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

Tags

Fields of Study

  • Computer science

Readers

  • Distributed Systems and Data Platform Development
  • Research Science/Academic Research
  • Robotics and Automation.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • AI & ML - Neural Networks
  • Autonomy