Thesis: Data set generation for trustworthy AI*
Thesis: Data set generation for trustworthy AI*
Waldkirch (bei Freiburg), DE, 79183
Waldkirch (bei Freiburg), DE, 79183
Summer Semester 2025 - fixed-term for 3-6 months
In the context of machines and robots, people are exposed to specific dangers. Artificial intelligence has the potential to revolutionize industrial safety solutions, with proof and assurance of high reliability being crucial. The goal of this work is to develop a method for creating a curated dataset for AI training and validation, ensuring that robot applications can be designed safely for humans.
YOUR TASKS:
- Design and develop a measurement setup for capturing hands and arms using various 3D-TOF sensors
- Research typical movement patterns and protective equipment in industrial environments
- Record a comprehensive and systematic dataset and link it with metadata in a data management system
- Develop algorithms for automatic data segmentation
- Create methods for data augmentation, using segmentation to generate enhanced training data
- Collaborate daily with AI experts from pre-development and contribute to a strategic project initiative
YOUR PROFILE:
- Master's degree program in computer science, robotics, or a related field
- Expertise in deep learning, machine learning, and integration of common open-source libraries
- Strong programming skills, ideally in Python or C++
- Comprehensive understanding of image processing and working with 2D and 3D data
- You have experience & enjoy working with mechanical setups and electronic integration of sensors
- Systematic and structured way of thinking and working
- Creativity in finding solutions and an innovative spirit round off your profile
YOUR APPLICATION:
- We are looking forward to your online application
- Sarah Disch
- Job-ID 36312
- All applications will be treated confidentially
*At SICK, we see people, not gender.
We put great emphasis on diversity, reject discrimination and do not think in categories such as gender, ethnicity, religion, disability, age or sexual identity.
Stichworte: Intern, Internship, Abschlussarbeit
Summer Semester 2025 - fixed-term for 3-6 months
In the context of machines and robots, people are exposed to specific dangers. Artificial intelligence has the potential to revolutionize industrial safety solutions, with proof and assurance of high reliability being crucial. The goal of this work is to develop a method for creating a curated dataset for AI training and validation, ensuring that robot applications can be designed safely for humans.
YOUR TASKS:
- Design and develop a measurement setup for capturing hands and arms using various 3D-TOF sensors
- Research typical movement patterns and protective equipment in industrial environments
- Record a comprehensive and systematic dataset and link it with metadata in a data management system
- Develop algorithms for automatic data segmentation
- Create methods for data augmentation, using segmentation to generate enhanced training data
- Collaborate daily with AI experts from pre-development and contribute to a strategic project initiative
YOUR PROFILE:
- Master's degree program in computer science, robotics, or a related field
- Expertise in deep learning, machine learning, and integration of common open-source libraries
- Strong programming skills, ideally in Python or C++
- Comprehensive understanding of image processing and working with 2D and 3D data
- You have experience & enjoy working with mechanical setups and electronic integration of sensors
- Systematic and structured way of thinking and working
- Creativity in finding solutions and an innovative spirit round off your profile
YOUR APPLICATION:
- We are looking forward to your online application
- Sarah Disch
- Job-ID 36312
- All applications will be treated confidentially
*At SICK, we see people, not gender.
We put great emphasis on diversity, reject discrimination and do not think in categories such as gender, ethnicity, religion, disability, age or sexual identity.
Stichworte: Intern, Internship, Abschlussarbeit