Simulation-based optimization approach for explicit forward gait prediction

Thomas Bonis , Nicolas Pronost (1) , Gilmar F Santos , Christof Hurschler , Saida Bouakaz

1 SAARA - Simulation, Analyse et Animation pour la Réalité Augmentée

Accurate and specific predictive numerical simulation of the human gait can help in many clinical routines. Predictive methods often track modifications applied to a reference motion but that usually do not take into account the characteristics and the stability of the predicted motion. We propose an approach that includes a cost function, computed on the predicted motion, which optimization preserves these concerns. Experimental studies on subjects with different walking patterns confirmed that our method preserves the characteristics of the gait.

Mots clés: Human gait simulation; Reinforcement learning; Knee brace; Explicit forward simulation; CMA-ES

Domaines: Modélisation et simulation

Thomas Bonis, Nicolas Pronost, Gilmar F Santos, Christof Hurschler, Saida Bouakaz. Simulation-based optimization approach for explicit forward gait prediction. 14th ACM SIGGRAPH Conference on Motion, Interaction and Games, Nov 2021, Lausanne, Switzerland. ⟨hal-03542688⟩