Modeling pathological gait resulting from motor impairments: compare and combine neuromechanical simulation and machine learning approaches

Within this project we seek to develop machine learning methods for the modelling of pathological human locomotion. This is a collaborative Sinergia project funded by the Swiss National Science Foundation. The overall goal of the project is to develop, through a combination of machine learning and neuromechanical simulation, accurate models of human locomotion. In addition to the DMML group the project partners are Stephane Armand (University of Geneva, Kinesiology laboratory) and Auke Ijspeert (Biorobotics laboratory, EPFL, BIOROB). The project will (1) model pathological gaits resulting from motor impairments such as cerebral palsy, and (2) compare and combine neuromechanical simulation and machine learning approaches for gait analysis. It brings together expertise on pathological gait, neuromechanical simulation models, machine learning, coupled with a unique collection of relevant real world data.

Human locomotion is a highly complex dynamical system and learning locomotion models is a challenging task. Pathological locomotion modelling is even more challenging due to the limited availability of training data. This project will address these challenges by bringing together machine learning and neuromechanical simulation. On the machine learning side we will explore a number of research problems such as learning of dynamical systems using conditional generative models, learning with simulated data, learning, tunning and improving simulators. A simulator is a model of domain knowledge and as such it can be imprecise and incomplete. We are particularly interested in the tight integration of simulation and learning and their interactin in a virtuous cycle with each one improving the other.