PhD in Embodied AI for Continuous Human-Like Learning

Are you interested in developing cutting-edge generative AI that is inspired by how the brain works? In this PhD project you will design an artificial agent that executes haptic manipulation tasks as a human would, by leveraging embodied intelligence. This research requires a multidisciplinary approach, based on probabilistic (Bayesian) machine learning, soft robotics, and neuromorphic engineering. Please see this video (https://youtu.be/QYbcm6G_wsk) on Natural Artificial Intelligence for more information about our research.



Humans learn real-world haptic tasks through interaction with their environment. For example, through experience, children quickly learn to manipulate objects and solve physical puzzles. We continuously learn from sensory feedback, and actively seek sensory observations that inform our model of the world. In this PhD project, you will work towards the first integrated embodied AI system capable of human-like haptic exploration. This does not imply perfection, but behaviour that is relatable to a human user.

Your main task will be to design continuous learning algorithms for haptic exploration, based on a leading physics/neuroscientific theory about computation in the brain, the Free Energy Principle (FEP). You will implement your algorithms on a real-world (physical) soft-robotic system that simultaneously serves as a research platform and as a demonstrator.

This PhD project is funded by the EMDAIR program, which stimulates exploratory multi-disciplinary AI research. Therefore the project has a strong interdisciplinary character. You will work in the BIASlab team in the Electrical Engineering department at TU/e. This lab focuses its research activities on transferring FEP to practical use in engineered devices. During this project you will closely collaborate with other BIASlab researchers, as well as with project team members at the Reshape lab and the Neuromorphic Engineering lab in the Mechanical Engineering department.

Key areas of interest include Bayesian machine learning, probabilistic graphical models (factor graphs), soft robotics, neuromorphic computation and software development.

Requirements:

• A master's degree in electrical engineering, physics, robotics, computer science or similar (this is mandatory).
• A record that shows specific interest in any or more of the following fields: (Bayesian) machine learning, sensorimotor learning, intelligent robotics.
• Good written and spoken command of English (C1 level or better).
• A team player attitude, willingness to work hard and know how to have fun at it.

Salary Benefits:

A meaningful job in a dynamic and ambitious university, in an interdisciplinary setting and within an international network. You will work on a beautiful, green campus within walking distance of the central train station. In addition, we offer you:

• Full-time employment for four years, with an intermediate evaluation (go/no-go) after nine months. You will spend 10% of your employment on teaching tasks.
• Salary and benefits (such as a pension scheme, paid pregnancy and maternity leave, partially paid parental leave) in accordance with the Collective Labour Agreement for Dutch Universities, scale P (min. €2,872 max. €3,670).
• A year-end bonus of 8.3% and annual vacation pay of 8%.
• High-quality training programs and other support to grow into a self-aware, autonomous scientific researcher. At TU/e we challenge you to take charge of your own learning process.
• An excellent technical infrastructure, on-campus children's day care and sports facilities.
• An allowance for commuting, working from home and internet costs.
• A Staff Immigration Team and a tax compensation scheme (the 30% facility) for international candidates.

38 hours per week

De Rondom 70