Differences
This shows you the differences between two versions of the page.
Both sides previous revisionPrevious revisionNext revision | Previous revisionNext revisionBoth sides next revision | ||
jobs [2015/06/19 12:58] – winkler | jobs [2021/10/21 15:37] – [Theses and Student Jobs] pmania | ||
---|---|---|---|
Line 1: | Line 1: | ||
~~NOTOC~~ | ~~NOTOC~~ | ||
- | =====Theses and Jobs===== | ||
- | If you are looking for a bachelor/ | ||
+ | =====Open researcher positions===== | ||
+ | ====Digital Twin Knowledge Base for submarine robot inspection/ | ||
+ | The Institute for Artificial Intelligence (IAI) investigates methods for cognition-enabled robot control. The research is at the intersection of robotics and Artificial Intelligence and includes methods for intelligent perception, dexterous object manipulation, | ||
- | == HiWi-Position: | + | As a researcher of the IAI, you actively research by applying |
- | When dealing with real-world robot tasks, simulation that is close to reality is key to test behavior-driven, | + | **Prerequisites: |
+ | * Digital Twins | ||
+ | * Knowledge Representation | ||
+ | * Data structures | ||
+ | * Data Stream Representation. | ||
- | Requirements: | + | **Hiring institution: |
- | | + | |
- | | + | |
- | | + | |
- | Contact: [[team: | + | **PhD Enrollment:** PhD position in the Institute for Artificial Intelligence at University of Bremen. The project involves collaboration with ROSEN in Bremen and UiO in Oslo. |
+ | The PhD examination acceptance requires a “Certificate of Equivalence for Foreign Vocational Qualifications”. More information available at [[https:// | ||
- | == GPU-based Parallelization | + | **Duration |
- | 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. | + | **Main Academic Supervisor: |
- | Requirements: | + | **Co-supervisors:** prof. Einar Broch Johnsen (UiO, Norway), dr. Peter Kampmann (ROSEN, Germany) |
- | | + | =====Theses |
- | | + | 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: | ||
- | == Online Learning of Markov Logic Networks for Natural-Language Understanding | + | == Physics-based grasping in VR with finger tracking(Student Job / HiWi) == |
- | Markov Logic Networks (MLNs) combine the expressive power of first-order logic and probabilistic graphical | + | Implementing physics-based grasping |
+ | using Manus VR. | ||
Requirements: | Requirements: | ||
- | * Experience in Machine Learning. | + | * Good C++ programming skills |
- | * Experience with statistical relational learning | + | * Familiar with skeletal animations |
- | * Good programming skills in Python. | + | * Experience with simulators/ |
+ | * Familiar with Unreal Engine API | ||
+ | * Familiar with version-control systems | ||
+ | * Able to work independently with minimal supervision | ||
- | Contact: [[team:daniel_nyga|Daniel Nyga]] | + | Contact: [[team:andrei_haidu|Andrei Haidu]] |
- | ==HiWi-Position: | ||
- | In the context of the European research project RoboHow.Cog [1,2] we | + | < |
- | are investigating methods for combining multimodal sources of knowledge | + | == Lisp / CRAM support assistant |
- | The Institute | + | Technical support |
- | development and the integration of probabilistic methods in AI, which enable intelligent robots | + | 8+ hours per week for up to 1 year (paid). |
- | This HiWi-Position can serve as a starting point for future Bachelor' | + | Requirements: |
+ | * Good programming skills in Common Lisp | ||
+ | * Basic ROS knowledge | ||
- | Tasks: | + | The student will be introduced |
- | * Implementation of an interface | + | |
- | * Linkage of the knowledge base to the executive | + | |
- | * Support | + | |
- | Requirements: | + | Contact: [[team:gayane_kazhoyan|Gayane Kazhoyan]] |
- | * Studies in Computer Science (Bachelor' | + | --></ |
- | * 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 | + | < |
+ | == Mesh Editing | ||
+ | {{ : | ||
- | Contact: [[team: | + | |
- | [1] www.robohow.eu\\ | + | Requirements: |
- | [2] http:// | + | * Good knowledge in 3D Modeling |
+ | * Familiar with Blender | ||
+ | Contact: [[team/ | ||
+ | --></ | ||
- | == Kitchen Activity Games in a Realistic Robotic Simulator (BA/ | ||
- | {{ : | ||
- | Developing new activities and improving the current simulation framework done under the [[http:// | ||
- | Requirements: | + | == 3D Animation and Modeling (Student Job / HiWi)== |
- | * Good programming skills in C/C++ | + | {{ : |
- | * Basic physics/ | + | |
- | * Gazebo simulator basic tutorials | + | |
- | Contact: [[team: | + | Developing and improving existing or new 3D (static/ |
+ | models in Blender / Maya (or other). Further importing and testing the | ||
+ | models against Unreal Engine. | ||
- | == Integrating Eye Tracking in the Kitchen Activity Games (BA/MA)== | + | Bonus: Working with state of the art 3D Scanners |
- | | + | |
- | + | ||
- | 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. | + | |
Requirements: | Requirements: | ||
- | * Good programming skills in C/C++ | + | * Experience with Blender |
- | * 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: | Contact: [[team: | ||
- | == Hand Skeleton Tracking Using Two Leap Motion Devices (BA/MA)== | ||
- | {{ : | ||
- | Improving the skeletal tracking offered by the [[https:// | + | == App zur Generierung von Ernährungsempfehlungen |
- | The tracked hand can then be used as input for the Kitchen Activity Games framework. | + | Dies ist ein Wissensrepräsentations-Thema. Basierend auf einem bestehenden Wissensgraphen mit Produktinformationen sollen weitere ernährungsspezifische Informationen wie z.B. Substitute für Rezeptzutaten oder Rezepte für spezielle Ernährungsgewohnheiten generiert werden. Diese Informationen müssen aus bestehenden web-Quellen extrahiert und mit dem Wissensgraphen verknüpft werden. Die Informationen sollen dann in einer Smartphone-App (Android) visualisiert werden. Dabei kann auf bestehenden Apps aufgebaut werden. |
- | Requirements: | + | Aufgaben: |
- | * Good programming skills in C/C++ | + | * Arbeit mit Wissensrepräsentation und Wissensgraphen |
+ | * Wissensakquisition aus web-Quellen | ||
+ | * App Entwicklung mit der Unity game engine und/oder Flutter | ||
- | Contact: [[team:andrei_haidu|Andrei Haidu]] | + | Contact: [[team:michaela_kümpel|Michaela Kümpel]] |
- | == Fluid Simulation in Gazebo | + | == Sprachauswahl für Shopping Assistenten |
- | {{ : | + | |
- | [[http:// | + | Weiterentwicklung eines Produktinformationssystems im Einzelhandel für Smartphones |
+ | Dabei wird auf bestehenden Apps aufgebaut. | ||
- | Currently there is an [[http:// | + | Aufgaben: |
+ | * App Entwicklung mit der Unity game engine und Flutter | ||
+ | * Erweiterung der App um eine Sprachauswahl | ||
+ | * Arbeit mit Wissensrepräsentation und Wissensgraphen für Sprachmodellierung | ||
- | 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/ | ||
- | 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: |
- | Another topic would be the visualization of the fluid, currently is done by rendering every particle. For the rendering engine [[http:// | + | == Situational awareness in kitchen environments (MA Thesis) == |
- | Here is a [[https:// | + | This is a knowledge representation topic including knowledge graphs. The idea is so link external Web-knowledge to an existing knowledge framework |
- | Requirements: | + | A result would be that a spoon next to a bowl with cereal would be used for eating while a spoon on a stove next to a pot would be used for stirring. |
- | * Good programming skills in C/C++ | + | |
- | * Interest in Fluid simulation | + | |
- | * Basic physics/ | + | |
- | * Gazebo simulator and Fluidix basic tutorials | + | |
- | Contact: [[team: | + | requirements: |
+ | * Work with KnowRob knowledge processing framework | ||
+ | * Work with knowledge graphs and Linked Data to create a situational awareness knowledge graph that can be linked to KnowRob | ||
+ | * Implement reasoning about situations (based on perceived environment) and object use | ||
- | == Automated sensor calibration toolkit | + | Contact: [[team: |
+ | == Integration of novel objects into Digital Twin Knowledge Bases (MA 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, | + | In this thesis, the goal is to make a robotic system learn new objects automatically. |
+ | The system should be able to generate | ||
- | The topic for this thesis | + | The focus of the thesis |
+ | * Develop methods | ||
+ | * In the second step the system | ||
- | {{ : | ||
- | 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: | + | Requirements: |
- | * Good programming skills | + | * Knowledge about sensor data processing |
- | * ROS, OpenCV | + | * Interest |
+ | * Work with KnowRob knowledge processing framework | ||
- | [1] http:// | ||
- | Contact: [[team:alexis_maldonado|Alexis Maldonado]] and [[team: | + | Contact: [[team:patrick_mania|Patrick Mania]] |
- | == On-the-fly 3D CAD model creation (MA)== | ||
- | Create models during runtime | + | == Development of Modules |
+ | 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 | ||
+ | In this context, we are currently offering | ||
+ | * Software development to create Interfaces between ROS and Unreal Engine 4 (mainly C++) | ||
+ | * Software development for our Robot Perception framework [[http:// | ||
- | Requirements: | + | Requirements: |
- | * Good programming skills | + | * Experience |
- | * strong background | + | * Basic understanding of the ROS middleware. |
- | * ROS, OpenCV, PCL | + | The spoken language |
- | Contact: [[team:thiemo_wiedemeyer|Thiemo Wiedemeyer]] | + | Contact: [[team:patrick_mania|Patrick Mania]] |
- | == Simulation of a robots belief state to support perception(MA) == | + | == Game Engine Developer and 3D-Modelling |
+ | A recent development in the field of AI is the usage of photorealistic simulations, | ||
+ | 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. | ||
- | Create a simulation environment that represents | + | Therefore, we are currently offering multiple Hiwi positions / student jobs for the following tasks: |
+ | * Modelling of objects | ||
+ | * Creation | ||
- | Requirements: | + | Requirements: |
- | * Good programming skills in C/C++ | + | * Knowledge of 3D-Modelling tools. Blender would be highly preferred. |
- | * strong background | + | * Experience |
- | * Gazebo, OpenCV, PCL | + | |
- | + | ||
- | Contact: [[team: | + | |
- | + | ||
- | == Multi-expert segmentation of cluttered and occluded scenes == | + | |
- | + | ||
- | 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 | + | |
- | Requirements: | + | The spoken language |
- | * Good programming skills | + | |
- | * 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: