Design optimization of soft pneumatic actuators using genetic algorithms

Abstract

Recent trends in bioinspired robotic systems are paving the way for robots to become part of our daily lives. Soft robots, which are widely recognized as the next generation of human-friendly robots, are such a trend. Soft robots are generally more adaptable, more flexible, and safer than their rigid-link counterparts. Research in soft robotics has produced a broad variety of interesting solutions for all sorts of applications ranging from medical engineering and rehabilitation over exploration to industrial handling. This diversity together with a general lack of experience in designing with soft materials has contributed to a design flow that is highly empirical in nature. For soft robots to become mass-producible in the near future, more general design and modeling methods are needed. In this article, we present a method for the design optimization of soft robot modules that effectively combines finite element modeling and gradient-free optimization. To demonstrate the feasibility of the approach, a soft pneumatic actuator is designed and optimized. Performance analysis of the optimization scheme shows the robustness of the solution in the given case.