Master Thesis Long Term Human Action Prediction using Large Language Models

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 GmbHis looking forward to your application!

Job Description

Predicting human actions in complex environments is essential for effective robot operations, especially in human-populated settings. Recent advances in Natural Language Processing (NLP) and Large Language Models (LLMs) have shown great potential in tackling these challenges. Despite progress, most studies focus on single human scenarios, with limited research on group actions and human-human interactions. This master thesis aims to develop a novel approach to integrate humans and their semantic relationships into environmental representations, enabling the recognition and prediction of long-term actions of multiple humans using visual data and LLMs.

• During your Master thesis, you will focus on developing a cutting-edge recognition and prediction model for long-term human actions based on Large Language Models (LLMs) to be used by downstream planning components, and accelerating the testing and deployment of advanced robots and other autonomous systems.
• You will make recognizing and predicting long-term human actions more interpretable. You will extend the model to provide explanations for its decisions, shedding light on the reasoning behind certain actions.
• Last but not least, you will evaluate the model with open-source datasets, benchmark against state-of-the-art approaches, apply it to downstream tasks (e.g., robot TAMP), and demonstrate on real-world applications.

Qualifications

• Education: Master studies in the field of Computer Science, Electrical Engineering, Physics or comparable with very good grades
• Experience and Knowledge: strong knowledge in Machine Learning, computer vision, and/or robotics, practical experience with Python, PyTorch, TensorFlow, etc.
• Personality and Working Practice: eager to learn, open-minded, ready to dive into a topic at the forefront of machine learning research, robotics, and autonomous driving applications
• Languages: fluent in English, German is a plus

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.

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?
Yuchen Liu (Functional Department)
+49 711 811 6877

#LI-DNI

Summary

• Type: Full-time
• Function: Research