about it. Ideally, plan on a 30 - 45 min duration for your presentation and a subsequent in-depth discussions (which you will also moderate). Presentations will be graded and will account for 40% of your overall grade. Performance on questions and the term paper will account for 20% and 40% of your overall grade, respectively.

Please email your term paper to barkowsky@informatik.uni-bremen.de. Term papers have to be submitted by 28 February 2016 the latest. Any form of plagiarism or failure to submit the term paper by the specified date will result in automatic failure of the course.

 

Behaviour Recognition in Ambient and Smart Environments (Be-AmI 2011)

Description

A wide-range of application domains within the fields of ambient intelligence, and pervasive and ubiquitous computing environments require the ability to represent and reason about dynamic spatial phenomena. Real world ambient intelligence systems that monitor and interact with an environment populated by humans and other artefacts require a formal means for representing and reasoning with spatio-temporal, event and action based phenomena that are grounded to real aspects of the environment being modelled. A fundamental requirement within such application domains is the representation of dynamic knowledge pertaining to the spatial aspects of the environment within which an agent, system or robot is functional. At a very basic level, this translates to the need to explicitly represent and reason about dynamic spatial configurations or scenes and desirably, integrated reasoning about space, actions and change. With these modelling primitives, primarily the ability to perform predictive and explanatory analyzes on the basis of available sensory data is crucial toward serving a useful intelligent function within such environments.

The course will introduce the audience to applications of behaviour recognition which are starting to have a practical impact in the real world, but it will also familiarise the audience with the underlying methods and techniques. It will serve the following objectives:

 

 

ECTS Points: 4
Duration: 4 weeks; June 2011.

Time and place: will be announced in 1st introduction lecture

Course introduction lecture: May 26 (14.00 - 16.00, Cartesium, Level 3)

Format: One 2hr lecture per week, and reading assignments. Evaluation will be done in Seminar mode during early July.

Delivered by:

Hans W. Guesgen (Massey University, New Zealand), and Mehul Bhatt (University of Bremen)

Enrolment:

by email: bhatt@informatik.uni-bremen.de

Cognitive Analysis of Scenes: from Computer Vision to High-Level Descriptions for Reasoning and Generating Natural Language Descriptions (SoSe 2013)

Kind of subject 4 ECTS Seminar
Academic Year 2012/2013, Summer Semester SoSe (02.04.13 - 06.07.13)
Degree Master Informatik at Universität Bremen
Language English
First Meeting Thursday 4th April at 9.00h in 0.41 Room, Cartesium, Groundfloor
Initial Timing Thursdays 8.30h – 10.00h (Open to negotiation according to students’ and teacher’s availability)
Seminaroom 0.41 Groundfloor at Cartesium Building
Research group Cognitive Systems (CoSy)

Teacher

Dr.-Ing. Zoe Falomir Llansola

Cartesium Building, Office 3.54

Email: zfalomir@informatik.uni-bremen.de

Office attending hours: Wednesday 15.00h – 17.00 h

More information:

 

 

1. Introduction

Digital images are fully integrated within modern daily life. By using digital cameras we can take photographs of trips and holidays, mobile phone cameras allow us to capture any daily scene, and we can use webcams in laptops to show where we are instantly across the network. The digital images and/or videos generated can be easily copied, deleted, edited, sent by email or multimedia messages, included in web pages, etc. and computer systems applications have been developed to provide all these possibilities. However, there is still no system capable of describing a digital image cognitively, that is, in a similar way to how human beings do it.

Psychological studies carried out on how people describe images [1–4] explain that people find the most relevant content in the images and use words to describe it. Usually nouns are used to refer to objects, adjectives to express properties of these objects and prepositions to express relationships between them. And these nouns, adjectives and prepositions are qualitative labels that extract knowledge from images and that communicate and explain image content.

As digital images represent visual data numerically, most image processing has been carried out applying mathematical techniques to obtain and describe image content. Therefore, using a computer vision system to extract information from space and interpreting it in a meaningful way as human beings can do, it is still a challenge.

In this seminar, this challenge is introduced from the perspectives of computer vision, qualitative modelling and cognitive science. And, after given the theoretical and practical fundamentals, students will have the opportunity to carry out a small project in which they will apply their knowledge and creativity. The projects will be developed in teams of two people and there will be class sessions for the students to explain their project to their classmates, for the students to help/be helped by their classmates, and for the students to evaluate/be evaluated by their classmates. This innovative teaching methodology and assessment was previously applied at Universitat Jaume I, Castellón, Spain, on master and bachelor students on Computer Science Engineering and successful results were obtained [5], such as conference papers, master thesis final projects, interships, etc.

