You are here:: » Home » Open researcher positions

Differences

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

--- jobs [2015/07/28 12:11] – [Theses and Jobs] winkler
+++ jobs [2023/08/01 12:05] – [Theses and Student Jobs] hoanggia
@@ 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=====
+{{blog>:jobs?3&date&footer&firstseconly&readmore}}
-== GPU-based Parallelization of Numerical Optimization Techniques (BA/MA/HiWi)==
-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.
+<html>
+<div style="width:100%;border-bottom:10px solid #DCDFE3;margin-bottom:80px;"></div>
+</html>
-Requirements:
-  * Skills in numerical optimization algorithms
-  * Good programming skills in Python and C/C++
-Contact: [[team:daniel_nyga|Daniel Nyga]]
-== Online Learning of Markov Logic Networks for Natural-Language Understanding (MA)==
+=====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.
-Requirements:
+<html><!--
-  * Experience in Machine Learning.
+== Physics-based grasping in VR with finger tracking(Student Job / HiWi) ==
-  * Experience with statistical relational learning (e.g. MLNs) is helpful.
-  * Good programming skills in Python.
-Contact: [[team:daniel_nyga|Daniel Nyga]]
+Implementing physics-based grasping models in virtual environments,
+using Manus VR.
+Requirements:
+  * Good C++ programming skills
+  * Familiar with skeletal animations
+  * Experience with simulators/physics-/game- engines
+  * Familiar with Unreal Engine API
+  * Familiar with version-control systems (git)
+  * Able to work independently with minimal supervision
-==HiWi-Position: Knowledge Representation & Language Understanding for Intelligent Robots==
+Contact: [[team:andrei_haidu|Andrei Haidu]]
+--></html>
-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
+<html><!--
-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.
+== Lisp / CRAM support assistant (HiWi) ==
-This HiWi-Position can serve as a starting point for future Bachelor's, Master's or Diploma Theses.
+Technical support for the group for Lisp and the CRAM framework. \\
++ hours per week for up to 1 year (paid).
-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:
-  * 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\\
+<html><!--
-[2] http://www.youtube.com/watch?v=0eIryyzlRwA
+== Mesh Editing / Mesh Segmentation/Cutting (Student Job / HiWi)==
+ {{ :research:human_hand_cutting.png?150|}}
+ Editing and cutting a human mesh into different parts in Blender / Maya (or other).
-== Kitchen Activity Games in a Realistic Robotic Simulator (BA/MA/HiWi)==
+Requirements:
- {{ :research:gz_env1.png?200|}}
+  * Good knowledge in 3D Modeling
+  * Familiar with Blender / Maya (or other)
-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.
+Contact: [[team/mona_abdel-keream|Mona Abdel-Keream]]
+--></html>
-Requirements:
-  * Good programming skills in C/C++
-  * Basic physics/rendering engine knowledge
-  * Gazebo simulator basic tutorials
-Contact: [[team:andrei_haidu|Andrei Haidu]]
+<html><!--
+== 3D Animation and Modeling (Student Job / HiWi)==
+ {{ :research:kitchen_unreal.jpg?200|}}
-== Integrating Eye Tracking in the Kitchen Activity Games (BA/MA)==
+Developing and improving existing or new 3D (static/skeletal)
- {{ :research:eye_tracker.png?200|}}
+models in Blender / Maya (or other). Further importing and testing the
+models against Unreal Engine.
-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 sketching new models.
 Requirements:
-  * Good programming skills in C/C++
+  * Experience with Blender / Maya (or other)
-  * Gazebo simulator basic tutorials
+  * Knowledge of Unreal Engine material / lightning development
+  * Familiar with version-control systems (git)
+  * Able to work independently with minimal supervision
 Contact: [[team:andrei_haidu|Andrei Haidu]]
+--></html>
-== Hand Skeleton Tracking Using Two Leap Motion Devices (BA/MA)==
+== Scene Format Conversion Tool for Robotics Simulation (MA Thesis) ==
- {{ :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.
+**Motivation:**
-The tracked hand can then be used as input for the Kitchen Activity Games framework.
+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.
-Requirements:
+{{:multiformat.png?400|}}
-  * Good programming skills in C/C++
-Contact: [[team:andrei_haidu|Andrei Haidu]]
+**Task Description:**
-== Fluid Simulation in Gazebo (BA/MA)==
+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:
- {{ :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.
+  - 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.
-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.
+**Requirements:**
-The computational method for the fluid simulation is SPH (Smoothed-particle Dynamics), however newer and better methods based on SPH are currently present
+  * A strong passion for robotics.
-and should be implemented (PCISPH/IISPH).
+  * Dedication to the chosen topic.
+  * Eager to learn.
-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).
+Contact: [[team:hoang_giang_nguyen|Giang Nguyen]]
-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.
+== Generating Comics about Everyday Experiences of a Robot (BA Thesis) ==
-Here is a [[https://vimeo.com/104629835|video]] example of the current state of the fluid in Gazebo.
+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
-Requirements:
+Contact: [[team:daniel_bessler|Daniel Beßler]]
-  * Good programming skills in C/C++
-  * Interest in Fluid simulation
-  * Basic physics/rendering engine knowledge
-  * Gazebo simulator and Fluidix basic tutorials
-Contact: [[team:andrei_haidu|Andrei Haidu]]
+== 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.
-== Automated sensor calibration toolkit (BA/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.
-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.
-The topic for this thesis is to develop an automated system for calibrating cameras, especially RGB-D cameras like the Kinect v2.
+Requirements:
+  * Knowledge about sensor data processing
+  * Interest in model construction from sensory data
+  * Work with KnowRob knowledge processing framework
- {{ :kinect2_calibration_setup_small.jpg?200|}}
-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:
+Contact: [[team:patrick_mania|Patrick Mania]]
-  * Good programming skills in Python and C/C++
-  * ROS, OpenCV
-[1] http://www.halcon.de/
+== Integration von Nährwertangaben für Rezepte in bestehende Website (BA Thesis) ==
-Contact: [[team:alexis_maldonado|Alexis Maldonado]] and [[team:thiemo_wiedemeyer|Thiemo Wiedemeyer]]
+In dieser Arbeit soll eine bestehende Website mit Nährwertangaben und Zusatzfunktionalität zu Produkten um eine Nährwertangabe zu Rezepten erweitert werden. Es handelt sich um folgende website: productkg.informatik.uni-bremen.de
-== On-the-fly 3D CAD model creation (MA)==
+Die Aufgaben dazu sind:
+  * Vergleich von bestehenden Lösungen.
+  * Erweiterung einer Ontologie um Nährwertangaben.
+  * Erweiterung der Website.
-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.
-Requirements:
+Contact: [[team:michaela_kümpel|Michaela Kümpel]]
-  * 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) ==
+<html><!--
+== 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 currently 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++)
-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:
+  * 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.
-Requirements:
+Contact: [[team:patrick_mania|Patrick Mania]]
-  * Good programming skills in C/C++
+--></html>
-  * strong background in computer vision
-  * Gazebo, OpenCV, PCL
-Contact: [[team:ferenc_balint-benczedi|Ferenc Balint-Benczedi]]
+== 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.
-== Multi-expert segmentation of cluttered and occluded scenes ==
+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.
-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:
+  * Knowledge of 3D-Modelling tools. Blender would be highly preferred.
+  * Experience in Game Engine development. Ideally Unreal Engine 4 and C++.
-Requirements:
+The spoken language in this job is german or english, based on your preference.
-  * 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]]
+Contact: [[team:patrick_mania|Patrick Mania]]

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: