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 [2014/04/15 15:48] – [Theses and Jobs] jworchjobs [2023/09/14 10:26] – [Theses and Student Jobs] cstoess
Line 1: Line 1:
 ~~NOTOC~~ ~~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. 
  
-== Web-based knowledge visualizations (BA/HiWi) ==+=====Open researcher positions=====
  
-{{ :research:knowledge-visualization.png?200}}+{{blog>:jobs?3&date&footer&firstseconly&readmore}}
  
-The knowledge base visualization allows to display semantic environment maps, + 
-objects, human poses, trajectories and similar information stored in the +<html> 
-robot's knowledge base. Its [[http://www.ros.org/wiki/mod_vis|current version]] +<div style="width:100%;border-bottom:10px solid #DCDFE3;margin-bottom:80px;"></div> 
-is written in Java and has grown old over the years. Recently, there has been +</html> 
-much progress in creating [[http://www.ros.org/wiki/interactive_markers|interactive + 
-3D visualizations]] for ROS that can also be accessed with a + 
-[[http://www.ros.org/wiki/wviz|web browser]]. This project is about creating + 
-a web-based version of the visualization using these techniques.+=====Theses and Student Jobs===== 
 +If you are looking for a bachelor's/master's thesis or a job as a student research assistant, you may find some interesting opportunities on this page. 
 + 
 + 
 +<html><!-- 
 +== Physics-based grasping in VR with finger tracking(Student Job / HiWi) == 
 + 
 +Implementing physics-based grasping models in virtual environments, 
 +using Manus VR.
  
 Requirements: Requirements:
-  * Good programming skills +  * Good C++ programming skills 
-  * Experience with JavaScript development +  * Familiar with skeletal animations 
-  * Knowledge of Web technologies (HTML, XML, OWL)+  * 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:moritz_tenorth|Moritz Tenorth]]+Contact: [[team:andrei_haidu|Andrei Haidu]] 
 +--></html>
  
  
-== Tools for knowledge acquisition from the Web (BA/MA/HiWi) ==+<html><!-- 
 +== Lisp / CRAM support assistant (HiWi) ==
  
-There are several options for doing a project related to the acquisition of +Technical support for the group for Lisp and the CRAM framework. \\ 
-knowledge from Web sources like online shops, repositories of object models, +8+ hours per week for up to 1 year (paid).
-recipe databases, etc.+
  
 Requirements: Requirements:
-  * Programing skills (Java) +  * Good programming skills in Common Lisp 
-  * Experience with Web languages and datamining techniques is helpful +  * Basic ROS knowledge
-  * Depending on the focus of the project, experience with database technology, natural-language processing or computer vision may be helpful+
  
-Contact: [[team:moritz_tenorth|Moritz Tenorth]]+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.
  
 +Contact: [[team:gayane_kazhoyan|Gayane Kazhoyan]]
 +--></html>
  
-== GPU-based Parallelization of Numerical Optimization Techniques (BA/MA/HiWi)==+<html><!-- 
 +== Mesh Editing / Mesh Segmentation/Cutting (Student Job / HiWi)== 
 + {{ :research:human_hand_cutting.png?150|}}
  
-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.+ Editing and cutting a human mesh into different parts in Blender / Maya (or other).
  
 Requirements: Requirements:
-  * Skills in numerical optimization algorithms +  * Good knowledge in 3D Modeling 
-  * Good programming skills in Python and C/C+++  * Familiar with Blender / Maya (or other)
  
-Contact: [[team:daniel_nyga|Daniel Nyga]]+Contact: [[team/mona_abdel-keream|Mona Abdel-Keream]] 
 +--></html>
  
-== Online Learning of Markov Logic Networks for Natural-Language Understanding (MA)== 
  
-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.+<html><!-- 
 +== 3D Animation and Modeling (Student Job / HiWi)== 
 + {{ :research:kitchen_unreal.jpg?200|}}  
 + 
 +Developing and improving existing or new 3D (static/skeletal) 
 +models in Blender / Maya (or other). Further importing and testing the 
 +models against Unreal Engine. 
 + 
 +Bonus: Working with state of the art 3D Scanners [[https://www.goscan3d.com/|Go!SCAN]] for creating sketching new models.
  
