Project Overview

Project Code: ED 08

Project name:

Adaptive Robot-Applications through AI-enabled Perception

TUM Department:

ED - Mechanical Engineering

TUM Chair / Institute:

Institute for Machine Tools and Industrial Management (iwb)

Research area:

Industrial Robotics

Student background:

Computer EngineeringComputer ScienceComputer Science/ InformaticsMechanical Engineering

Further disciplines:

Participation also possible online only:

Planned project location:

Technical University of Munich
Institute for Machine Tools and Industrial Management (iwb)
Boltzmannstraße 15
Gebäude 1, Tor 20 Einfahrt Maschinenwesen Ost
85748 Garching b. München

Project Supervisor - Contact Details


Title:

M.Sc.

Given name:

Julian

Family name:

Müller

E-mail:

julian.mueller@iwb.tum.de

Phone:

+49 89 289 154 94

Additional Project Supervisor - Contact Details


Title:

M.Sc.

Given name:

Celina

Family name:

Dettmering

E-mail:

celina.dettmering@iwb.tum.de

Phone:

Additional Project Supervisor - Contact Details


Title:

Given name:

Family name:

E-mail:

Phone:

Project Description


Project description:

Project Description

The principal objective of this research project is to enhance the autonomy of industrial robot systems, thereby increasing the flexibility and scalability of automation solutions. The objective is to generate and utilise synthetic sensor data, which robot systems can then learn visual and tactile perception from in a safe and cost-effective manner. The utilisation of sophisticated AI algorithms guarantees that the expertise and abilities acquired through this process can be effectively deployed in practical applications. The integration of conventional regulatory and control methodologies ensures the development of dependable systems capable of autonomous recognition and adaptation to evolving environmental conditions. The enhanced perception capabilities enhance the autonomy of robot systems, enabling the execution of a broader range of tasks without manual intervention. Consequently, even intricate operations can be automated economically, thereby alleviating the challenges posed by the scarcity of skilled labour in Bavaria as a business hub.

Student Tasks

Depending on the student's motivation, skills, and interests, the following tasks are possible:

- Program a collaborative robot in a digital environment and test it in real-world applications.
- Design gripping systems for a robot's end effector.
- Manufacture gripping systems using additive manufacturing (3D printing).
- Evaluate the gripping capabilities of robotic systems.
- Use 3D cameras and other sensors to virtualize production environments.
- Use computer vision systems to enable gesture detection for codeless robot programming.
- Synthesize image datasets from virtual environments for AI training.
- Deploy orchestrated applications using containerization in production environments.

These tasks provide opportunities for students to apply their skills and explore their interests in robotics and technology.

Possible Learnings

The learning outcomes associated with the completion of specific tasks may vary. Depending on the content of the tasks, the following skills may be developed during the course of work:

- Programming in Python or C++ (e.g. in ROS)
- Developing and testing algorithms
- Understanding robotics and automation
- Designing and 3D printing components
- Working with sensors and 3D cameras
- Applying computer vision techniques
- Training AI models
- Simulating robotic movements
- Using containerization (e.g., Docker)

Working hours per week planned:

35

Prerequisites


Required study level minimum (at time of TUM PREP project start):

2 years of bachelor studies completed

Subject related:

The following technical skills would be beneficial:

- Basic programming skills
- Affinity towards robotic systems
- Interest in working with AI
- Inclination towards tinkering with technology

Other:

Further favorable skills are:

- Problem-solving abilities
- Hands-on mentality
- Eagerness to tackle new challenges
- Structured and independent approach to tasks

  • Keine Stichwörter