Toward Shape Optimization of Soft Robots

Thomas Morzadec (1) , Damien Marchal (2, 1) , Christian Duriez (1)

1 DEFROST - Deformable Robots Simulation Team
2 CNRS - Centre National de la Recherche Scientifique

In this paper we present our work on shape optimization for soft robotics where the shape is optimized for a given soft robot usage. To obtain a parametric optimization with a reduced number of parameters, we rely on an approach where the designer progressively refines the parameter space and the fitness function until a satisfactory design is obtained. In our approach, we automatically generate FEM simulations of the soft robot and its environment to evaluate a fitness function while checking the consistency of the solution. Finally, we have coupled our framework to an evolutionary optimization algorithm, and demonstrated its use for optimizing the design of a deformable leg of a locomotive robot.

Domaines: Modélisation et simulation

Thomas Morzadec, Damien Marchal, Christian Duriez. Toward Shape Optimization of Soft Robots. RoboSoft 2019 - IEEE International Conference on Soft Robotics, Apr 2019, Séoul, South Korea. ⟨hal-02078776v2⟩