 Requirements: Requirements:
-  * Experience in Machine Learning. +  * Experience with Blender / Maya (or other) 
-  * Experience with statistical relational learning (e.g. MLNs) is helpful. +  * Knowledge of Unreal Engine material / lightning development 
-  * Good programming skills in Python.+  * Familiar with version-control systems (git) 
 +  * Able to work independently with minimal supervision
  
-Contact: [[team:daniel_nyga|Daniel Nyga]]+Contact: [[team:andrei_haidu|Andrei Haidu]] 
 +--></html>
  
 +== Scene Format Conversion Tool for Robotics Simulation (MA Thesis) ==
  
-==HiWi-Position: Knowledge Representation & Language Understanding for Intelligent Robots==+**Motivation:**
  
-In the context of the European research project RoboHow.Cog [1,2] we +With robotics playing a significant role in various domains, simulation is essential for developing and testing algorithms. Multiple simulators are available, each with its own specialized format (SDF, USD, MJCF, URDF, FBX) for describing scenes. This diversity of formats makes it challenging to transfer scenarios between simulators. Therefore, a versatile parser that can convert scene descriptions between these formats is highly valuable.
-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.  +
  
-The Institute for Artificial Intelligence is hiring a student researcher for the +{{:multiformat.png?400|}}
-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.+**Task Description:** 
 + 
 +The objective of this project is to develop a universal parser capable of converting scene descriptions between common formats. The following key steps are involved: 
 + 
 +  - Create a model to represent and store the scene graph. 
 +  - Implement import functions for the model to handle scene descriptions in any of the supported formats. 
 +  - Implement export functions for the model to generate scene descriptions in any of the supported formats. 
 + 
 +**Requirements:** 
 + 
 +  * A strong passion for robotics. 
 +  * Dedication to the chosen topic. 
 +  * Eager to learn. 
 + 
 +Contact: [[team:hoang_giang_nguyen|Giang Nguyen]] 
 + 
 +== Generating Comics about Everyday Experiences of a Robot (BA Thesis) == 
 + 
 +Summary: 
 +  * Query experience data from an existing database 
 +  * Retrieve situations of interest 
 +  * Recreate the scene in a 3D environment 
 +  * Apply a comic shader 
 +  * Find good camera position for moments of interest 
 +  * Generate a PDF summarizing the experiences as a comic strip 
 + 
 +Contact: [[team:daniel_bessler|Daniel Beßler]] 
 + 
 +== Integration of novel objects into Digital Twin Knowledge Bases (MA Thesis) == 
 + 
 +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. 
 + 
 +The focus of the thesis would be twofold: 
 +  * 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.
  
-Tasks: 
-  * 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: Requirements:
-  * Studies in Computer Science (Bachelor's, Master's or Diploma) +  * Knowledge about sensor data processing 
-  * Basic skills in Artificial Intelligence +  * Interest in model construction from sensory data 
-  * Optional: basic skills in Probability Theory +  * Work with KnowRob knowledge processing framework
-  * Optional: basic skills in Machine Learning +
-  * Good programming skills in Python and Java+
  
-Hours: 10-20 h/week 
  
-Contact: [[team:daniel_nyga|Daniel Nyga]]+Contact: [[team:patrick_mania|Patrick Mania]]
  
-[1] www.robohow.eu\\ +== Übersetzung einer globalen Produktklassifikation in eine bestehende Ontologie (BA Thesis) ==
-[2] http://www.youtube.com/watch?v=0eIryyzlRwA+
  
-== HiWi position: Segmentation and interpretation of 3D object models (HiWi/MA) ==+In dieser Arbeit soll die GS1 Produktklassifikation in eine Ontologie transformiert werden. Der GS1 Produktklassifikationsstandard ist online ( https://gpc-browser.gs1.org/) einsehbar. Anschließend soll in einem Jupyter Notebook anhand eines Beispiels gezeigt werden, wie andere Ontologien mit der erstellten Taxonomie verbunden werden können.
  
-{{ :research:cup2-segmented.png?170}}+Die Aufgaben dazu sind: 
 +  * Einarbeitung in Web Scraping und Abfrage der Daten von GS1 
 +  * Einarbeitung in Owlready und Erstellen der Taxonomie 
 +  * Erstellung des Jupyter Notebooks mit einem Beispiel, wie andere Ontologien verbunden werden können (die Beispielontologie wird gestellt)
  
-Competent object interaction requires knowledge about the structure and 
-composition of objects. In an ongoing research project, we are investigating 
-how part-based object models can automatically be extracted from CAD models 
-found on the Web, e.g. on the [[http://sketchup.google.com/3dwarehouse|3D warehouse]]. 
  
-We are looking for a student research assistant to push this topic forward. +Contact: [[team:michaela_kümpel|Michaela Kümpel]]
-In close collaboration with the researchers of the Institute for Artificial +
-Intelligence, the student will work on extending the software for mesh +
-segmentation, implement novel algorithms, improve the integration of the +
-methods into the robot's knowledge base, and update the modules for visualizing +
-the segmentation results. Depending on the results, cooperation on joint  +
-publications may be possible.+
  
-This HiWi position can serve as a starting point for future Bachelor's, + 
-Master's or Diploma Theses. Alternatively, we could extract a research +<html><!-- 
-project that could be worked on as a Master's or Diploma Thesis.+== Development of Modules for Robot Perception (Student Job / HiWi) == 
 +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. 
 +In this context, we are offering multiple Hiwi positions / student jobs for the following tasks: 
 +  * 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: Requirements:
-  * Good Java programming skills +  * Experience in C++. 
-  * Basic knowledge of 3D geometry calculations +  * Basic understanding of the ROS middleware and Linux. 
-  * Experience with working with 3D models is helpful+The spoken language in this job is german or english, based on your preference.
  
-Contact: [[team:moritz_tenorth|Moritz Tenorth]]+Contact: [[team:patrick_mania|Patrick Mania]] 
 +--></html>
  
-== Depth-Adaptive Superpixels (BA/HiWi)==+== Development of Modules for Robot Perception (Student Job / HiWi) == 
 +In our research group, we focus on the development of intelligent robots that are combining modern computer vision methods with knowledge representation.  
 +We are offering multiple Hiwi positions / student jobs for software development in the context of our Robot Perception framework [[http://robokudo.ai.uni-bremen.de/|RoboKudo]], which contains many algorithms for computer vision problems (mainly Python).
  
-We are currently investigating a new set of sensors (RGB-D-T), which is a combination of a kinect with a thermal image camera. Within this project we want to enhance the Depth-Adaptive Superpixels (DASP) to make use of the thermal sensor data. Depth-Adaptive Superpixels oversegment an image taking into account the depth value of each pixel. {{ :research:dt_dasp.png?200|}}+Requirements: 
 +  * Solid experience in python and object-oriented programming 
 +  * Basic understanding of the ROS middleware and Linux 
 +  * Basic understanding of computer vision methods
  
-Since the current implementation of DASP is not very performant for high resolution images, there are several possibilities options for doing a project in this field like reimplementing DASP using the CUDA, investigating how thermal data can be integrated, ...+The spoken language in this job is german or english, based on your preference. Work can be done fully remote. 
 + 
 +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 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: Requirements:
-  * Basic knowledge of image processing +  * Knowledge of 3D-Modelling tools. Blender would be highly preferred. 
-  * Good programming skills in C/C++. +  * Experience in Game Engine development. Ideally Unreal Engine 4 and C++. 
-  * Experience with CUDA is helpful+ 
 +The spoken language in this job is german or english, based on your preference.
  
-Contact: [[team:jan-hendrik_worch|Jan-Hendrik Worch]]+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: