Co-Optimization and Co-Learning Methods for Automated Design of Rigid and Soft Robots
Nature demonstrates an incredible diversity, capability, and complexity of life, with organisms that can robustly run, jump, and swim. Compared with their biological brethren, robotic "life" lacks rich dexterity or economy of motion, and their plainly simple designs indicate room for impr...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
Massachusetts Institute of Technology
2022
|
| Online Access: | https://hdl.handle.net/1721.1/140163 https://orcid.org/0000-0002-6937-6204 |
| _version_ | 1826209491593461760 |
|---|---|
| author | Spielberg, Andrew Everett |
| author2 | Rus, Daniela L. |
| author_facet | Rus, Daniela L. Spielberg, Andrew Everett |
| author_sort | Spielberg, Andrew Everett |
| collection | MIT |
| description | Nature demonstrates an incredible diversity, capability, and complexity of life, with organisms that can robustly run, jump, and swim. Compared with their biological brethren, robotic "life" lacks rich dexterity or economy of motion, and their plainly simple designs indicate room for improvement. Unfortunately, a major barrier to creating similarly adept robots is the design process itself. Each aspect of robot design, including the (physical) body (e.g. actuation, sensing, geometry, materials) and the (cyber) brain (e.g. control, proprioception) is typically not integrated in a single design workflow, and a lack of fast, accurate, useful simulators leads to expensive, spiraling, hardware intensive iteration. This thesis introduces methods to marry all aspects of robot design into combined algorithms for holistic cyberphysical design. Core to this solution is co-optimization and co-learning methods which can simultaneously reason about different design domains and achieve locally optimal performance. This thesis further discusses considerations in modeling (via differentiable simulation) and realizability (through automated and semi-automated fabrication worfklows). We describe how this entire suite of capabilities from modeling to automated fabrication can be conceptualized in a complete end-to-end "robot design stack," providing full CAD-CAM computational design capabilities. We demonstrate these capabilities on for rigid, compliant, and soft robot design tasks, including locomotion, manipulation, and tactile sensing, and discuss the frontiers of this burgeoning field of computational robot design. |
| first_indexed | 2024-09-23T14:23:20Z |
| format | Thesis |
| id | mit-1721.1/140163 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T14:23:20Z |
| publishDate | 2022 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1401632022-02-08T03:21:02Z Co-Optimization and Co-Learning Methods for Automated Design of Rigid and Soft Robots Spielberg, Andrew Everett Rus, Daniela L. Matusik, Wojciech Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Nature demonstrates an incredible diversity, capability, and complexity of life, with organisms that can robustly run, jump, and swim. Compared with their biological brethren, robotic "life" lacks rich dexterity or economy of motion, and their plainly simple designs indicate room for improvement. Unfortunately, a major barrier to creating similarly adept robots is the design process itself. Each aspect of robot design, including the (physical) body (e.g. actuation, sensing, geometry, materials) and the (cyber) brain (e.g. control, proprioception) is typically not integrated in a single design workflow, and a lack of fast, accurate, useful simulators leads to expensive, spiraling, hardware intensive iteration. This thesis introduces methods to marry all aspects of robot design into combined algorithms for holistic cyberphysical design. Core to this solution is co-optimization and co-learning methods which can simultaneously reason about different design domains and achieve locally optimal performance. This thesis further discusses considerations in modeling (via differentiable simulation) and realizability (through automated and semi-automated fabrication worfklows). We describe how this entire suite of capabilities from modeling to automated fabrication can be conceptualized in a complete end-to-end "robot design stack," providing full CAD-CAM computational design capabilities. We demonstrate these capabilities on for rigid, compliant, and soft robot design tasks, including locomotion, manipulation, and tactile sensing, and discuss the frontiers of this burgeoning field of computational robot design. Ph.D. 2022-02-07T15:27:49Z 2022-02-07T15:27:49Z 2021-09 2021-09-21T19:30:18.170Z Thesis https://hdl.handle.net/1721.1/140163 https://orcid.org/0000-0002-6937-6204 In Copyright - Educational Use Permitted Copyright retained by author(s) https://rightsstatements.org/page/InC-EDU/1.0/ application/pdf Massachusetts Institute of Technology |
| spellingShingle | Spielberg, Andrew Everett Co-Optimization and Co-Learning Methods for Automated Design of Rigid and Soft Robots |
| title | Co-Optimization and Co-Learning Methods for Automated Design of Rigid and Soft Robots |
| title_full | Co-Optimization and Co-Learning Methods for Automated Design of Rigid and Soft Robots |
| title_fullStr | Co-Optimization and Co-Learning Methods for Automated Design of Rigid and Soft Robots |
| title_full_unstemmed | Co-Optimization and Co-Learning Methods for Automated Design of Rigid and Soft Robots |
| title_short | Co-Optimization and Co-Learning Methods for Automated Design of Rigid and Soft Robots |
| title_sort | co optimization and co learning methods for automated design of rigid and soft robots |
| url | https://hdl.handle.net/1721.1/140163 https://orcid.org/0000-0002-6937-6204 |
| work_keys_str_mv | AT spielbergandreweverett cooptimizationandcolearningmethodsforautomateddesignofrigidandsoftrobots |