PhD Opening: Reinforcement learning in human neuromusculoskeletal models for the control of human-inspired musculoskeletal r...

We’re seeking for motivated candidates that are interested in developing computer models of the composite human neuro-muscular system that combine detailed musculoskeletal geometries, muscle-tendon models and neural control pathways (e.g., CPG-like and reflexive). Moreover, candidates will be required to develop reinforcement learning techniques to teach such neuromuscular models to execute a broad range of movement as well as performing the “sim2real” step for the control of physical musculoskeletal robots in the real world, i.e., use cass include neuromuscular model-based control of robotic legs and arms for both autonomous and prosthetic applications.

If you’re excited by all this, we encourage you to apply.

The opening:
In this project, you will develop:

• Detailed, large-scale computer models of the composite human neuro-musculo-skeletal system (NMS) that incorporate neural control strategies (i.e., CPG-lie and reflex pathways), muscle-tendon units with variable stiffness and damping properties and 3D musculoskeletal geometries. Info.
• Novel reinforcement learning (RL) strategies to teach NMS models to execute a broad repertoire of movemets in presence of external disturbances. Info.
• Simulation-to-real-world transfer, where NMS model control policies acquired via RL are flashed on a physical robot to operate in the real world.

Your tasks will be:
Your core tasks will include using the MyoSuite framework to:

• Development of computer models of the musculoskeletal system incorporating neural control pathways
• Train NMS model control policies via RL

Your seconday tasks will include:

• Using learned NMS model control policies to control real-world robotic legs and arms.

About the Lab
The NeuBotics Lab is a multidisciplinary team at the forefront of neuromechanics and assistive robotics. Our work bridges neuroscience, biomechanics, and robotics to develop real-time models of joint biomechanics and adaptive control strategies for wearable exoskeletons and bionic limbs. You’ll be part of a dynamic, collaborative environment that values innovation, rigor, and translational impact.

• As a PhD candidate at UT, you will be appointed to a full-time position for four years, with a qualifier in the first year, within a very stimulating and exciting scientific environment.
• Your salary and associated conditions are in accordance with the collective labour agreement for Dutch universities (CAO-NU).
• You will receive a gross monthly salary ranging from € 3059,- in the first year, increasing to € 3881,- in the fourth year.
• There are excellent benefits including a holiday allowance of 8% of the gross annual salary, an end-of-year bonus of 8.3%, and a solid pension scheme.
• A minimum of 232 leave hours in case of full-time employment based on a formal workweek of 38 hours. A full-time employment in practice means 40 hours a week, therefore resulting in 96 extra leave hours on an annual basis.
• Free access to sports facilities on campus.

Why Join Us?

• Be part of a cutting-edge research project.
• Collaborate with leading researchers across Europe.
• Work in a vibrant academic environment at one of the Netherlands’ top technical universities.
• Access to state-of-the-art lab computational and robotics facilities.