The general skills that students will practice and improve in this seminar are:

  1. Team working, problem solving, autonomous learning, and critical thinking, and communicating effectively orally and in writing;
  2. Learning how to evaluate, how to give/receive critical feedback to/from their equals and how to use it to improve their knowledge and work.

IMPORTANT:

The most outstanding, collaborative and creative student(s) will be given the opportunity to apply for a rewarded training stay at CoSy research group in July 2013 for extending their project and collaborating in the project “Providing human-understandable qualitative and semantic reasoning” funded by the Zentrale Forschungsförderung der Universität Bremen.

Students registered in this seminar would be also given the opportunity to attend the SFB/TR 8 Colloquia on Spatial Cognition organized by Cognitive Systems research group. And if they write a good summary of the talk relating it to the contents of the seminar, they can ask for a certificate of profitable attendance for their professional CVs.

 

 

 

2. General Objectives

  1. Knowing the fundamentals on cognitive vision perception.
  2. Understanding computer vision techniques and how and where to apply them.
  3. Learning how to use computer vision libraries i.e. OpenCV, CImg, OpenSIFT, OpenSURF, etc.
  4. Using computer vision methods and techniques by means of computer vision libraries.
  5. Understanding what is a Qualitative Representation, a Qualitative Model, and what Qualitative Spatial Reasoning involves.
  6. Knowing what is a research paper and where and how to find them.
  7. Learning the structure of a research paper: how to read it and how to write it.
  8. Learning how to make an effective oral presentation.
  9. Improving students' English language skills.

 

3. Contents

This seminar is divided into two thematic units. In the first unit of the seminar, the fundamental contents will be explained and, in the second unit, the students will have the opportunity to carry out a small project related to one o more of the previous explained contents.

Unit I: Learning the Fundamentals

  1. Motivation (1h)
    • 1.1  The Challenge
    • 1.2.  The Contribution to the Research Community
  2. Cognitive Vision Perception in Humans (1h)
    • 2.1.  Fundamentals
    • 2.2.  Mental Imagery
  3. Computer Vision Methods (2h)
    • 3.1.  Definition and Applications
    • 3.2.  Image Formation
    • 3.3.  Segmentation Methods
    • 3.4.  Object Descriptors and Detectors
    • 3.5.  People Pose Descriptors and Detectors
  4. Qualitative Representation and Reasoning (QR) (2h)
    • 4.1.  Qualitative Representations: Symbolic or Interval-based
    • 4.2.  Qualitative Modelling
      • 4.2.1.    Qualitative Models of Distance
      • 4.2.2.    Qualitative Models of Shape
      • 4.2.3.    Qualitative Models of Colour
      • 4.2.4.    Qualitative Models of Topology
      • 4.2.5.    Qualitative Models of Orientation
    • 4.3.  Qualitative Reasoning
  5. Applying QR to Analyse Scenes (2h)
    • 5.1.  Interesting Approaches in the Literature
    • 5.2.  Advantages and Disadvantages
    • 5.3.  Generation of Semantic Information
      • 5.3.1.    For Users: Natural Language
      • 5.3.2.    For Users and Agents: Ontology
    • 5.4.  Spatial Reasoning in Scenes

Unit II: Introduction to Research

  1. Project Selection and Exposition to Classmates (2h x 2 sessions)
    • Example of Theoretical Project: State-of-the-art and critical review of the literature on an issue related to the seminar contents, i.e. Semantic perception with RGB-D cameras/Android devices/etc.
    • Example of Practical Project: Using computer vision libraries to detect events in digital images (i.e. objects, people faces, people poses, movement, etc.) and to extract some semantic information from them (i.e. locations, kind of environment, activity, etc.)
  2. Project Development (2h x 5 attending sessions)
    • 2.1.  Group-Working Meeting 1
    • 2.2.  Group-Working Meeting 2
    • 2.3.  Group-Working Meeting 3
    • 2.4.  Group-Working Meeting 4
    • 2.5.  Group-Working Meeting 5
  3. Project Results Presentation and Evaluation (2h x 2 sessions): Final Report

 

4. Methodology

The methodology applied to the first part of the seminar is mainly expositive but also interactive/communicative in order to discuss with students what they know about the contents but also to correct their misunderstandings and to orientate them.

The methodology applied to the second part of the seminar is based on learning by projects because it is a practical technique that helps students developing important skills, such as independent learning and problem solving, which are very important for a successful professional career.

A class session is dedicated for the students to explain to the rest of their classmates in an oral presentation: (a) their project and (b) the initial approach and means they plan to use to develop it. All the students are invited to make critical and constructive comments on the exposed work and then they are asked to fill in and submit an evaluation of the oral presentation made by each of their classmates. This evaluation is done using questionnaires that teachers provide to students which deal with the interest and difficulty of the problem, the quality of the oral presentation made, the viability of the initial solution proposed, etc.

After defining and presenting their projects, students have time to work in their projects and to discusse their progress in the group-working meetings. These group-working sessions are compulsory. Students can use them to share with the teacher and their classmates the challenges of their problems and to collaborate to find solutions. By means of these group-meetings, the teacher can follow students’ work and orientate them towards successful results and can also observe the level of cooperation that each group has.

Finally, students will present and explain their work in a joint session of oral presentations. Both teacher and classmates can ask questions to evaluate the work presented following a predefined chart. Students must also hand out the final report on the project which should be written in English and has a research paper structure: Abstract, Introduction, Methods, Results, Discussion, Conclusion and Future Work. It should not be larger than 10 pages.

 

5. Assessment and Final Evaluation

Introducing a formative and qualifying assessment by applying a co-evaluation or a method of evaluation between classmates [5-6] is intended to for students to develop general skills of critical and constructive thinking about their own work, very important also in professional practice.

Moreover, students’ work and progress will be followed by means of the group-working meetings. The teacher will guide the students whenever needed (formative and regulatory assessment). Students can also use their colleges and teacher feedback on their presentation and report in order to improve their oral and written skills. Students also can use the teacher’s attending hours to solve doubts and make more progress on their projects.

The percentages estimated for the final evaluation of the seminar are:

Project extensions may add 10-20% to the final grade obtained, depending of the quality and quantity of the extension made.

 

7. Schedule

The schedule below is for guidance only and it may be adapted to the needs of the final group of students.

 

Session Week   Contents
1 4 April

P

A

R

T

I

Seminar Presentation
2 8-12 April

1. Motivation

2. Cognitive Vision Perception in Humans

3 15-19 April 3. Computer Vision Methods
4 22-26 April 4. Qualitative Representation and Reasoning (QR)
5 29-3 May 5. Applying QR to Analyse Scenes
6 6-10 May   Week for Deciding and Negotiating the Project
7 13-17 May

P

A

R

T

II

Project Presentation to Classmates
8 21-24 May 1st Group-Working Meeting
9 27-31 May 2nd Group-Working Meeting
10 3-7 June 3rd Group-Working Meeting
11 10-14 June 4th Group-Working Meeting
12 17-21 June 5th Group-Working Meeting
13 24-28 June   Week for Preparing Presentations
14 1-5 June   Final Project Presentations and Final Report
 

 

References

[1] C. Jörgensen, Attributes of images in describing tasks, Information Processing Management: An International Journal 34 (2–3) (1998) 161–174.

[2] M. Laine-Hernandez, S. Westman, Image semantics in the description and categorization of journalistic photographs. in: A. Grove, J. Stefl-Mabry (Eds.), Proceedings of the 69th Annual Meeting of the American Society for Information Science and Technology, vol. 43, 2006, pp. 1–25.

[3] H. Greisdorf, B. O’Connor, Modelling what users see when they look at images: a cognitive viewpoint, Journal of Documentation 58 (1) (2002) 6–29.

[4] X. Wang, P. Matsakis, L. Trick, B. Nonnecke, M. Veltman, A study on how humans describe relative positions of image objects, in: Lecture Notes in Geoinformation and Cartography, Headway in Spatial Data Handling, Springer, Berlin, Heidelberg, 2008, ISBN 978-3-540-68565-4, pp. 1–18. ISSN:1863-2246.

[5] Falomir Z., Museros L., Escrig M. T., Mixing a teaching methodology based on ‘learning by projects’ with a ‘co-evaluation’ assessment for enhancing competences of students in Artificial Intelligence. In Proc. of International Conference on Education, Research and Innovation (ICERI), organized by the International Association of Technology, Education and Development (IATED), ISBN: 978-84-615-3324-4, pp. 006187 – 006192, Madrid, 14-16th November 2011.

[6] M. Valero-García, L. Díaz de Cerio Ripalda, Autoevaluación y co-evaluación: Estrategias para fomentar la evaluación continuada, Actas del Congreso Español de Informática (CEDI), 2005. http://epsc.upc.edu/projectes/usuaris/miguel.valero/  (Web access on March 2013).

 

Cognitive Computing - SoSe 2015

Seminar (ECTS: 4)
 
Lecturer
Prof. Dr. Mehul Bhatt (bhatt@informatik.uni-bremen.de)
 
Tutor
Jakob Suchan (jsuchan@informatik.uni-bremen.de)
 
Termine:
wöchentlich Mi 14:00 - 16:00 CART 3.01
 
Einzeltermine:
Mi 08.04.15 14:00 - 16:00 CART 3.01
 
Profile: KIKR, DMI
Artificial Intelligence, Cognition, and Robotics (KIKR – Küstliche Intelligenz, Kognition und Robotik)
Digital Media and Interaction (DMI – Digitale Medien und Informatik)
 
Description:
Human-Centred Cognitive Computing (HC3) aims to systematically develop theories, formal specifications, and computational models that capture human-like cognitive capabilities concerning commonsense reasoning about space, actions, change, and interaction in everyday situations. Human-centred’ness, with its emphasis on knowledge about people and their context, will be at the heart of next-generation collaborative cognitive systems and assistive technologies that empower humans in creative and productive tasks, knowledge discovery and perceptual data analyses, high-level control of autonomous systems etc.
This seminar will focus on the conceptual, theoretical, and applied facets of Cognitive Computing. State of the art literature will be discussed each week, and students will have the opportunity to specialise in one particular application area where the general concepts & theory of cognitive computing can be situated. Application areas include: architecture design cognition, cognitive vision, dynamic geographic information systems, and cognitive robotics.The seminar will also expose students to open research questions.
 
Course Information. PDF
 

Commonsense Spatial Reasoning (CSR) - SS 2012

About the Course.

This course will introduce students with formal logic-based methods for integrated representation and reasoning about space, actions, and change. It will prepare the students to apply these methods for solving spatio-temporal reasoning tasks for systems such as cognitive robotics, GIS, spatial puzzles, games, smart environments. Topics that will be convered include:

  1. Commonsense reasoning
  2. Non-Monotonic Reasoning
  3. Reasoning about Actions and Change
  4. Spatial Representation and Reasoning, Spatial Logics
  5. Qualitative Spatial Calculi
  6. Reasoning about Space, Actions, and Change
  7. Collaborative Spatial Reasoning
  8. Applications and Future Perspective for Research, Projects

Summer Semester 2012 (03-ME-711.99c)

ECTS 6; One 2hrs lecture per week. (additional weekly reading assignments and final assignment);

Students have the choice to pick ECTS 4 or ECTS 6.

June 1 - July 31 2012

Lecture timing: Every Thursday, starting June 7 2012 at 16.00hrs - Cartesium. 0.01

First Student Meeting / Course Introduction

Venue: Cartesium. 0.01 (Ground floor)

Time (three possibilities):

            1. Wed 16 May - 10.00hrs

            2. Wed 16 May - 16.00hrs

            3. Thu 17 May - 16.00hrs 

Outside of these times, meet me in person - email: bhatt@informatik.uni-bremen.de

Lecturers

Dr. Mehul Bhatt, Cognitive Systems Group (CoSy; AG Freksa), University of Bremen

Prof. Paulo E. Santos, IAAA Group, Centro Universitário da FEI, Brazil

Experimental Cognitive Robotics. ExpCog (WS 2011-12)

 

Experimental Cognitive Robotics (ExpCog)

Modul: Spezielle Themen der Kognitiven Systeme. (ECTS: 4)
2 SWS Mi von 16:00 - 18:00 CART Besprechungsraum (0.01)

 

Lecturers

Dr. Mehul Bhatt, and Dr. Frank Dylla

Overview

Humans, robots and systems that act, and interact, are embedded in   space, and this change is often the result of actions and events. This  course covers state-of-the-art cognitive robotics techniques that may be  used as a basis for high-level reasoning (e.g., for spatial planning, control) with real and simulated robots. The course is an integrated lab and lecture, i.e. half of the dates will be lectures and the other half will be labs. The lecture part comprises e.g. low-level robot control, an introduction to state-of-the-art high-level robot control approaches. Practical work will also be required using the ExpCog framework (http://cindy.informatik.uni-bremen.de/cosy/staff/bhatt/ExpCog/www/)
 
 

From Syllogism to Commonsense: A Tour through the Logical Landscape (WS 2011-12)

 

Lecturers
Dr. Mehul Bhatt, Dr. Oliver Kutz, Dr. Thomas Schneider
 
Audience
Diplom, MSc, and PhD students in computer science, mathematics, philosophy and related subjects
 
Hours
V2Ü1 – 90min lecture, break, 45min tutorial
 
Time and place
Thu 16:00–18:00 and 18:00–19:00 MZH 1110 (exceptions: 3rd and 17th Nov in MZH 3150)
 

Abstract

This course will give an overview of different non-classical logics and relate them with classical logics. Tentative list of topics (subject to change):

We will discuss intuitions and important theoretical aspects, and will demonstrate tools where they exist. Every lecture will be accompanied by exercises, to be discussed in the following week. There is no prerequisite for taking this course.


Literature

To be given as the course advances

 

Graduate Seminar Cognitive Systems - SS 2011

Course 03-711.91

Graduate Seminar Cognitive Systems
S 2 SWS bi-weekly Wed. 14:00 - 17:00 CARTESIUM Rotunde
Freksa, Christian; Barkowsky, Thomas

Ph.D. and master/diploma students discuss their current research. For the preparation of the session the candidates distribute a research paper one or two weeks ahead of time to the seminar participants. In the seminar session, the most important aspects of the paper are summarized by the author to initiate an in-depth discussion of the work in progress.

 

 

 

Date Contributer
13.04.2011 post doc presentation
27.04.2011 -- semester break --
11.05.2011 dissertation presentation
25.05.2011 Paolo, Giorgio
08.06.2011 Immo, Arne
13.07.2011 Jae, Jasper

 

 

 

 


 

 

 

 

 

 

 

The management of the contributors is currently handled by Immo Colonius, please contact him when in doubt.

Graduate Seminar Cognitive Systems - SS 2014

Course 03-711.91
Christian Freksa, Thomas Barkowsky (coordinated by Carl Schultz)

Summer 2014
Wednesdays 14:00 - 17:15 (approximately bi-weekly)
Cartesium 3rd floor meeting room

 

 

The Graduate Seminar programme provides PhD students with the opportunity to communicate their progress with the group and to receive constructive feedback, support, and advice. For the preparation of the session the candidates will distribute a research paper one or two weeks in advance to the seminar participants. Additionally, the student will nominate two reviewers who will provide more focused and detailed feedback. In the seminar session, the most important aspects of the paper are summarized by the author to initiate an in-depth discussion of the work in progress.

 

This semester's graduate seminar is coordinated by Carl Schultz. Please contact Carl if there are any enquires about the programme or scheduling.

 

Students will nominate two reviewers approximately two weeks in advance, and will send their material to the reviewers one week in advance. The seminar schedule is given below.

 

This semester we will also be conducting Lightning Talks (a very nice suggestion from our substitute professor Tomi Kauppinen):

 

Date Contributor Reviewers
7 May 2014

Ana-Maria Olteteanu

Lightning Talks

Carl Schultz and Zoe Falomir

Hosted by Tomi Kauppinen

14 May 2014

Ahmed Loai Ali

Rami Al Salman

Carl Schultz and Holger Schultheis

Zoe Falomir and Thomas Barkowsky

25 June 2014

Jakob Suchan

Chunyuan Cai

 

Giorgio de Felice and Carl Schultz

9 July 2014

Jasper van de Ven

Immo Colonius

(to be decided)

 

 

 

 

 

 

 

 

 

 

 

 

 

Graduate Seminar Cognitive Systems - WS 2010/2011

Course 03-711.91

Graduate Seminar Cognitive Systems

S 2 SWS bi-weekly Wed. 14:00 - 17:00 CARTESIUM Rotunde

Freksa, Christian; Barkowsky, Thomas

Ph.D. and master/diploma students discuss their current research. For the preparation of the session the candidates distribute a research paper one or two weeks ahead of time to the seminar participants. In the seminar session, the most important aspects of the paper are summarized by the author to initiate an in-depth discussion of the work in progress.

 

Date Contributer
27.10.2010 -- dissertation presentation --
10.11.2010 -- cosyroadmap + postdoc presentation
24.11.2010  
08.12.2010 Iinjie Guan (Jason)
05.01.2010 Jan Frederik Sima, Jasper van de Ven
19.01.2011 Immo Colonius, Paolo
02.02.2011 Jay, Denise Peters

 

 

 

 

 

 

 

 

 

 

The management of the contributors is currently handled by Immo Colonius, please contact him when in doubt.

Graduate Seminar Cognitive Systems - WS 2011/2012

Course 03-711.91

Graduate Seminar Cognitive Systems
S 2 SWS bi-weekly Wed. 14:00 - 17:00 CARTESIUM Rotunde
Freksa, Christian; Barkowsky, Thomas; Dietrich Wolter

Ph.D. and master/diploma students discuss their current research. For the preparation of the session the candidates distribute a research paper one or two weeks ahead of time to the seminar participants. In the seminar session, the most important aspects of the paper are summarized by the author to initiate an in-depth discussion of the work in progress.

See http://www.informatik.uni-bremen.de/~dwolter/GradSem/ for the current assignements.

The management of the contributors is currently handled by Dietrich Wolter, please contact him when in doubt.

Graduate Seminar Cognitive Systems - WS 2013/2014

Course 03-711.91
Christian Freksa, Thomas Barkowsky (coordinated by Carl Schultz)

Winter 2013/14
Wednesdays 14:00 - 17:15 (approximately bi-weekly)
Cartesium 3rd floor meeting room

 

 

The Graduate Seminar programme provides PhD students with the opportunity to communicate their ideas and work with the group and to receive constructive feedback, support, and advice. For the preparation of the session the candidates will distribute a research paper one or two weeks in advance to the seminar participants. Additionally, the student will nominate two reviewers who will provide more focused and detailed feedback. In the seminar session, the most important aspects of the paper are summarized by the author to initiate an in-depth discussion of the work in progress.

 

This semester's graduate seminar is coordinated by Carl Schultz. Please contact Carl if there are any enquires about the programme or scheduling.

 

Students will nominate two reviewers approximately two weeks in advance, and will send their material to the reviewers one week in advance. The seminar schedule is given below.

 

Date Contributor Reviewers
23 October 2013

Jan Frederik Sima

Rasmus Wienemann

Carl Schultz and Holger Schultheis

Frank Dylla and Jae Hee Lee

20 November 2013

Jasper van de Ven

Arne Kreutzmann

Zoe Falomir Llansola and Jae Hee Lee

 

4 December 2013

Ahmed Loai Ali

 

Giorgio de Felice and Thomas Barkowsky

 

18 December 2013

Chunyuan Cai

 

(to be decided)
8 January 2013

Jae Hee Lee

Jakob Suchan

Holger Schultheis

 

22 January 2014

Rami Al Salman

Sandra H. Budde

Carl Schultz and Giorgio de Felice

Jae Hee Lee and Lutz Frommberger

29 January 2014

Immo Colonius

Ana-Maria Olteteanu

Frank Dylla and Mehul Bhatt

Carl Schultz and Thomas Barkowsky

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Qualitative Spatial and Temporal Reasoning-summer term 2012

Diedrich Wolter, 4 SWS, 6 ECTS, 03-ME-711.10
 
This course addresses state-of-the-art qualitative methods for spatio-temporal reasoning which are subject to contemporary research in artificial intelligence (AI). Qualitative methods draw motivation from the observation that even in infinite domains (such as spatial or temporal information) only a few distinctions are relevant for solving a given task. These distinctions are made explicit and build the basis for symbolic reasoning. This course covers both the theoretical properties of qualitative reasoning techniques (most importantly constraint-based reasoning) and their applications (e.g. navigation). We will analyze reasoning methods by theoretical means, implement algorithms for practical use, and test algorithms through empirical experiments.

[Ziel dieses Kurses ist das Erlernen des qualitativen Schlussfolgerns mit zeitlicher und räumlicher Information. Der Umgang mit zeitlicher und räumlicher Information ist wichtig in vielen Anwendungen im Themenumfeld der Künstlichen Intelligenz (KI); Beispiele reichen von Geoinformationssystemen bis hin zu Kontrolle autonomer Agenten oder Benutzerintzeraktion. Allen Aufgaben gemeinsam ist, dass häig nur wenige, gezielte Unterscheidungen und Überlegungen zu einer Lösung führen; damit eröffnet sich eine Möglichkeit, auch mit unendlichen Domänen (effizient) umgehen zu können - dies bildet die Motivation qualititativer Verfahren. Im Rahmen dieses Kurses vermitteln wir verschiedene Ansätze und Verfahren im engen Bezug zu aktueller Forschung. Der Kurs kombiniert theoretische Betrachtungen mit praktischer Umsetzung. Fragen?

Tuesday 14:15 - 15:45 Cartesium 0.001
Thursday 14:15 - 15:45 Cartesium 0.001
course language: English/ German

Spatial Computing for Design (SpaDe 2011)

Description:

Design is one of the most complex of human endeavours requiring an enormous number of often conflicting criteria to be contemplated when identifying optimal solutions. It is constrained by major building codes and standards applicable to the individual location that the design will be sited. It has to be created within a collaborative team consisting of many professionals focussed on specific sub-systems that provide unique functionality to the overall design. To manage the space of potential solutions a designer typically relies upon a suite of simulation tools and rules of thumb which are based upon the precise physical properties of a design. Few of these tools support qualitative analysis within the Design Space, which is a style of analysis more closely aligned with the designer's mental model. Newly developed computing techniques now allow this form of design assistance to be created and to build upon the traditional quantitative support offered to designers.

This course will cover the basics of spatial design in the context of computer-aided architectural design. We will study design paradigms and systems, classical perspectives on the role of form and function in design, and the spatial informatics of architecture design assistance systems. Latest design standards and frameworks will also be discussed.

ECTS Points: 4
Duration: 4 weeks; June 2011 (precise lecture times and evaluation schedule will be decided in consultation with students)

Time and place: will be announced in 1st introduction lecture

Course introduction lecture: June 1 (14.00 - 16.00, Cartesium, Level 3)

Format: One 2hr lecture per week, and reading assignments. Evaluation will be done in Seminar mode during early July.

Delivered by:

Robert Amor (University of Auckland, New Zealand), and Mehul Bhatt (University of Bremen)

Enrolment:

by email: bhatt@informatik.uni-bremen.de

Spatial Reasoning for Computational Cognitive Systems - SoSe 2015

Blockcourse (ECTS: 6)

Lecturer
Prof. Dr. Mehul Bhatt (bhatt@informatik.uni-bremen.de)
 
Tutor
 
 
Einzeltermine:
Di 21.04.15 16:00 - 18:00 CART 3.01
 
Mo 10.08.15 - Fr 14.08.15 (Mo, Di, Mi, Do, Fr) 10:00 - 12:00 and 13:00 - 16:00 CART 3.01 
Mo 17.08.15 - Fr 21.08.15 (Mo, Di, Mi, Do, Fr) 10:00 - 12:00 and 13:00 - 16:00 CART 3.01 
 
Profile: KIKR, DMI
Artificial Intelligence, Cognition, and Robotics (KIKR – Küstliche Intelligenz, Kognition und Robotik)
Digital Media and Interaction (DMI – Digitale Medien und Informatik)
 
Description:
This course will introduce students to declarative problem solving skills with logic programming. After a basic introduction to the declarative logic programming language Prolog, this course presents an application-driven in-depth overview of methods for commonsense spatial representation and reasoning within artificial intelligence based computer programs, computational cognitive systems, intelligent agents (e.g., in computer games). Methods that can be used to model and implement commonsense spatial reasoning components within (hybrid) intelligent systems will be introduced in detail with state-of-the-art deployed examples from ongoing research projects in the fields of architecture design, computer vision, robotics, geographic information systems, computer games, spatial puzzles, smart homes.
 
Course Information. PDF
 

Start your Engines ... High-level Agent Control (WS 2011/12)

About: development of intelligent control systems (for a racing simulation)

Where & When:

Credit Points: 6 ECTS

Audience: Bachelor (Masters: General Studies) 

Maximum participants: 30 (Minimum participants: 10)

Requirement: Basic knowledge on C/ C++ 

In the future autonomous artificial systems will be present more and more in our daily life. Such systems need to be able to interact with humans and to react to unexpected situations 'intelligently'. This course comprises an introduction as well as practical deepening of various agent models, psychological foundations, and diverse reasoning technics. Within small groups racing agents will be developed (racing simulation TORCS: http://torcs.sourceforge.net/). At the end of the course the developed agents are evaluated in a contest.

Homework: Schreibe einen einfachen Torcs-Agenten, der eine beliebige Strecke alleine als einziges Fahrzeug mindestens einmal abfahren kann. Installiere dir dazu selbst Torcs auf einem Rechner, schreibe einen entsprechenden Agenten und schicke den Sourcecode des Agenten an uns. Dokumentiere und nenne alle genutzten Hilfsmittel (inklusive HowTo's, Tutorials, Websites und Kooperationen!).

AttachmentSize
HLAgCtrl_Vorbereitung.pdf726.5 KB

Start your Engines ... High-level Agent Control

About: development of intelligent control systems (for a racing simulation)

Where & When:

Credit Points: 6 ECTS

Audience: Bachelor (Masters: General Studies) 

Maximum participants: 30

Requirement: Basic knowledge on C/ C++ 

In the future autonomous artificial systems will be present more and more in our daily life. Such systems need to be able to interact with humans and to react to unexpected situations 'intelligently'. This course comprises an introduction as well as practical deepening of various agent models, psychological foundations, and diverse reasoning technics. Within small groups an racing agent will be developed to further. At the end of the course the developed agents are evaluated in a contest.

Homework: Schreibe einen einfachen Torcs-Agenten, der eine beliebige Strecke alleine als einziges Fahrzeug mindestens einmal abfahren kann. Installiere dir dazu selbst Torcs auf einem Rechner, schreibe einen entsprechenden Agenten und schicke den Sourcecode des Agenten an uns. Dokumentiere und nenne alle genutzten Hilfsmittel (inklusive HowTo's, Tutorials, Websites und Kooperationen!).

AttachmentSize
HLAgCtrl_Vorbereitung.pdf766.94 KB

Student Projects

Location Sensitive Office Communication

Projektstart 01.10.2006

Das Projekt "Location Sensitive Office Communication" (LSOC) hat das Ziel, eine ortsbezogene Arbeitsplatz-Kommunikation im Informatik-Neubau zu implementieren. Basierend auf einem zu entwickelnden Indoor-Lokalisierungssystem sollen audio-visuelle Nachrichten sowohl zwischen Mitarbeitern als auch zwischen Besuchern des Gebäudes und Mitarbeitern dem Aufenthaltsort des Empfängers entsprechend verschickt und angezeigt werden. Ausserdem soll das System einen Besucher des Gebäudes mittels geeigneter Assistenz zum Ziel (einem Raum, einer Veranstaltung oder einer Person) führen können.

Von besonderer Bedeutung in einem solchen Szenario ist natürlich der Umgang mit der Privatsphäre der Mitarbeiter (Stichwort Datenschutz).

Rückrat des Systems ist ein raumgenaues Mitarbeiter-Lokalisierungssystem. Hierbei sollen entweder RFID- oder Bluetooth-basierte Lösungen zum Einsatz kommen.

Leitung:

Prof. Christian Freksa

Betreuung:

  • Dr.-Ing. Kai-Florian Richter
  • Falko Schmid

Dokument(e) zum Download

Dokument(e) zum DownloadLSOC.pdf (196.5KB application/pdf)

Project AUGMENT: Augmented Interaction and Analysis for Spatial Design

 

About AUGMENT

The project AUGMENT aims to develop systems that will empower professional designers and practitioners in design, architecture, and spatial planning by the use of augmented reality technology, and novel methods in natural interaction and complex data visualization. The methods and envisaged results of the project aim to address aspects of (architectural) spatial cognition and spatial computing that relate to processes of Design Tools and Assistive Frameworks, real-world Design Practice, and Design Learning & Education.

Project SupervisorMehul Bhatt, Cognitive Systems Group (CoSy; AG Freksa).

Project URL. www  ( www.tinyurl.com/project-augment )

Project Mobile4D: Mobile Solutions for Poverty Reduction in Developing Countries

Über Mobile4D

Ziel des Projekts ist die Konzeption und Entwicklung eines Systems zur Vernetzung landwirtschaftlicher Extension Worker in Laos mit mobilen Endgeräten. Das System soll unter Ausnutzung der Möglichkeiten moderner Smartphones ermöglichen, dass Informationen auf adäquate Weise gesammelt, aufbereitet und mit anderen geteilt werden können.

Betreuer: Lutz Frommberger, Falko Schmid

http://www.informatik.uni-bremen.de/cms/media.php/75/mobile4d.pdf

Spatial Interaction Laboratory Project

The project will develop the basis for a 'Spatial Interaction Laboratory'. It is intended to use the touch screen computers installed in the Cartesium building to provide functionality for general usage like door plates. Furthermore, the possibility to easily introduce systems to research interaction in spatially separated environments has to be created. This requires availability of and access to a spatial representation of the included parts of the building.

Further topics of interesst will be communication, configuration and user interfaces within and for the used kind of environment.

For further information please visit the project web site: http://spatial.cosy.informatik.uni-bremen.de