Thesis Opportunity- Reducing the need for robot demonstrations in VLA

What the Master Thesis is about/background to the problem to investigate

Vision Language Action models (VLA) show impressive results on many robotics tasks like picking and placing clothes. However, training a VLA requires huge amount of robot demonstrations and even fine tuning the action decoder step for a new robot requires a lot of demonstrations.

Since collecting real robot demonstrations is highly time-consuming, reducing the number of required demonstrations is highly beneficial. This can be achieved in several ways, for example through the use of simulation environments. This thesis investigates methods for reducing the need for real robot demonstrations.

The master thesis work focuses on the following/example of research questions

• Can hand-eye and/or gripper calibration be used to switch between different setups without any additional training?
• Does the existing VLA models using depth require less demonstrations compared to the models only using RGB?
• Can the depth be used in a different way to reduce the number of demonstrations needed?
• To what extent can simulators like MUJOCO be used instead of real robot demonstrations?

Prerequisites

You should have some familiarity with modern computer vision architectures and be motivated to dive deeper. You should be comfortable programming in Python.

Contact

For more information about the position, contact:

Anders Moe, Software Developer, anders.moe@sick.se

We warmly welcome your application — please submit it no later than October 25th.

SICK is a world-leading supplier of sensors and sensor solutions for industrial applications. We’re part of SICK AG — a global leader in sensor technology with 10,000 employees across 50 countries and headquarters in Freiburg, Germany. Together, we build technology that makes industries more efficient, intelligent, and safe.

As a Machine Vision Innovation Center, SICK Linköping develops advanced AI-powered software that drives the future of both manufacturing and logistics automation. Whether it’s helping robots pick the right item or enabling high-precision quality control with 2D and 3D vision, our solutions bring clarity, speed, and smart decision-making to complex industrial environments — all driven by a dedicated team of 100 colleagues.

We are very proud of being a healthy and attractive workplace. We have consistently been recognized as one of the best workplaces in Sweden according to the Great Place to Work survey. We actively work to reduce our climate footprint and engage in various initiatives to contribute to society and enhance diversity at our workplace.