Automated End-to-End Design and Digital Fabrication of Multi-Task Soft Robots Via Deep Representations
Abstract
This proposal seeks postdoctoral fellowship support for research focused on creating a simulation-driven design pipeline that couples automated in silico co-design with digital fabrication of multifunctional soft robots. The proposed pipeline will automatically synthesize candidate robot designs with optimal trade-offs between desired functional outputs. The robot designs will be co-optimized for specific tasks, yet no aspect of the robot shape or behavior will be prescribe a priori. Rather, a digital instruction set will emerge from this design algorithm that can be 3D printed and tested rapidly. The ultimate goal is to create a pipeline with a 48 h design-to-fabrication cycle for soft robots.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Nov 05, 2021
- Source ID
- HR00112110007
Entities
People
- Jennifer A. Lewis
Organizations
- Defense Advanced Research Projects Agency
- President and Fellows of Harvard College