Master Thesis in Vision-Language-Action Models for Robotic Manipulation

Robert Bosch Group; Renningen; Vor Ort; EUR 40.000 - 60.000; Vollzeit

Zusammenfassung

A leading engineering company in Germany seeks a Master's student for a thesis on Vision‑Language‑Action models in robotic manipulation. Candidates should have a background in relevant fields and experience with Python and PyTorch. The role involves exploring VLA methods, implementing baselines, and developing data pipelines. The position offers a 6-month duration and requires university enrollment.

Qualifikationen

• Enrollment at university required for the thesis.
• Good grades in relevant fields.
• Structured work approach with good communication skills.

Aufgaben

• Explore recent VLA methods and define evaluation criteria.
• Implement and benchmark strong baselines for tasks.
• Build data pipeline for training and evaluation.
• Develop prototypes for action decoding strategies.

Kenntnisse

Python

PyTorch

Computer Vision

Git

Clean Code

Ausbildung

Master studies in Computer Science, Robotics, Electrical Engineering, Mechanical Engineering

Tools

ROS/ROS2

Weights & Biases

Isaac

MuJoCo

Jobbeschreibung

Master Thesis in Vision‑Language‑Action Models for Robotic Manipulation

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!

In this Master’s thesis, you will work with Vision‑Language‑Action (VLA) models, which enable robots to understand a scene, follow natural‑language instructions, and execute reliable, interpretable actions in the environment.

Responsibilities

• Explore recent VLA methods and define evaluation criteria for accuracy, robustness, and data efficiency.
• Implement and benchmark strong baselines for manipulation tasks.
• Build the necessary data pipeline for training and evaluation.
• Develop prototypes for action decoding strategies.

Requirements

• Education: Master studies in Computer Science, Robotics, Electrical Engineering, Mechanical Engineering or comparable with good grades.
• Experience and Knowledge: Experienced in Python and PyTorch; background in computer vision, LLMs / language modeling, imitation or reinforcement learning, or multimodal learning; good software engineering practices (Git, clean code, reproducible experiments, documentation); familiarity with distributed training frameworks, ROS/ROS2, basic robot kinematics/control, simulators (e.g., Isaac, MuJoCo), data processing at scale, and experiment tracking (e.g., Weights & Biases) is a bonus.
• Personality and Working Practice: You have a curious and proactive personality, coupled with a structured work approach, enabling you to drive your own experiments and effectively communicate results.

Start: according to prior agreement

Duration: 6 months

Requirement for this thesis is 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?
Babu Harisankar (Functional Department)
[phone]