Studentische Arbeiten und HiWi-Stellen

Initiative zeigen!

Falls in dieser Übersicht kein passendes Thema oder eine passende Stelle gefunden werden konnte, aber trotzdem Interesse besteht an unseren Lehrstuhl mitzuwirken, kann über die folgende Emailadresse eine Nachricht hinterlassen werden:

work-and-thesis@rsi.ei.tum.de

Mechatronics System Developement

Development of an Electronic (Sub-)Module Library for Robotic Systems

→ Research/Engineering-Internship
→ For more information contact us!

Steps:

  • Component research
  • Design, production and test of component submodules
  • Documentation and development of module library/database

Prerequisites:

  • PCB Design / Production
  • Microcontroller programming

Contact:
Johannes Ringwald
johannes.ringwald@tum.de
+49 (89) 289 - 29414
---
Edmundo Pozo Fortunic
edmundo.pozo@tum.de

Forschungspraxis in Mechatronic Systems and Robot Development, Control, Optimization or Pneumatic Acutators

I am always looking for talented students who are interested in doing their internship (Forschungspraxis) in the following fields:

  • mechatronic systems and robot development (CAD + system design)
  • optimization and identification, 
  • control and observers,
  • pneumatic acutators,
  • modeling of multibody systems and actuators,
  • experimental data analysis and signal processing.

It would be benefitial if you have already gained some experience in Matlab Simulink or Solidworks. It might also be possible to write a master thesis after the internship.

Please contact me by the following address:
alexander.toedtheide@tum.de

Development of a Mechatronic Pneumatic Wrist for Human Robot Collaboration

Pneumatic (air driven) actuators are a promising technology for human robot collaboration as they offer unique features such as inherent compliance, backdrivability and robustness to external impacts that have not been achieved by conventional electromechanical actuators so far. In the last years tendon-driven pneumatic systems, inspired by the biological architecture of the human arm, have been proposed by our team showing the promising performance of the technology.

The focus of this thesis is the mechatronic system design and further integration of the wrist based on our previous works.

You will get the opportunity to work in:

  • CAD-Design (Solidworks),
  • Pneumatic actuators,
  • Multiphysics Modeling and Control (Matlab/Simulink),
  • PCB design and low-level communication.

Prior background in pneuamtic systems or thermodynamics is not required. Sound knowledge in Automatic Control, Mechanical or Electrical Modeling and Optimization can be usefull.

For more information please contact:

alexander.toedtheide@tum.de

Tel.: +49 (89) 289 - 29414

Videos of previous works see below:

 

Modeling and Control of Pneumatically Driven Structures

Pneumatic (air driven) actuators are a promising technology for human robot collaboration as they offer unique features such as inherent compliance, backdrivability and robustness to external impacts that have not been achieved by conventional electromechanical actuators so far. In the last years tendon-driven pneumatic systems, inspired by the biological architecture of the human arm, have been proposed by our team showing the promising performance of the technology.

Apart from other listed topics in the field of pneumatic actuators other interesting topics might be available. For more information please contact:

alexander.toedtheide@tum.de

You will get the opportunity to work in the following fields:

  • Pneumatic actuators,
  • Matlab/Simulink
  • Multibody systems

Prior background in pneuamtic systems or thermodynamics is not required. Sound knowledge in Automatic Control, Mechanical or Electrical modeling, Optimization and Observers can be usefull.

Videos of previous research see below:

Prosthesis Model Learning and Identification

MSRM is currently developing a new prototype of an intelligent full mechatronic arm prosthesis.
The system has been successfully integrated and shows good performance.

The work focuses on model learning and identification of multi-body systems and gearboxes.

You will get the opportunity to work in:

  • Mechanical Modeling (Matlab/Simulink),
  • Optimization algorithms,
  • Experimental Evaluation.

The work can be adapted or extended to an Forschungspraxis (FP) or Bachelor thesis.

For more information please contact:

alexander.toedtheide@tum.de

Tel.: +49 (89) 289 - 29414

Development of a Miniature, Mechatronic Valve for Pneumatic Systems

Mechatronics Motor Module Development

MSRM plans to build new robotic systems.

We are looking for talented students who are interested in the mechatronic development of electromechanical devices.

The work includes CAD modeling of robot joints, experimental implementation of sensors, motors and controllers.

Please contact us for further information.

alexander.toedtheide@tum.de

 

Projects in Rehabilitation Robotics

A Study on Lower Limb Neuromuscular Rehabilitation

Tasks:

• Defining protocol for optimizing rehabilitation process

• Defining criterion for monitoring the recovery

Preferred background:

• Biomechanics

• Physical therapy and/or diagnostics

Description:

In collaboration with Schön Klinik Bad Aibling (internationally recognized hospital for neurology) and Reactive Robotics GmbH, we aim to develop an intelligent robotic solution for early mobilization of intensive care unit patients.

The goals of the thesis are:

• To observe and analyze the neuromuscular recovery process of patients in intensive care stations

• To define a set of parameters which can be monitored to quantitatively assess the patient recovery process

• Define a protocol for optimizing the recovery process. This protocol will subsequently be implemented on a robot by the project team. The long term motivation of this work is to make effective physiotherapy accessible to every individual in need with the help of machine intelligence.

Contact information:

Chair of Robotics Science and Systems Intelligence Munich School of Robotics and Machine Intelligence, TUM Dinmukhamed Zardykhan (d.zardykhan@tum.de)

Robot Safety: Bachelor/Master Thesis | Research/Engineering-Internship

Designing Collision Test Devices and Collision Testing

Recently the collaboration between robot and human is becoming more and more close. Therefore several constraints for the robot have to be fulfilled. Most importantly human injury has to be prevented. Based on work of Prof. Dr. Haddadin a new portable collision test device has to be build, collision test with human subjects and models for human subjects run and the data merged into safety curves. 
 

Tasks:

- CAD modelling and construction of a collision test device for human limbs 
- Validation of the device and propsed models
- Testing and data collection

Type:

Internship, Bachelor-/Masterthesis
(The tasks can be spllit into diffrent workpackages)

Prerequisites:

- experience in CAD-modelling
- C++ knowledge
- basic biomechanical knowledge

Contact:

robin-jeanne.kirschner@tum.de

Collision Analysis and Safe Control in Human-Robot Interaction

Currently, increasing effort is taken in the robotics community to understand injury mechanisms during physical human-robot interaction (pHRI). This is motivated by the fact that human and robot will work intensively and closely together, and therefore, one has to be aware of the potential threats in case such a close cooperation takes place and take appropriate countermeasures to ensure human safety via planning and/or control. In the context of safety in pHRI, possible topics that can be addressed in the thesis/internship are:

  • Design and analysis of collision experiments and/or testing devices
  • Development and verification of collision simulations
  • Survey of biomechanics and forensics literature
  • Development of robot motion planning and/or control schemes for ensuring human safety

Prerequisites:

  • Studies in Mechanics, Mechatronics, Electronics, Computer Science 
  • Knowledge in robotics & control (for topics on planning & control)
  • Good C++ programming skills
  • Matlab/Simulink
  • Working knowledge in ROS
  • Ability to work well structured and organized
  • Creativity

Contact:
Mazin Hamad, M.Sc.
mazin.hamad@tum.de
Chair of Robotics Science and Systems Intelligence

Artificial Hand Design

Novel Contact Sensor Design and Interpretation Pipeline

→ Bachelor/Master Thesis
→ For more information contact us!

Steps:

  • Literature research
  • Concept design
  • Experimental setup
  • Experimental evaluation (compare different sensors)

Prerequisites:

  • Signal-Processing
  • Sensor-Techonology
  • Mechatronic-System developement
    --> Focus on: Sensors and sensor-electronics
  • Programming
  • Matlab

Contact:
 Francesco Vigni
francesco.vigni@tum.de
+49 (89) 289 - 29436
---
Johannes Ringwald
johannes.ringwald@tum.de
+49 (89) 289 - 29414

Learning the Body of Robotic Hands: Automatic Component Placement

Bachelor/Master Thesis | Research/Engineering-Internship
→ For more information contact us!

