Master Thesis Long Term Human Action Prediction using Large Language Models

Join Bosch - Master Thesis on Long Term Human Action Prediction Using Large Language Models

At Bosch, we are shaping the future with high-quality technologies and services that inspire and enhance lives. We deeply value our promise to our associates to grow, enjoy our work, and motivate one another. The Robert Bosch GmbH eagerly awaits your application!

Job Description

Effective robot operations in human-populated settings demand the prediction of human actions in complex environments. While recent advances in Natural Language Processing (NLP) and Large Language Models (LLMs) show potential, most research is limited to single human scenarios. This master thesis focuses on a novel approach to integrate humans and their semantic relationships into environmental representations, aiming at recognizing and predicting long-term actions of multiple humans using visual data and LLMs.

During your Master thesis, you will develop an innovative model for recognizing and predicting long-term human actions based on Large Language Models (LLMs). This model will be pivotal for downstream planning components, thereby accelerating the testing and deployment of advanced robots and other autonomous systems.

Your contributions will enhance the interpretability of long-term human action predictions by extending the model to provide explanations for its decisions. Furthermore, you will evaluate the model using open-source datasets, benchmark it against state-of-the-art approaches, apply it to downstream tasks (e.g., robot TAMP), and demonstrate its effectiveness in real-world applications.

Qualifications

Education:

Master studies in Computer Science, Electrical Engineering, Physics, or comparable fields with excellent 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 and open-minded.
• Ready to dive into cutting-edge research in machine learning, robotics, and autonomous driving applications.

Languages:

Fluent in English; German is a plus.

Additional Information

Start: According to prior agreement

Duration: 6 months

A requirement for this thesis is enrollment at a university. Please attach your CV, transcript of records, examination regulations, and if applicable, a valid work and residence permit.

Diversity and inclusion are core values at Bosch. We welcome all applications irrespective of gender, age, disability, religion, ethnicity, or sexual identity.

Need further information about the job?

Contact Yuchen Liu (Functional Department) at +49 711 811 6877

#LI-DNI.

Company Information

Company Name: Bosch Group

Job Title: Master Thesis Long Term Human Action Prediction Using Large Language Models