Thesis in the field of industrial data analysis and automation

Economic, precise, safe and energy-efficient: Bosch Rexroth's drive and control technology moves machines and systems of all sizes. Under the Rexroth brand, innovative components, tailor-made system solutions and services are created for mobile applications, plant construction and engineering as well as factory automation. Bosch Rexroth AG is looking forward to your application!

Type of employment: Limited Working time: Full time Place of work: Horb am Neckar We are looking for a:n Student:in for a final thesis (Bachelor or Master) in one of the following topics:

detection and extraction of relevant component views in technical drawings: Building a training and evaluation data set for the localization of relevant views in technical drawings as well as training, comparison and comprehensive evaluation of suitable detection models and model architectures under real industrial boundary conditions. OR Fusion of drawing and sensor data for variant identification: Analysis and development of a fusion logic for variant identification by combining SOLL and IST data taking into account plausibility, conflicts and uncertainties, followed by prototypical implementation and experimental evaluation based on real or simulated case studies. OR Multimodal detection of component features in Brownfield environments: Investigation of camera-based 2D/3D detection methods and extraction of relevant component features from RGB and depth data under analysis of the influence of illumination, distance and perspective, the development of robust evaluation logics and their experimental validation in the industrial environment. OR Automated detection of assembly-critical features from technical drawings: Analysis of technical inventory drawings for automated transfer to image data and for the localization and extraction of relevant views and parameters. Various approaches, including rule-based methods, classic image processing, YOLO, OCR and multimodal models, are compared and examined in terms of their robustness in different drawing qualities and training data. OR Development and application of a model for annotation of technical documents: Sighting and structuring of technical data for developing an annotation scheme and creating a quality-secured data set, including analysis of label consistency and data quality, to provide baselines for downstream AI models.

Education: You study in the field of computer science, production technology, industrial engineering, mechatronics or a comparable course of study. Know-How: Good knowledge in Python. Experiences: Funded interest and basic understanding in machine learning, computer vision, data processing and automation. Working methods: An independent, structured and analytical method rounds off your profile Languages: Very good German knowledge. Start: From September 2026 Duration: 5 - 6 months

Work-Life Balance: Flexible work in terms of time, location and work model. Health and Sports: Wide range of health and sports activities. Childcare: childcare services. Employee discounts: Advantages for employees. Free space for creative work: free space for creative work. Social counselling and care: Social counselling and brokerage services.

The future personnel department or the department will be happy to inform you about the individual service catalogue. .