Conference proceeding
A Manifold Operator Representation for Adaptive Design
PROCEEDINGS OF THE FOURTEENTH INTERNATIONAL CONFERENCE ON GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, pp.529-536
01/01/2012
DOI: 10.1145/2330163.2330239
Abstract
Many natural organisms exhibit canalization: small genetic changes are accommodated by adaptation in other systems that interact with them. Engineered systems, however, are typically quite brittle, making design automation extremely difficult. We propose to address this problem with a generative representation of design based on manifold operators. The operator set we propose combines the intuitive simplicity of top-down rewrite rules with the flexibility and distortion tolerance of bottom-up GRN-based models. An embryogeny specified using this representation thus places constraints on a developing design, rather than specifying a fixed body plan, allowing canalization processes to modulate the design as it continues to develop. We demonstrate our ideas in the domain of electromechanical design and validate them with simulations at different levels of abstraction.
Details
- Title: Subtitle
- A Manifold Operator Representation for Adaptive Design
- Creators
- Jacob Beal - Raytheon BBN Technol, Cambridge, MA 02138 USAHala Mostafa - Raytheon BBN Technol, Cambridge, MA 02138 USAAnnan Mozeika - iRobotBenjamin Axelrod - iRobotAaron Adler - RaytheonGretchen Markiewicz - Raytheon BBN Technol, Cambridge, MA 02138 USA
- Contributors
- T Soule (Editor)
- Resource Type
- Conference proceeding
- Publication Details
- PROCEEDINGS OF THE FOURTEENTH INTERNATIONAL CONFERENCE ON GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, pp.529-536
- Publisher
- Assoc Computing Machinery
- DOI
- 10.1145/2330163.2330239
- Number of pages
- 8
- Language
- English
- Date published
- 01/01/2012
- Academic Unit
- Electrical and Computer Engineering
- Record Identifier
- 9984627320502771
Metrics
1 Record Views