Modular Controllers Facilitate the Co-Optimization of Morphology and Control in Soft Robots

Presenter's Name(s)

Alican Mertan

Conference Year

2023

Abstract

Soft robotics is a rapidly growing area that would benefit from design automation. A major hurdle limiting co-optimization is the fragile specialization between a robot's controller and the particular body plan it controls. Here we posit that modular controllers are more robust to changes to a robot’s body. Moreover, we show that the increased transferability enables more effective brain-body co-evolution, resulting in higher overall performance. We hope that this work helps provide specific methods to improve soft robot design automation in this particular setting, while also providing evidence to support our understanding of the challenges of brain-body co-optimization more generally.

Primary Faculty Mentor Name

Nick Cheney

Status

Graduate

Student College

Graduate College

Program/Major

Computer Science

Primary Research Category

Engineering and Math Science

Abstract only.

Share

COinS
 

Modular Controllers Facilitate the Co-Optimization of Morphology and Control in Soft Robots

Soft robotics is a rapidly growing area that would benefit from design automation. A major hurdle limiting co-optimization is the fragile specialization between a robot's controller and the particular body plan it controls. Here we posit that modular controllers are more robust to changes to a robot’s body. Moreover, we show that the increased transferability enables more effective brain-body co-evolution, resulting in higher overall performance. We hope that this work helps provide specific methods to improve soft robot design automation in this particular setting, while also providing evidence to support our understanding of the challenges of brain-body co-optimization more generally.