Reality-assisted evolution of soft robots through large-scale physical experimentation: a review

TL;DR

This review discusses a framework called reality-assisted evolution that combines virtual simulations and large-scale physical experiments to enhance the design process of soft robots, leveraging real-world data for iterative improvement.

Contribution

It introduces the concept of reality-assisted evolution, integrating model-based and model-free approaches with physical experimentation to improve soft robot design.

Findings

Large-scale physical experimentation enables testing many robot designs.

Data-driven models improve through real-world experimental data.

Ground-truth data guides virtual optimization and design refinement.

Abstract

In this review we introduce the framework of reality-assisted evolution to summarize a growing trend towards combining model-based and model-free approaches to improve the design of physically embodied soft robots. In silico, data-driven models build, adapt and improve representations of the target system using real-world experimental data. By simulating huge numbers of virtual robots using these data-driven models, optimization algorithms can illuminate multiple design candidates for transference to the real world. In reality, large-scale physical experimentation facilitates the fabrication, testing and analysis of multiple candidate designs. Automated assembly and reconfigurable modular systems enable significantly higher numbers of real-world design evaluations than previously possible. Large volumes of ground-truth data gathered via physical experimentation can be returned to the virtual environment to improve data-driven models and guide optimization. Grounding the design process in physical experimentation ensures the complexity of virtual robot designs does not outpace the model limitations or available fabrication technologies. We outline key developments in the design of physically embodied soft robots under the framework of reality-assisted evolution.