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