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 [2015/03/19 13:27] – [Theses and Jobs] raiderjobs [2018/11/15 10:04] – [Theses and Student Jobs] ahaidu
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. 
  
 +=====Open researcher positions=====
 +== Doctoral Candidate / Early Stage Researcher position == 
 +As a research associate at the Institute for Artificial Intelligence, you will develop systems for automated knowledge representation and knowledge acquisition, which combine the human ability of understanding language, perceiving objects and learning from experience. In particular, intelligent robots are to be endowed with the capability of autonomously acquire knowledge in order to robustly act in human environments and competently and successfully achieve everyday human-scale tasks.  
  
 +In particular, your challenges comprise the following:
 +  * the development and implementation of probabilistic models and algorithms for learning and reasoning in complex scenarios of intelligent service robots, 
 +  * the creation and maintenance of software documentation as well as the presentation of research results at top-tier international conferences, 
 +  * self-organized and ambitious work both individually and in a team of researchers, 
 +  * the authoring of research grant proposals.  
  
-== GPU-based Parallelization of Numerical Optimization Techniques (BA/MA/HiWi)==+Prerequisites:  
 +  * Successfully completed Master's degree (or equivalent) in Computer Science with a major in Artificial Intelligence/Machine Learning,  
 +  * very good skills in Machine Learning and Data Mining; esp. experience with probabilistic graphical models (Bayesian networks/Markov random fields/Markov logic networks) and related formalisms,  
 +  * very good programming skills in the Python/Cython/C/C++ programming languages and respective libraries for scientific computing (numpy/scipy/sympy),  
 +  * experience in natural-language understanding and semantic modeling helpful.
  
-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.+Besides the willingness and ability to quickly dive into new and complex research scenarios and topics, we expect organizational skills, the ability to work in a team and high commitment and dedication to you research. Very good skills of the English language is required.
  
-Requirements: +Research associate 
-  * Skills in numerical optimization algorithms +with the Institute for Artificial Intelligence 
-  * Good programming skills in Python and C/C+++at the University of Bremen, Germany,
  
-Contact: [[team:daniel_nyga|Daniel Nyga]]+Salary is according to the German Federal pay scale, TV-L 13, full-time. The position is available as soon as possible.
  
-== Online Learning of Markov Logic Networks for Natural-Language Understanding (MA)==+Please send your application (cover letter, CV, certificates, project references, etc) under reference number **A192/18** to: [[mailto:ai-office@cs.uni-bremen.de|ai-office@cs.uni-bremen.de]] 
 +=====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.
  
-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><!-- 
 +== Lisp / CRAM support assistant (HiWi) ==
  
-Requirements: +Technical support for the group for Lisp and the CRAM framework. \\ 
-  * Experience in Machine Learning. +8+ hours per week for up to 1 year (paid).
-  * Experience with statistical relational learning (e.g. MLNs) is helpful. +
-  * Good programming skills in Python. +
- +
-Contact: [[team:daniel_nyga|Daniel Nyga]] +
- +
- +
-==HiWi-Position: Knowledge Representation & Language Understanding for Intelligent Robots== +
- +
-In the context of the European research project RoboHow.Cog [1,2] we +
-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 +
-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: +
-  * 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) +  * Good programming skills in Common Lisp 
-  * Basic skills in Artificial Intelligence +  * Basic ROS knowledge
-  * Optional: basic skills in Probability Theory +
-  * Optional: basic skills in Machine Learning +
-  * Good programming skills in Python and Java+
  
-Hours: 10-20 h/week+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:daniel_nyga|Daniel Nyga]]+Contact: [[team:gayane_kazhoyan|Gayane Kazhoyan]] 
 +--></html>
  
-[1] www.robohow.eu\\ +== Student job for data visualization ==
-[2] http://www.youtube.com/watch?v=0eIryyzlRwA+
  
 +In the scope of the CRC Farbige Zustände we use machine-learning techniques and novel high-troughput methods to find new materials. To present the project to the scientific community as well as to the non-scientific audience, we want to visualize its ideas and concepts in terms of interactive web applications. Your task would be to design and develop visualization tools that allow the interaction with the data of the project. You will work with Javascript/AngularJS/NodeJS and MongoDB, so it would be helpful if you already have experience in those fields. Creativity in developing new visualizations is demanded just as much as good programming skills.
  
-== Kitchen Activity Games in a Realistic Robotic Simulator (BA/MA/HiWi)== +Perspective of future BA/MA topics in this project!
- {{ :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.+If you're interested, contact [[team:mareike_picklum|Mareike Picklum]]
  
-Requirements: 
-  * Good programming skills in C/C++ 
-  * Basic physics/rendering engine knowledge 
-  * Gazebo simulator basic tutorials 
  
-Contact: [[team:andrei_haidu|Andrei Haidu]]+<html><!-- 
 +== 3D Model / Material / Lightning Developer (Student Job / HiWi)== 
 + {{ :research:kitchen_unreal.jpg?200|}} 
  
-== Integrating Eye Tracking in the Kitchen Activity Games (BA/MA)== +Developing and improving existing 3D models in Blender / Maya (or other). Importing the models in Unreal Engine, where the Materials and Lightning should be improved to be close as possible to realism. 
- {{ :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.+Bonus: Working with state of the art 3D Scanners [[https://www.goscan3d.com/|Go!SCAN]] for creating new realistic models.
  
 Requirements: Requirements:
-  * Good programming skills in C/C++ +  * Experience with Blender / Maya (or other) 
-  * Gazebo simulator basic tutorials+  * Knowledge of Unreal Engine material / lightning development
  
-Contact: [[team:andrei_haidu|Andrei Haidu]] 
  
-== Hand Skeleton Tracking Using Two Leap Motion Devices (BA/MA)== 
- {{ :research:leap_motion.jpg?200|}}  
- 
-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. 
- 
-The tracked hand can then be used as input for the Kitchen Activity Games framework. 
- 
-Requirements: 
-  * Good programming skills in C/C++ 
  
 Contact: [[team:andrei_haidu|Andrei Haidu]] Contact: [[team:andrei_haidu|Andrei Haidu]]
  
-== Fluid Simulation in Gazebo (BA/MA)== +== Integrating PR2 in the Unreal Game Engine Framework (BA/MA/HiWi)== 
- {{ :research:fluid.png?200|}} + {{ :research:unreal_ros_pr2.png?100|}} 
  
-[[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. +Integrating the [[https://www.willowgarage.com/pages/pr2/overview|PR2]] robot with [[http://www.ros.org/|ROS]] support in the [[https://www.unrealengine.com|Unreal Engine 4]] Framework.
- +
-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. +
- +
-The computational method for the fluid simulation is SPH (Smoothed-particle Dynamics), however newer and better methods based on SPH are currently present +
-and should be implemented (PCISPH/IISPH). +
- +
-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). +
- +
-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++   * Good programming skills in C/C++
-  * Interest in Fluid simulation 
   * Basic physics/rendering engine knowledge   * Basic physics/rendering engine knowledge
-  * Gazebo simulator and Fluidix basic tutorials+  * Basic ROS knowledge 
 +  * UE4 basic tutorials
  
 Contact: [[team:andrei_haidu|Andrei Haidu]] Contact: [[team:andrei_haidu|Andrei Haidu]]
  
  
-== Automated sensor calibration toolkit (MA)==+== Realistic Grasping using Unreal Engine (BA/MA/HiWi) ==
  
-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.+{{  :teaching:gsoc:topic2_unreal.png?nolink&150|}}
  
-The topic for this thesis is to develop an automated system for calibrating cameras, especially RGB-D cameras like the Kinect v2.+The objective of the project is to implement var- 
 +ious human-like grasping approaches in a game developed using [[https://www.unrealengine.com/|Unreal Engine]]. 
  
- {{ :kinect2_calibration_setup_small.jpg?200|}} +The game consist of a household environment where a user has to execute various given tasks, such as cooking a dish, setting the table, cleaning the dishes etc. The interaction is done using various sensors to map the users hands onto the virtual hands in the game.
-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+
  
 +In order to improve the ease of manipulating objects the user should
 +be able to switch during runtime the type of grasp (pinch, power
 +grasp, precision grip etc.) he/she would like to use.
 +  
 Requirements:  Requirements: 
-  * Good programming skills in Python and C/C++ +  * Good programming skills in C++ 
-  * ROS, OpenCV+  * Good knowledge of the Unreal Engine API.  
 +  * Experience with skeletal control / animations / 3D models in Unreal Engine.
  
-[1] http://www.halcon.de/ 
  
-Contact: [[team:alexis_maldonado|Alexis Maldonado]] and [[team:thiemo_wiedemeyer|Thiemo Wiedemeyer]]+Contact: [[team/andrei_haidu|Andrei Haidu]] 
 +--></html>
  
-== 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.+== Unreal Engine Editor Developer (Student Job / HiWi)== 
 + {{ :research:unreal_editor.png?150|}} 
  
-Requirements:  +Creating new user interfaces (panel customization) for various internal plugins using the Unreal C++ framework [[https://docs.unrealengine.com/latest/INT/Programming/Slate/|SLATE]].
-  * Good programming skills in C/C++ +
-  * strong background in computer vision  +
-  * ROS, OpenCV, PCL+
  
-Contact: [[team:thiemo_wiedemeyer|Thiemo Wiedemeyer]] 
  
-== Simulation of a robots belief state to support perception(MA) ==+Requirements: 
 +  * Good C++ programming skills 
 +  * Familiar with the [[https://docs.unrealengine.com/latest/INT/Programming/Slate/|SLATE]] framework 
 +  * Familiar with Unreal Engine API
  
-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. +Contact: [[team:andrei_haidu|Andrei Haidu]]
  
-Requirements:  
-  * Good programming skills in C/C++ 
-  * strong background in computer vision  
-  * Gazebo, OpenCV, PCL 
  
-Contact: [[team:ferenc_balint-benczedi|Ferenc Balint-Benczedi]] 
  
-== Multi-expert segmentation of cluttered and occluded scenes ==+== OpenEASE rendering in Unreal Engine (BA/MA Thesis, Student Job / HiWi)==
  
-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:  +Implmenting the rendering of the [[https://data.open-ease.org/|OpenEASE]] knowledge base visualization in Unreal Engine. This will have to be packaged as a HTML5 executable and inserted into the website.
-  * Good programming skills in C/C++ +
-  * strong background in 3D vision  +
-  * basic knowledge of ROS, OpenCV, PCL+
  
-Contact: [[team:ferenc_balint-benczedi|Ferenc Balint-Benczedi]]+Requirements: 
 +  * Good C++ programming skills 
 +  * Familiar with Unreal Engine API 
 +  * Familiar with HTML5 and JavaScript 
 +  * Familiar with the [[https://docs.unrealengine.com/latest/INT/Programming/Slate/|SLATE]] framework 
 +  * Familiar with basic ROS communication 
 + 
 +Contact: [[team:andrei_haidu|Andrei Haidu]]
- 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: