Thesis in Multi-Modal Predictions for End-to-End Architectures Robert-Bosch-Campus 1, 71272 Renningen, Germany Full-time Robert Bosch GmbH Company Description At Bosch, we shape the future by inventing high-quality technologies and services that spark enthusiasm and enrich people’s lives. Our promise to our associates is rock-solid: we grow together, we enjoy our work, and we inspire each other. Join in and feel the difference. The Robert Bosch GmbH is looking forward to your application Job Description In the context of autonomous driving, the need for accurate predictions is paramount. Achieving more robust predictions is crucial for ensuring the safety and efficiency of autonomous vehicles. By accurately predicting the future movements of surrounding objects and other vehicles, autonomous driving systems can proactively plan and adapt their actions, thereby reducing the risk of accidents and improving overall driving experience. Additionally, the ability to provide feedback from predictions back to perception allows the system to continuously learn and improve its overall end-to-end capabilities, leading to enhanced decision-making in dynamic environments. During your thesis you will address the critical need for predictions in autonomous driving systems. To this end, you will aim to improve the coupling between predictions and perception (i.e. multi-object detection and tracking). Query-based approaches have been receiving a lot of attention during the last years, particularly for their performance and easy integration within end-to-end architectures. Current architectures fatigue to have a proper flow of information from downstream tasks to the perception models of the architecture. Within this thesis you will explore methods for achieving this, also considering multi-modal predictions models. Qualifications Education: studies in the field of Computer Science or comparable Experience and Knowledge: in data analysis and visualization; proficiency in Python and tools like Pandas, NumPy, and Matplotlib; knowledge of deep learning frameworks; familiarity with TensorFlow, Keras, or PyTorch; understanding of computer vision; experience with OpenCV or similar libraries; familiarity with autonomous systems (e.g. automated driving) Personality and Working Practice: you are eager to learn and able to tackle complex challenges, develop innovative solutions, clearly articulate technical concepts to both technical and non-technical audiences Languages: fluent in English Additional Information Start: according to prior agreement Duration: 6 months Requirement for this thesis is the enrollment at university. Please attach your CV, transcript of records, examination regulations and if indicated a valid work and residence permit. You are almost finished with your Bachelor's degree and would like to gain some practical experience before embarking on your next academic adventure with a Master's degree? Then you fit in perfectly well with our PreMaster Programm Take a look at our vacancies here. Diversity and inclusion are not just trends for us but are firmly anchored in our corporate culture. Therefore, we welcome all applications, regardless of gender, age, disability, religion, ethnic origin or sexual identity. Need further information about the job? Joerg Wagner (Functional Department) 49 711 811 35050 LI-DNI