Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
Next revisionBoth sides next revision
jobs [2015/07/28 12:11] – [Theses and Jobs] winklerjobs [2022/05/02 08:49] – [Theses and Student Jobs] kording
Line 1: Line 1:
-~~NOTOC~~ 
-=====Theses and Jobs===== 
-If you are looking for a bachelor/master thesis or a job as a student research assistant, you may find some interesting opportunities on this page. 
  
 +=====Open researcher positions=====
  
 +====Research assistants (f/m/d)====
 +At the University of Bremen, the Institute for Artificial Intelligence (Prof. Michael Beetz) – part of the department Mathematics and Computer Science FB3 - calls for applications in the area of Artificial Intelligence and Robotics – under the condition of job release – for several positions in the DFG funded Collaborative Research Center 1320 “Everyday Activity Science and Engineering (EASE):
  
-== GPU-based Parallelization of Numerical Optimization Techniques (BA/MA/HiWi)==+**Research assistants (f/m/d)**
  
-In the field of Machine Learning, numerical optimization techniques play a focal role. However, as models grow larger, traditional implementations on single-core CPUs suffer from sequential execution causing a severe slow-down. In this thesis, state-of-the-art GPU frameworks (e.g. CUDA) are to be investigated in order implement numerical optimizers that substantially profit from parallel execution.+- Salary scale TV-L – 13 (100 %)\\ 
 +for the period to June 30, 2025.
  
-Requirements: +The employment is fixed-term and governed by the Act of Academic Fixed-Term Contract, § 2 (1) WissZeit VG (Wissenschaftszeitvertragsgesetz, i.e. temporary science employment act). Therefore, candidates may only be considered for appointment if they still have the respective qualification periods available in accordance with § 2 (1) WissZeitVG. 
-  * Skills in numerical optimization algorithms +EASE pursues an interdisciplinary approach to the principles of human information processing in basic research. Starting from the analysis of underlying problem structures and solution strategies, the development of information-processing models is intended to enable autonomous robots to fully master everyday activities. EASE stands for open research, open data and knowledge exchange. For more information see www.ease-crc.org.
-  * Good programming skills in Python and C/C+++
  
-Contact: [[team:daniel_nyga|Daniel Nyga]]+Successful candidates will support the expansion of the EASE central laboratory and conduct research in the following areas:
  
-== Online Learning of Markov Logic Networks for Natural-Language Understanding (MA)==+**Tasks:** 
 +  * knowledge-based robot control systems 
 +  * machine learning methods to successfully perform and improve robot-based everyday activities 
 +  * representation of everyday activities and their implementation as knowledge bases and virtual environments 
 +  * Knowledge modelling, representation and construction of knowledge bases for everyday activities 
 +  * cognitive architectures for robotic agents 
 +  * Integration of camera-based perception into simulation and rendering methods for everyday activities in household environments 
 +  * web-based experimental environments based on semantic digital twins 
 +  * scalable cloud-based knowledge representation and knowledge processing system based on KnowRob 
 +  * definitions of ontologies for everyday activities
  
-Markov Logic Networks (MLNs) combine the expressive power of first-order logic and probabilistic graphical models. In the past, they have been successfully applied to the problem of semantically interpreting and completing natural-language instructions from the web. State-of-the-art learning techniques mostly operate in batch mode, i.e. all training instances need to be known in the beginning of the learning process. In context of this thesis, online learning methods for MLNs are to be investigated, which allow incremental learning, when new examples come in one-by-one.+**Your ideal profile:** 
 +  * University degree in computer science (master's degree, university diploma) with above-average success or a comparable degree 
 +  * Very good academic achievements in the fields of Robotics, AI, perception, programming, etc. 
 +  * Profound knowledge in the development of complex software systems, ideally in the field of robotics 
 +  * Substantial Know-how on AI methods in robotic applications 
 +  * Excellent programming skills in the field of AI and/or robotics. The programming languages include, for example: Python, C++, LISP, Prolog 
 +  * Excellent English skills, both written and spoken 
 +  * Independent and committed research in close cooperation with internal and external cooperation partners 
 +  * High level of commitment, flexibility and team spirit
  
