This PhD position at the University of Twente's NeuBotics Lab focuses on developing advanced computer models of the human neuromusculoskeletal (NMS) system for the control of human-inspired musculoskeletal robots. The project aims to combine detailed musculoskeletal geometries, muscle-tendon models, and neural control pathways (such as central pattern generators and reflexive mechanisms) to create large-scale, realistic simulations. A key aspect of the research involves designing novel reinforcement learning (RL) strategies to teach these NMS models to perform a wide range of movements, even in the presence of external disturbances.

The successful candidate will use the MyoSuite framework to develop and train NMS model control policies via RL, and will also work on transferring these learned policies from simulation to real-world robotic systems, including robotic legs and arms for both autonomous and prosthetic applications. Secondary tasks include applying these control policies to physical robots, contributing to the development of wearable exoskeletons and bionic limbs. The NeuBotics Lab is a multidisciplinary team at the forefront of neuromechanics and assistive robotics, bridging neuroscience, biomechanics, and robotics to create adaptive control strategies for real-time joint biomechanics.

The lab offers a collaborative and innovative environment, with strong connections to UT research institutes such as Mesa+ Institute, TechMed Center, and Digital Society Institute. Applicants are expected to have expertise in computer modeling, reinforcement learning, robotics, biomechanics, or related fields, and should be proficient in English. The application process requires a video, cover letter, CV, and references, with screening as part of the procedure. The deadline for applications is November 23, 2025, with interviews scheduled for the week of December 1, and the expected start date no later than February 1, 2025.