PhD position in Interactive Alignment for Human-Robot Interaction

VU Amsterdam offers a 4-year full-time PhD position, in collaboration with Idiap Research Institute Switzerland, on interactive (knowledge) alignment for human-robot interaction. This position is funded by the Dutch Research Council (NWO).

PhD position in Interactive Alignment for Human-Robot Interaction

Your function

This project tackles a fundamental challenge in human-robot interaction: how can we align human and robot mental models for better collaboration? Rather than treating alignment as a one-time design problem, in this project we approach it as a continuous, interactive process.

You will specifically focus on “proactive knowledge transmission” strategies: enabling robots to “self-disclose” relevant information to users at the right moment, in the right way. This includes designing learning algorithms that allow robots to decide what to communicate, when to communicate, and how to communicate—balancing transparency with cognitive load and task efficiency.

The research combines reinforcement learning, human-in-the-loop feedback, and insights from psychology to create adaptive, user-aware robot behavior. You will validate your methods through interactive experiments using real robotic platforms in collaborative tasks such as assembly and cooking.

This position is embedded in the Social AI group and contributes to a larger Dutch-Swiss collaboration on human–AI alignment. You will work at the intersection of machine learning, human-robot interaction, and cognitive science, with opportunities for international collaboration and interdisciplinary impact.

We are looking for candidates with strong technical skills, curiosity about human-centered AI, and an interest in shaping how humans and intelligent systems work together.

The candidate will mainly supervised by dr. Kim Baraka, and will involve a collaboration with Swiss PI dr. Emmanuel Senft.

Your duties

• Develop novel algorithms for human-robot alignment with a focus on transparency
• Conduct extensive user studies in a lab setting
• Develop software on two robot platforms, the Franka robot arm and the Stretch mobile manipulator
• Publish scientific results at international scientific conferences (e.g., HRI, AAMAS, CHI) and journals (THRI, Frontiers in Robotics and AI, Science Robotics)

Your profile

We are looking for candidates with the following profile:

• Master's degree in Artificial Intelligence, Robotics, Computer Science, or related fields
• Excellent programming and algorithm development skills
• Strong basis in machine learning (ideally, prior exposure to reinforcement learning)
• Prior experience working with robotic platforms, at least in simulation
• Willingness to step outside of their own discipline to solve complex problems that cut across bodies of knowledge in different fields
• Experience conducting user studies and analyzing human data (not required but preferred)
• A good team spirit and willingness to collaborate across institutions

We realise that each individual brings a unique set of skills, expertise and mindset. Therefore we are happy to invite anyone who recognises themselves in the profile to apply, even if you do not meet all the requirements.

What do we offer?

• A salary of € 3.059,00 (scale 85-0) gross per month in the first year, increasing to € 3.881,00 (scale 85-3) in the fourth year, on a full-time basis (UFO profile PhD candidate)
• An employment contract of initially 18 months, with the possibility of extension to a total of 4 years

About us

About the department

The Department of Computer Science at Vrije Universiteit Amsterdam is an internationally recognised centre of excellence, advancing the full spectrum of Computer Science in both research and education.