Prerequisites:

  • Handling/Collision-Detection of 3D models/objects
    (e.g. CAD, 3D-Game-Engines, STL-Files, ...)
  • Optimization
  • Programming
  • Matlab

Contact:
Johannes Ringwald
johannes.ringwald@tum.de
+49 (89) 289 - 29414

Self-Structure-Learning for Automatic Design of Robotic Hands (FEM based)

Bachelor/Master Thesis | Research/Engineering-Internship
→ Contact us for more information

Prerequisites:

  • Topology/Structure Optimization
  • CAD / FEM
  • Construction/hardware development
  • Programming
  • Matlab

Contact:
Johannes Ringwald
johannes.ringwald@tum.de
+49 (89) 289 - 29414

Task Planning

Multi-Agent Task Planning for Complex Assembly Tasks

Type: Research internship

Tasks

The goal is to implement a task planner that incorporates both human and robotic co-workers to accomplish a given assembly task. Concrete work packages are:

  • Implementation of task planner based on existing theory
  • Further development of task planner by integrating e.g. human factor analysis

Requirements

  • Experienced with C++ (this is very important)
  • Familiar with python
  • Basic knowledge in robotics (task planning, AI are a plus)

Motivation

The strict separation of human and robot workspaces was considered a necessity until a few years ago, as humans were usually considered as disturbances to the execution of a robot task and robots in turn posed significant threats to the human. However, with the recent emergence of safer robots that enable humans and robots to share the same workspace, the field of physical human-robot-interaction (pHRI) gained also significant practical relevance. On the practical side, pHRI is nowadays of particular interest in purely manual industrial assembly tasks. Despite robots have proven to be well suited for many tasks and the potential of safer robots is now well understood, numerous rather complex processes cannot be accomplished yet by robots alone due to their limited cognitive capabilities. In particular, flexible tasks, as well as unstructured or underspecified environments pose still significant challenges to full automation. Therefore, the combination of human cognitive skills with the skills of collaborative robots allows not only for working alongside humans and in partially unknown environments, but also collaborate with other agents, let them be humans or other robots, for accomplishing a common goal. Consequently, the robot needs to be able to plan complex tasks, which involve interactions, collaborations, common goals and certain group dynamics.

Contact

Lars Johannsmeier

lars.johannsmeier@tum.de

+49 (89) 289 - 29406

Designing Adaptive and Intelligent Robots using Behavior Trees (BTs)

Type: Bachelor / Master Thesis  / Internship

Background

The Flagship Initiative 'Geriatronics – Robot Assistants for the Elderly' powered by the Munich School of Robotics and Machine Intelligence (MSRM) is driven by its vision to create intelligent assistants that support the elderly in long-term self-determined ageing.

The newly founded TUM Research Center Geriatronics is located is Garmisch-Partenkirchen, 90km south of Munich. With its geriatronics demo apartment, it is the initiative’s prime project location and offers a superb working environment for research and field test of robotic solutions for the elderly.

Motivation

Central goal of the project is the development of an adaptive, humanoid service robot called GARMI for the preservation of self-determination in third life stage. GARMI should be able for perform simple everyday tasks in household environments. We propose behavior trees (BTs) to design and structure GARMI’s high-level task plan. BTs have been well proven in the game developer community to design the behavior of autonomous agents, being used in high profile video games such as Halo. Unlike a Finite State Machine (FSM), or other systems used for AI programming, a behavior tree is a tree of hierarchical nodes that control the flow of decision making of an AI entity, making task nodes both modular and reusable.

Tasks

The goal is to implement and evaluate a behavior tree for our GARMI prototype and model first tasks like setting the table or fetching an object. The research questions will be defined together with the student. Interesting questions can include: How can autonomous robot behavior be designed with behavior trees? How can tasks be modularized and decomposed (e.g. skills and actions)? How can behavior trees be generated based on teaching by non-expert users? 

Requirements

  • Good programming skills in C++ or Python 
  • Experience with Robot Operating System (ROS) – especially familiarity with topics, services and actions
  • Basic understanding of robotics
  • Experience in JavaScript (Node.js) is a plus
  • Creativeness and ability to work independently 

Location

Garmisch-Partenkirchen | no full-time presence needed – remote work possible

Contact

Anton Reindl

Email: anton.reindl@tum.de
Phone:  +49 (89) 289 – 29472
 

AI-Enabled Lab-Automation

AI unterstützter robotischer Lab Assistent: Zuverlässiges automatisiertes Flüssigkeitshandling für den Laboralltag der Zukunft

Typ: Forschungs-/Ingenieurpraktikum

→ Für weitere Informationen kontaktieren Sie uns!

Die Automatisierung von Laborprozessen in der Chemie, Bio-, Pharma- und Lebensmitteltechnologie sowie in der Medizin ist bereits heute Realität. Doch viele Lösungen, die heute auf dem Markt angeboten werden, sind entweder zu hochpreisig und/oder nur speziell und unflexibel für bestimmte Prozesse im Labor entwickelt und optimiert. Damit die Laborautomatisierung für den dynamischen Laboralltag als Werkzeug für Jedermann genutzt werden kann, soll in diesem Anwendungsforschungsprojekt ein mit AI unterstützter Automatisierungsablauf für einen robotischen Laborassistenten entwickelt und im Labor umgesetzt werden. Als zu automatisierender Prozess soll vorerst das zuverlässige automatisierte Flüssigkeitshandling angegangen werden. Um dies zu erreichen steht einer der neusten kollaborativen Roboter zur Verfügung sowie 3D-Druck-Möglichkeiten zur flexiblem Gripperfingerentwicklung.

Folgender Ablauf ist geplant:

  • Ausführliche Literaturrecherche Robotik in der Laborautomatisierung
  • Analyse und Entwicklung von Roboterfingersystemen zur Nutzung von Laborwerkzeugen
  • Analyse, Automatisierung und Evaluierung von Prozessabläufen in Bezug auf Flüssigkeitshandling im Labor
  • Und vieles mehr …

Voraussetzungen:

  • Aus dem Fachbereich Elektrotechnik und Informationstechnik, Maschinenbau oder Mechatronik
  • Grundwissen in Robotik, Regelungstechnik und Systemtheorie
  • Gute Programmierkenntnisse in C/C++, Python, Matlab
  • Gute Fähigkeiten in CAD-Design (SolidWorks usw.)
  • Erfahrung mit 3D-Druck

Kontakt:
Dennis Knobbe
dennis.knobbe@tum.de
+49 (89) 289 - 29412

Optimal Sensor Configuration

Optimal Sensor Configuration

Sensor fusion and filtering is an important topic in signals and systems as well as robotics. More specifically, combining sensors of different types enables one for further robot analysis and devise advanced control strategies. However, in order to get optimal technical and computation costs, the number of sensors has to be carefully chosen. Moreover, for some sensors such as accelerometers whose output signal depends on their location, the sensor placement needs to be optimally chosen, as well. Within the framework of these criteria, we seek to formulate an algorithm for proper selection of sensors and analyze the method optimality, in this thesis.

Who Are You?

  • An enthusiastic mechanical/electrical/robotic master student
  • Interested in signals and systems analysis and optimization problems
  • Familiar with sensor technologies
  • Familiar with Matlab, Simulink and python

Contact

ali.baradaran@tum.de

Human modeling

3D-Modellierung und Echtzeitvisualisierung der Muskelverformung

Es gibt heutzutage ja zahlreiche 3D computergraphische Modelle für muskuloskelettale Systeme, die sind aber leider entweder statisch mit anatomisch korrekter Muskelabbildung oder beweglich mit aber hohem Abstraktionsgrad für Muskelrepräsentation. Für ein 3D-Modell mit sowohl anatomisch korrekter Muskeldarstellung als auch diversen Bewegungsfreiheitsgrade ist es die Muskelverformung während der Bewegungen eine Herausforderung (siehe Video).

Wir erwarten von Ihnen
- Grundkenntnis der Mechanik und der Mehrkörpersysteme (Kinematik, Statik)
- Objektorientierte Programmierung (C++ oder C#)
- Interesse an Visualisierung der Anatomie und Entwicklung von Computerspielen

Wir bieten
- Gut gestalteter Arbeitsplatz
- Fachliche Betreuung

Kontakt:
M.Sc. M.Sc. Tingli Hu
tingli.hu@tum.de