-Requirements: +If you think that your knowledge and skills match part of the task areas, we are looking 
-  * Experience in Machine Learning. +forward to your application. 
-  * Experience with statistical relational learning (e.g. MLNs) is helpful. +We offer a team-oriented, attractive and future-oriented research environment in an interdisciplinary team with renowned national and international partners and ideal conditions for further scientific qualification.
-  * Good programming skills in Python.+
  
-Contact: [[team:daniel_nyga|Daniel Nyga]]+**General remarks:** 
 +The University is committed to a policy of providing equal employment opportunities for both men and women alike, and therefore strongly encourages women to apply for the positions offered. Applicants with disabilities will be considered preferentially in case of equal qualifications and aptitudes. The University of Bremen explicitly invites individuals with migration backgrounds to apply.
  
 +If you have any questions regarding the positions, please contact Prof. Michael Beetz, PhD (<cryptmail>ai-office@cs.uni-bremen.de</cryptmail>).
  
-==HiWi-Position: Knowledge Representation & Language Understanding for Intelligent Robots==+Applications including a cover letter, CV, publication list, copies of degree certificates, should be submitted citing the **reference number A92/21** to:
  
-In the context of the European research project RoboHow.Cog [1,2] we +Prof. Michael Beetz, PhD\\ 
-are investigating methods for combining multimodal sources of knowledge (e.g. video, natural-language recipes or computer games), in order to enable mobile robots to autonomously acquire new high level skills like cooking meals or straightening up rooms.  +Artificial Intelligence / Universität Bremen\\ 
 +Am Fallturm 1\\ 
 +28359 Bremen\\ 
 +Germany
  
-The Institute for Artificial Intelligence is hiring a student researcher for the +or by Email (including up to two PDF files; reference number A92/21) to: <cryptmail>ai-office@cs.uni- bremen.de</cryptmail>
-development and the integration of probabilistic methods in AI, which enable intelligent robots to understand, interpret and execute natural-language instructions from recipes from the World Wide Web.+
  
-This HiWi-Position can serve as a starting point for future Bachelor's, Master's or Diploma Theses. 
  
-Tasks: +The costs of application and presentation cannot be reimbursed. We kindly ask you to submit only copies (no folders) of your application documents, as these will be destroyed after the selection process has been completed.
-  * Implementation of an interface to the Robot Operating System (ROS). +
-  * Linkage of the knowledge base to the executive of the robot. +
-  * Support for the scientific staff in extending and integrating components onto the robot platform PR2.+
  
-Requirements: 
-  * Studies in Computer Science (Bachelor's, Master's or Diploma) 
-  * Basic skills in Artificial Intelligence 
-  * Optional: basic skills in Probability Theory 
-  * Optional: basic skills in Machine Learning 
-  * Good programming skills in Python and Java 
  
-Hours: 10-20 h/week +=====Theses and Student Jobs===== 
- +If you are looking for a bachelor/master thesis or a job as a student research assistant, you may find some interesting opportunities on this page.
-Contact: [[team:daniel_nyga|Daniel Nyga]] +
- +
-[1] www.robohow.eu\\ +
-[2] http://www.youtube.com/watch?v=0eIryyzlRwA+
  
  
-== Kitchen Activity Games in a Realistic Robotic Simulator (BA/MA/HiWi)== +== Physics-based grasping in VR with finger tracking(Student Job / HiWi) ==
- {{ :research:gz_env1.png?200|}} +
  
-Developing new activities and improving the current simulation framework done under the [[http://gazebosim.org/|Gazebo]] robotic simulator. Creating a custom GUI for the game, in order to launch new scenarios, save logs etc.+Implementing physics-based grasping models in virtual environments, 
 +using Manus VR.
  
 Requirements: Requirements:
-  * Good programming skills in C/C++ +  * Good C++ programming skills 
-  * Basic physics/rendering engine knowledge +  * Familiar with skeletal animations 
-  * Gazebo simulator basic tutorials+  * Experience with simulators/physics-/game- engines 
 +  * Familiar with Unreal Engine API 
 +  * Familiar with version-control systems (git) 
 +  * Able to work independently with minimal supervision
  
 Contact: [[team:andrei_haidu|Andrei Haidu]] Contact: [[team:andrei_haidu|Andrei Haidu]]
  
-== Integrating Eye Tracking in the Kitchen Activity Games (BA/MA)== 
- {{ :research:eye_tracker.png?200|}}  
  
-Integrating the eye tracker in the [[http://gazebosim.org/|Gazebo]] based Kitchen Activity Games framework and logging the gaze of the user during the gameplay. From the information typical activities should be inferred.+ 
 +<html><!-- 
 +== Lisp / CRAM support assistant (HiWi) == 
 + 
 +Technical support for the group for Lisp and the CRAM framework. \\ 
 +8+ hours per week for up to 1 year (paid).
  
 Requirements: Requirements:
-  * Good programming skills in C/C++ +  * Good programming skills in Common Lisp 
-  * Gazebo simulator basic tutorials+  * Basic ROS knowledge
  
-Contact: [[team:andrei_haidu|Andrei Haidu]]+The student will be introduced to the CRAM framework at the beginning of the job, which is a robot programming framework written in Lisp. The student will then be responsible for assisting not familiar with the framework people, explaining them the parts they don't understand and pointing them to the relevant documentation sources.
  
-== Hand Skeleton Tracking Using Two Leap Motion Devices (BA/MA)== +Contact: [[team:gayane_kazhoyan|Gayane Kazhoyan]] 
- {{ :research:leap_motion.jpg?200|}} +--></html>
  
-Improving the skeletal tracking offered by the [[https://developer.leapmotion.com/|Leap Motion SDK]], by using two devices (one tracking vertically the other horizontally) and switching between them to the one that has the best current view of the hand.+<html><!-- 
 +== Mesh Editing / Mesh Segmentation/Cutting (Student Job / HiWi)== 
 + {{ :research:human_hand_cutting.png?150|}}
  
-The tracked hand can then be used as input for the Kitchen Activity Games framework.+ Editing and cutting a human mesh into different parts in Blender / Maya (or other).
  
 Requirements: Requirements:
-  * Good programming skills in C/C+++  * Good knowledge in 3D Modeling 
 +  * Familiar with Blender / Maya (or other)
  
-Contact: [[team:andrei_haidu|Andrei Haidu]]+Contact: [[team/mona_abdel-keream|Mona Abdel-Keream]] 
 +--></html>
  
-== Fluid Simulation in Gazebo (BA/MA)== 
- {{ :research:fluid.png?200|}}  
  
-[[http://gazebosim.org/|Gazebo]] currently only supports rigid body physics engines (ODE, Bullet etc.), however in some cases fluids are preferred in order to simulate as realistically as possible the given environment. 
  
-Currently there is an [[http://gazebosim.org/tutorials?tut=fluids&cat=physics|experimental version]] of fluids  in Gazebo, using the [[http://onezero.ca/fluidix/|Fluidix]] library to run the fluids computation on the GPU.+== 3D Animation and Modeling (Student Job / HiWi)== 
 + {{ :research:kitchen_unreal.jpg?200|}} 
  
-The computational method for the fluid simulation is SPH (Smoothed-particle Dynamics), however newer and better methods based on SPH are currently present +Developing and improving existing or new 3D (static/skeletal) 
-and should be implemented (PCISPH/IISPH).+models in Blender / Maya (or other). Further importing and testing the 
 +models against Unreal Engine.
  
-The interaction between the fluid and the rigid objects is a naive one, the forces and torques are applied only from the particle collisions (not taking into account pressure and other forces). +Bonus: Working with state of the art 3D Scanners [[https://www.goscan3d.com/|Go!SCAN]] for creating sketching new models.
- +
-Another topic would be the visualization of the fluid, currently is done by rendering every particle. For the rendering engine [[http://www.ogre3d.org/|OGRE]] is used. +
- +
-Here is a [[https://vimeo.com/104629835|video]] example of the current state of the fluid in Gazebo. +
  
 Requirements: Requirements:
-  * Good programming skills in C/C++ +  * Experience with Blender / Maya (or other) 
-  * Interest in Fluid simulation +  * Knowledge of Unreal Engine material / lightning development 
-  * Basic physics/rendering engine knowledge +  * Familiar with version-control systems (git) 
-  * Gazebo simulator and Fluidix basic tutorials+  * Able to work independently with minimal supervision
  
 Contact: [[team:andrei_haidu|Andrei Haidu]] Contact: [[team:andrei_haidu|Andrei Haidu]]
  
  
-== Automated sensor calibration toolkit (BA/MA)==+== Linking saref to SOMA (BA Thesis) ==
  
-Computer vision is an important part of autonomous robots. For robots the image sensors are the main source of information of the surrounding world. Each camera is different, even if they are from the same production line. For computer vision, especially for robots manipulating their environment, it is important that the parameters for the cameras in use are well known. The calibration of a camera is a time consuming task, and the result depends highly on the chosen setup and the accuracy of the operator.+Wissensrepräsentation: Semantische Integration der saref Ontology (https://ontology.tno.nl/saref/) für smart devices in SOMA (https://ease-crc.github.io/soma/). Ziel dabei ist es, dass Roboter anhand von ein paar Beispielszenarien (z.B. Zubereitung von Popcorn/ Pizza) Fehler autonom finden können (z.B. Electricity ist aus -> deswegen wird der Herd nicht warm und Popcorn poppt nicht).
  
-The topic for this thesis is to develop an automated system for calibrating cameras, especially RGB-D cameras like the Kinect v2.+Aufgaben: 
 +  * Arbeit mit Wissensrepräsentation und Wissensgraphen 
 +  * Wissensakquisition aus web-Quellen 
 +  * Abfrage mit KnowRob (Prolog) für autonome Roboter
  
- {{ :kinect2_calibration_setup_small.jpg?200|}} +Contact: [[team:michaela_kümpel|Michaela Kümpel]]
-The system should: +
-  * be independent of the camera type +
-  * estimate intrinsic and extrinsic parameters +
-  * calibrate depth images (case of RGB-D) +
-  * integrate capabilities from Halcon [1] +
-  * operate autonomously+
  
-Requirements:  +== Case Study: Wissen zu Produkt-Aufbewahrungsorten aus dem Internet beziehen (BA Thesis) ==
-  * Good programming skills in Python and C/C++ +
-  * ROS, OpenCV+
  
-[1] http://www.halcon.de/+In dieser Thesis soll untersucht werden, ob die Autonomie von Robotern durch Integration von Wissen zu Aufbewahrungsorten von Produkten aus dem Internet erhöht werden kann. Es gibt verschiedene websites, die Wissen dazu bereitstellen. Dieses Wissen soll von den websites abgefragt und anschließend sinnvoll ontologisiert werden. Anhand verschiedener Fragen werden die Ergebnisse evaluiert (Menge der erworbenen Informationen/ Nutzen der Information, v.a. für autonome Roboter...)
  
-Contact: [[team:alexis_maldonado|Alexis Maldonado]] and [[team:thiemo_wiedemeyer|Thiemo Wiedemeyer]]+Aufgaben: 
 +  * Wissensakquise aus dem Internet 
 +  * Wissensrepräsentation/ Modellierung: Ontologisierung des Wissens 
 +  * Vergleich mit bestehenden Ontologien/ Arbeiten und manuell erstellten Ontologien 
 +  * Sinnvolle, automatisierte Abfrage des neu gewonnenen Wissens
  
-== On-the-fly 3D CAD model creation (MA)== 
  
-Create models during runtime for unknown textured objets based on depth and color information. Track the object and update the model with more detailed information, completing it's 3D model from multiple views improving redetection. Using the robots manipulator pick up the object and complete the model by viewing it from multiple viewpoints.+Contact: [[team:michaela_kümpel|Michaela Kümpel]]
  
-Requirements:  +== Integration of novel objects into Digital Twin Knowledge Bases (MA Thesis) ==
-  * Good programming skills in C/C++ +
-  * strong background in computer vision  +
-  * ROS, OpenCV, PCL+
  
-Contact: [[team:thiemo_wiedemeyer|Thiemo Wiedemeyer]]+In this thesis, the goal is to make a robotic system learn new objects automatically. 
 +The system should be able to generate the necessary models required for re-detecting it again and also consult online information sources to automatically acquire knowledge about it.
  
-== Simulation of a robots belief state to support perception(MA) ==+The focus of the thesis would be two-fold: 
 +  * Develop methods to automatically infer the object class of new objects. This would include perceiving it with state of the art sensors, constructing a 3d model of it and then infer the object class from online information sources. 
 +  * In the second step the system should also infer factual knowledge about the object from the internet and assert it into a robotic knowledgebase. Such knowledge could for example include the category of this product, typical object properties like its weight or typical location and much more.
  
-Create a simulation environment that represents the robots current belief state and can be updated frequently. Use off-screen rendering to investigate the affordances these objects possess, in order to support segmentation, detection and tracking of these in the real world.  
  
-Requirements:  +Requirements: 
-  * Good programming skills in C/C++ +  * Knowledge about sensor data processing 
-  * strong background in computer vision  +  * Interest in model construction from sensory data 
-  * Gazebo, OpenCV, PCL+  * Work with KnowRob knowledge processing framework
  
-Contact: [[team:ferenc_balint-benczedi|Ferenc Balint-Benczedi]] 
  
-== Multi-expert segmentation of cluttered and occluded scenes ==+Contact: [[team:patrick_mania|Patrick Mania]]
  
-Objects in a human environment are usually found in challenging scenes. They can be stacked upon eachother, touching or occluding, can be found in drawers, cupboards, refrigerators and so on. A personal robot assistant in order to execute a task, needs to detect these objects and recognize them. In this thesis a multi-modal approach to interpreting cluttered scenes is going to be investigated, combining the results of multiple segmentation algorithms in order to come up with more reliable object hypotheses. 
  
-Requirements:  +== Development of Modules for Robot Perception (Student Job / HiWi) == 
-  * Good programming skills in C/C++ +In our research group, we focus on the development of modern robots that can make use of the potential of game engines. One particular research direction, is the combination of computer vision with game engines. 
-  * strong background in 3D vision  +In this context, we are currently offering multiple Hiwi positions / student jobs for the following tasks: 
-  * basic knowledge of ROS, OpenCV, PCL+  * Software development to create Interfaces between ROS and Unreal Engine 4 (mainly C++) 
 +  * Software development for our Robot Perception framework [[http://robosherlock.org/|RoboSherlock]] which contains many algorithms for computer vision problems (mainly C++) 
 + 
 +Requirements: 
 +  * Experience in C++. 
 +  * Basic understanding of the ROS middleware and Linux. 
 +The spoken language in this job is german or english, based on your preference. 
 + 
 +Contact: [[team:patrick_mania|Patrick Mania]] 
 + 
 +== Game Engine Developer and 3D-Modelling  (Student Job / HiWi) == 
 +A recent development in the field of AI is the usage of photorealistic simulations, for example to create Digital Twins of environments like households or  [[https://iottechnews.com/news/2021/apr/13/bentley-systems-nvidia-omniverse-create-real-time-digital-twins/|factories]]. 
 +In our research group, we focus on the development of modern robots that can make use of the potential of game engines. This requires a high degree of specialized game engine plugins that can simulate certain aspects of our research. Another important task is the creation of 3d models. 
 + 
 +Therefore, we are currently offering multiple Hiwi positions / student jobs for the following tasks: 
 +  * Modelling of objects for the use in Unreal Engine 4. 
 +  * Creation of specific simulation aspects in Unreal Engine 4. For example the development of interactable objects. 
 + 
 +Requirements: 
 +  * Knowledge of 3D-Modelling tools. Blender would be highly preferred. 
 +  * Experience in Game Engine development. Ideally Unreal Engine 4 and C++. 
 + 
 +The spoken language in this job is german or english, based on your preference.
  
-Contact: [[team:ferenc_balint-benczedi|Ferenc Balint-Benczedi]]+Contact: [[team:patrick_mania|Patrick Mania]]
- Impressum - Datenschutz



Prof. Dr. hc. Michael Beetz PhD
Head of Institute

Contact via
Andrea Cowley
assistant to Prof. Beetz
ai-office@cs.uni-bremen.de

Discover our VRB for innovative and interactive research


Memberships and associations:


Social Media: