From Bioinspiration to Computer Generation: Developments in Autonomous Soft Robot Design. (17th October 2021)

• Record Type: Journal Article
• Authors: Pinskier, Joshua; Howard, David
• Is Part Of: Advanced intelligent systems. Volume 4:Number 1(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2021-10-17
• Subjects: autonomous design -- material robotics -- soft robotics; Artificial intelligence -- Periodicals; Robotics -- Periodicals; Control theory -- Periodicals; 006.3
• DOI: 10.1002/aisy.202100086
• Languages: English
• ISSNs: 2640-4567

Abstract

Abstract : The emerging field of soft robotics presents a new paradigm for robot design in which "precision through rigidity" is replaced by "cognition through compliance." Lightweight and flexible, soft robots have vast potential to interact with fragile objects and navigate unstructured environments. Like octopuses and worms in nature, soft robots' flexible bodies conform to hard objects and reconfigure for different tasks, delegating the burden of control from brain to body through embodied cognition. However, because of the lack of efficient modeling and simulation tools, soft robots are primarily designed by hand. Typically, hard components from rigid robots or living creatures are heuristically substituted for comparable soft ones. Autonomous design and manufacturing methodologies are urgently required to produce bespoke, high‐performing robots. Currently, design methodologies exist between simple but realistic parametric optimizations, and evolutionary algorithms which simulate morphology and control coevolution. To find high‐performing designs, novel high‐fidelity simulators and high‐throughput manufacturing and testing processes are required to explore the complex soft material, morphology and control landscape, blending simulation, and experimental data. This article reviews the state of the art in autonomous soft robotic design. Existing manual and automated designs are surveyed and future directions to automate soft robot design and manufacturing are presented. Abstract : By using soft and functional materials to deform around objects and adapt to new environments, soft robotics has the potential to revolutionize material handling and terrain navigation. But in the absence of accurate modeling tools, they are still laboriously designed manually. This article reviews progress toward autonomous modeling, simulation, and design.